Total: 333
Generalized zero-shot learning (GZSL) is a challenging task that aims to recognize not only unseen classes unavailable during training, but also seen classes used at training stage. It is achieved by transferring knowledge from seen classes to unseen classes via a shared semantic space (e.g. attribute space). Most existing GZSL methods usually learn a cross-modal mapping between the visual feature space and the semantic space. However, the mapping model learned only from the seen classes will produce an inherent bias when used in the unseen classes. In order to tackle such a problem, this paper integrates a deep embedding network (DE) and a modified variational autoencoder (VAE) into a novel model (DE-VAE) to learn a latent space shared by both image features and class embeddings. Specifically, the proposed model firstly employs DE to learn the mapping from the semantic space to the visual feature space, and then utilizes VAE to transform both original visual features and the features obtained by the mapping into latent features. Finally, the latent features are used to train a softmax classifier. Extensive experiments on four GZSL benchmark datasets show that the proposed model significantly outperforms the state of the arts.
Scene flow is a challenging task aimed at jointly estimating the 3D structure and motion of the sensed environment. Although deep learning solutions achieve outstanding performance in terms of accuracy, these approaches divide the whole problem into standalone tasks (stereo and optical flow) addressing them with independent networks. Such a strategy dramatically increases the complexity of the training procedure and requires power-hungry GPUs to infer scene flow barely at 1 FPS. Conversely, we propose DWARF, a novel and lightweight architecture able to infer full scene flow jointly reasoning about depth and optical flow easily and elegantly trainable end-to-end from scratch. Moreover, since ground truth images for full scene flow are scarce, we propose to leverage on the knowledge learned by networks specialized in stereo or flow, for which much more data are available, to distill proxy annotations. Exhaustive experiments show that i) DWARF runs at about 10 FPS on a single high-end GPU and about 1 FPS on NVIDIA Jetson TX2 embedded at KITTI resolution, with moderate drop in accuracy compared to 10× deeper models, ii) learning from many distilled samples is more effective than from the few, annotated ones available.
The key challenge in photorealistic style transfer is that an algorithm should faithfully transfer the style of a reference photo to a content photo while the generated image should look like one captured by a camera. Although several photorealistic style transfer algorithms have been proposed, they need to rely on post- and/or pre-processing to make the generated images look photorealistic. If we disable the additional processing, these algorithms would fail to produce plausible photorealistic stylization in terms of detail preservation and photorealism. In this work, we propose an effective solution to these issues. Our method consists of a construction step (C-step) to build a photorealistic stylization network and a pruning step (P-step) for acceleration. In the C-step, we propose a dense auto-encoder named PhotoNet based on a carefully designed pre-analysis. PhotoNet integrates a feature aggregation module (BFA) and instance normalized skip links (INSL). To generate faithful stylization, we introduce multiple style transfer modules in the decoder and INSLs. PhotoNet significantly outperforms existing algorithms in terms of both efficiency and effectiveness. In the P-step, we adopt a neural architecture search method to accelerate PhotoNet. We propose an automatic network pruning framework in the manner of teacher-student learning for photorealistic stylization. The network architecture named PhotoNAS resulted from the search achieves significant acceleration over PhotoNet while keeping the stylization effects almost intact. We conduct extensive experiments on both image and video transfer. The results show that our method can produce favorable results while achieving 20-30 times acceleration in comparison with the existing state-of-the-art approaches. It is worth noting that the proposed algorithm accomplishes better performance without any pre- or post-processing.
Existing co-localization techniques significantly lose performance over weakly or fully supervised methods in accuracy and inference time. In this paper, we overcome common drawbacks of co-localization techniques by utilizing self-supervised learning approach. The major technical contributions of the proposed method are two-fold. 1) We devise a new geometric transformation, namely point symmetric transformation and utilize its parameters as an artificial label for self-supervised learning. This new transformation can also play the role of region-drop based regularization. 2) We suggest a heat map extraction method for computing the heat map from the network trained by self-supervision, namely class-agnostic activation mapping. It is done by computing the spatial attention map. Based on extensive evaluations, we observe that the proposed method records new state-of-the-art performance in three fine-grained datasets for unsupervised object localization. Moreover, we show that the idea of the proposed method can be adopted in a modified manner to solve the weakly supervised object localization task. As a result, we outperform the current state-of-the-art technique in weakly supervised object localization by a significant gap.
We present an approach for detecting human-object interactions (HOIs) in images, based on the idea that humans interact with functionally similar objects in a similar manner. The proposed model is simple and efficiently uses the data, visual features of the human, relative spatial orientation of the human and the object, and the knowledge that functionally similar objects take part in similar interactions with humans. We provide extensive experimental validation for our approach and demonstrate state-of-the-art results for HOI detection. On the HICO-Det dataset our method achieves a gain of over 2.5% absolute points in mean average precision (mAP) over state-of-the-art. We also show that our approach leads to significant performance gains for zero-shot HOI detection in the seen object setting. We further demonstrate that using a generic object detector, our model can generalize to interactions involving previously unseen objects.
The prominence of deep learning, large amount of annotated data and increasingly powerful hardware made it possible to reach remarkable performance for supervised classification tasks, in many cases saturating the training sets. However the resulting models are specialized to a single very specific task and domain. Adapting the learned classification to new domains is a hard problem due to at least three reasons: (1) the new domains and the tasks might be drastically different; (2) there might be very limited amount of annotated data on the new domain and (3) full training of a new model for each new task is prohibitive in terms of computation and memory, due to the sheer number of parameters of deep CNNs. In this paper, we present a method to learn new-domains and tasks incrementally, building on prior knowledge from already learned tasks and without catastrophic forgetting. We do so by jointly parametrizing weights across layers using low-rank Tucker structure. The core is task agnostic while a set of task specific factors are learnt on each new domain. We show that leveraging tensor structure enables better performance than simply using matrix operations. Joint tensor modelling also naturally leverages correlations across different layers. Compared with previous methods which have focused on adapting each layer separately, our approach results in more compact representations for each new task/domain. We apply the proposed method to the 10 datasets of the Visual Decathlon Challenge and show that our method offers on average about 7.5× reduction in number of parameters and competitive performance in terms of both classification accuracy and Decathlon score.
Monocular 3D object detection task aims to predict the 3D bounding boxes of objects based on monocular RGB images. Since the location recovery in 3D space is quite difficult on account of absence of depth information, this paper proposes a novel unified framework which decomposes the detection problem into a structured polygon prediction task and a depth recovery task. Different from the widely studied 2D bounding boxes, the proposed novel structured polygon in the 2D image consists of several projected surfaces of the target object. Compared to the widely-used 3D bounding box proposals, it is shown to be a better representation for 3D detection. In order to inversely project the predicted 2D structured polygon to a cuboid in the 3D physical world, the following depth recovery task uses the object height prior to complete the inverse projection transformation with the given camera projection matrix. Moreover, a fine-grained 3D box refinement scheme is proposed to further rectify the 3D detection results. Experiments are conducted on the challenging KITTI benchmark, in which our method achieves state-of-the-art detection accuracy.
In various clinical scenarios, medical image is crucial in disease diagnosis and treatment. Different modalities of medical images provide complementary information and jointly helps doctors to make accurate clinical decision. However, due to clinical and practical restrictions, certain imaging modalities may be unavailable nor complete. To impute missing data with adequate clinical accuracy, here we propose a framework called self-supervised collaborative learning to synthesize missing modality for medical images. The proposed method comprehensively utilize all available information correlated to the target modality from multi-source-modality images to generate any missing modality in a single model. Different from the existing methods, we introduce an auto-encoder network as a novel, self-supervised constraint, which provides target-modality-specific information to guide generator training. In addition, we design a modality mask vector as the target modality label. With experiments on multiple medical image databases, we demonstrate a great generalization ability as well as specialty of our method compared with other state-of-the-arts.
This paper studies the task of image captioning with novel objects, which only exist in testing images. Intrinsically, this task can reflect the generalization ability of models in understanding and captioning the semantic meanings of visual concepts and objects unseen in training set, sharing the similarity to one/zero-shot learning. The critical difficulty thus comes from that no paired images and sentences of the novel objects can be used to help train the captioning model. Inspired by recent work (Chen et al. 2019b) that boosts one-shot learning by learning to generate various image deformations, we propose learning meta-networks for deforming features for novel object captioning. To this end, we introduce the feature deformation meta-networks (FDM-net), which is trained on source data, and learn to adapt to the novel object features detected by the auxiliary detection model. FDM-net includes two sub-nets: feature deformation, and scene graph sentence reconstruction, which produce the augmented image features and corresponding sentences, respectively. Thus, rather than directly deforming images, FDM-net can efficiently and dynamically enlarge the paired images and texts by learning to deform image features. Extensive experiments are conducted on the widely used novel object captioning dataset, and the results show the effectiveness of our FDM-net. Ablation study and qualitative visualization further give insights of our model.
We formulate a practical yet challenging problem: General Partial Label Learning (GPLL). Compared to the traditional Partial Label Learning (PLL) problem, GPLL relaxes the supervision assumption from instance-level — a label set partially labels an instance — to group-level: 1) a label set partially labels a group of instances, where the within-group instance-label link annotations are missing, and 2) cross-group links are allowed — instances in a group may be partially linked to the label set from another group. Such ambiguous group-level supervision is more practical in real-world scenarios as additional annotation on the instance-level is no longer required, e.g., face-naming in videos where the group consists of faces in a frame, labeled by a name set in the corresponding caption. In this paper, we propose a novel graph convolutional network (GCN) called Dual Bipartite Graph Autoencoder (DB-GAE) to tackle the label ambiguity challenge of GPLL. First, we exploit the cross-group correlations to represent the instance groups as dual bipartite graphs: within-group and cross-group, which reciprocally complements each other to resolve the linking ambiguities. Second, we design a GCN autoencoder to encode and decode them, where the decodings are considered as the refined results. It is worth noting that DB-GAE is self-supervised and transductive, as it only uses the group-level supervision without a separate offline training stage. Extensive experiments on two real-world datasets demonstrate that DB-GAE significantly outperforms the best baseline over absolute 0.159 F1-score and 24.8% accuracy. We further offer analysis on various levels of label ambiguities.
Though saliency detectors has made stunning progress recently. The performances of the state-of-the-art saliency detectors are not acceptable in some confusing areas, e.g., object boundary. We argue that the feature spatial independence should be one of the root cause. This paper explores the ubiquitous relations on the deep features to promote the existing saliency detectors efficiently. We establish the relation by maximizing the mutual information of the deep features of the same category via deep neural networks to break this independence. We introduce a threshold-constrained training pair construction strategy to ensure that we can accurately estimate the relations between different image parts in a self-supervised way. The relation can be utilized to further excavate the salient areas and inhibit confusing backgrounds. The experiments demonstrate that our method can significantly boost the performance of the state-of-the-art saliency detectors on various benchmark datasets. Besides, our model is label-free and extremely efficient. The inference speed is 140 FPS on a single GTX1080 GPU.
Person Search is a challenging task which requires to retrieve a person's image and the corresponding position from an image dataset. It consists of two sub-tasks: pedestrian detection and person re-identification (re-ID). One of the key challenges is to properly combine the two sub-tasks into a unified framework. Existing works usually adopt a straightforward strategy by concatenating a detector and a re-ID model directly, either into an integrated model or into separated models. We argue that simply concatenating detection and re-ID is a sub-optimal solution, and we propose a Hierarchical Online Instance Matching (HOIM) loss which exploits the hierarchical relationship between detection and re-ID to guide the learning of our network. Our novel HOIM loss function harmonizes the objectives of the two sub-tasks and encourages better feature learning. In addition, we improve the loss update policy by introducing Selective Memory Refreshment (SMR) for unlabeled persons, which takes advantage of the potential discrimination power of unlabeled data. From the experiments on two standard person search benchmarks, i.e. CUHK-SYSU and PRW, we achieve state-of-the-art performance, which justifies the effectiveness of our proposed HOIM loss on learning robust features.
Neural architecture search (NAS) can have a significant impact in computer vision by automatically designing optimal neural network architectures for various tasks. A variant, binarized neural architecture search (BNAS), with a search space of binarized convolutions, can produce extremely compressed models. Unfortunately, this area remains largely unexplored. BNAS is more challenging than NAS due to the learning inefficiency caused by optimization requirements and the huge architecture space. To address these issues, we introduce channel sampling and operation space reduction into a differentiable NAS to significantly reduce the cost of searching. This is accomplished through a performance-based strategy used to abandon less potential operations. Two optimization methods for binarized neural networks are used to validate the effectiveness of our BNAS. Extensive experiments demonstrate that the proposed BNAS achieves a performance comparable to NAS on both CIFAR and ImageNet databases. An accuracy of 96.53% vs. 97.22% is achieved on the CIFAR-10 dataset, but with a significantly compressed model, and a 40% faster search than the state-of-the-art PC-DARTS.
Event cameras, which are asynchronous bio-inspired vision sensors, have shown great potential in computer vision and artificial intelligence. However, the application of event cameras to object-level motion estimation or tracking is still in its infancy. The main idea behind this work is to propose a novel deep neural network to learn and regress a parametric object-level motion/transform model for event-based object tracking. To achieve this goal, we propose a synchronous Time-Surface with Linear Time Decay (TSLTD) representation, which effectively encodes the spatio-temporal information of asynchronous retinal events into TSLTD frames with clear motion patterns. We feed the sequence of TSLTD frames to a novel Retinal Motion Regression Network (RMRNet) to perform an end-to-end 5-DoF object motion regression. Our method is compared with state-of-the-art object tracking methods, that are based on conventional cameras or event cameras. The experimental results show the superiority of our method in handling various challenging environments such as fast motion and low illumination conditions.
Recognizing ingredients for a given dish image is at the core of automatic dietary assessment, attracting increasing attention from both industry and academia. Nevertheless, the task is challenging due to the difficulty of collecting and labeling sufficient training data. On one hand, there are hundred thousands of food ingredients in the world, ranging from the common to rare. Collecting training samples for all of the ingredient categories is difficult. On the other hand, as the ingredient appearances exhibit huge visual variance during the food preparation, it requires to collect the training samples under different cooking and cutting methods for robust recognition. Since obtaining sufficient fully annotated training data is not easy, a more practical way of scaling up the recognition is to develop models that are capable of recognizing unseen ingredients. Therefore, in this paper, we target the problem of ingredient recognition with zero training samples. More specifically, we introduce multi-relational GCN (graph convolutional network) that integrates ingredient hierarchy, attribute as well as co-occurrence for zero-shot ingredient recognition. Extensive experiments on both Chinese and Japanese food datasets are performed to demonstrate the superior performance of multi-relational GCN and shed light on zero-shot ingredients recognition.
In this paper, we focus on the task query-based video localization, i.e., localizing a query in a long and untrimmed video. The prevailing solutions for this problem can be grouped into two categories: i) Top-down approach: It pre-cuts the video into a set of moment candidates, then it does classification and regression for each candidate; ii) Bottom-up approach: It injects the whole query content into each video frame, then it predicts the probabilities of each frame as a ground truth segment boundary (i.e., start or end). Both two frameworks have respective shortcomings: the top-down models suffer from heavy computations and they are sensitive to the heuristic rules, while the performance of bottom-up models is behind the performance of top-down counterpart thus far. However, we argue that the performance of bottom-up framework is severely underestimated by current unreasonable designs, including both the backbone and head network. To this end, we design a novel bottom-up model: Graph-FPN with Dense Predictions (GDP). For the backbone, GDP firstly generates a frame feature pyramid to capture multi-level semantics, then it utilizes graph convolution to encode the plentiful scene relationships, which incidentally mitigates the semantic gaps in the multi-scale feature pyramid. For the head network, GDP regards all frames falling in the ground truth segment as the foreground, and each foreground frame regresses the unique distances from its location to bi-directional boundaries. Extensive experiments on two challenging query-based video localization tasks (natural language video localization and video relocalization), involving four challenging benchmarks (TACoS, Charades-STA, ActivityNet Captions, and Activity-VRL), have shown that GDP surpasses the state-of-the-art top-down models.
Few-shot learning is a challenging task that aims at training a classifier for unseen classes with only a few training examples. The main difficulty of few-shot learning lies in the lack of intra-class diversity within insufficient training samples. To alleviate this problem, we propose a novel generative framework, Diversity Transfer Network (DTN), that learns to transfer latent diversities from known categories and composite them with support features to generate diverse samples for novel categories in feature space. The learning problem of the sample generation (i.e., diversity transfer) is solved via minimizing an effective meta-classification loss in a single-stage network, instead of the generative loss in previous works. Besides, an organized auxiliary task co-training over known categories is proposed to stabilize the meta-training process of DTN. We perform extensive experiments and ablation studies on three datasets, i.e., miniImageNet, CIFAR100 and CUB. The results show that DTN, with single-stage training and faster convergence speed, obtains the state-of-the-art results among the feature generation based few-shot learning methods. Code and supplementary material are available at: https://github.com/Yuxin-CV/DTN.
Unsupervised domain Adaptation (UDA) aims to learn and transfer generalized features from a labelled source domain to a target domain without any annotations. Existing methods only aligning high-level representation but without exploiting the complex multi-class structure and local spatial structure. This is problematic as 1) the model is prone to negative transfer when the features from different classes are misaligned; 2) missing the local spatial structure poses a major obstacle in performing the fine-grained feature alignment. In this paper, we integrate the valuable information conveyed in classifier prediction and local feature maps into global feature representation and then perform a single mini-max game to make it domain invariant. In this way, the domain-invariant feature not only describes the holistic representation of the original image but also preserves mode-structure and fine-grained spatial structural information. The feature integration is achieved by estimating and maximizing the mutual information (MI) among the global feature, local feature and classifier prediction simultaneously. As the MI is hard to measure directly in high-dimension spaces, we adopt a new objective function that implicitly maximizes the MI via an effective sampling strategy and a discriminator design. Our STructure-Aware Feature Fusion (STAFF) network achieves the state-of-the-art performances in various UDA datasets.
Few-shot learning aims to learn novel categories from very few samples given some base categories with sufficient training samples. The main challenge of this task is the novel categories are prone to dominated by color, texture, shape of the object or background context (namely specificity), which are distinct for the given few training samples but not common for the corresponding categories (see Figure 1). Fortunately, we find that transferring information of the correlated based categories can help learn the novel concepts and thus avoid the novel concept being dominated by the specificity. Besides, incorporating semantic correlations among different categories can effectively regularize this information transfer. In this work, we represent the semantic correlations in the form of structured knowledge graph and integrate this graph into deep neural networks to promote few-shot learning by a novel Knowledge Graph Transfer Network (KGTN). Specifically, by initializing each node with the classifier weight of the corresponding category, a propagation mechanism is learned to adaptively propagate node message through the graph to explore node interaction and transfer classifier information of the base categories to those of the novel ones. Extensive experiments on the ImageNet dataset show significant performance improvement compared with current leading competitors. Furthermore, we construct an ImageNet-6K dataset that covers larger scale categories, i.e, 6,000 categories, and experiments on this dataset further demonstrate the effectiveness of our proposed model.
Existing image-text matching approaches typically infer the similarity of an image-text pair by capturing and aggregating the affinities between the text and each independent object of the image. However, they ignore the connections between the objects that are semantically related. These objects may collectively determine whether the image corresponds to a text or not. To address this problem, we propose a Dual Path Recurrent Neural Network (DP-RNN) which processes images and sentences symmetrically by recurrent neural networks (RNN). In particular, given an input image-text pair, our model reorders the image objects based on the positions of their most related words in the text. In the same way as extracting the hidden features from word embeddings, the model leverages RNN to extract high-level object features from the reordered object inputs. We validate that the high-level object features contain useful joint information of semantically related objects, which benefit the retrieval task. To compute the image-text similarity, we incorporate a Multi-attention Cross Matching Model into DP-RNN. It aggregates the affinity between objects and words with cross-modality guided attention and self-attention. Our model achieves the state-of-the-art performance on Flickr30K dataset and competitive performance on MS-COCO dataset. Extensive experiments demonstrate the effectiveness of our model.
Pedestrians in videos are usually in a moving state, resulting in serious spatial misalignment like scale variations and pose changes, which makes the video-based person re-identification problem more challenging. To address the above issue, in this paper, we propose a Frame-Guided Region-Aligned model (FGRA) for discriminative representation learning in two steps in an end-to-end manner. Firstly, based on a frame-guided feature learning strategy and a non-parametric alignment module, a novel alignment mechanism is proposed to extract well-aligned region features. Secondly, in order to form a sequence representation, an effective feature aggregation strategy that utilizes temporal alignment score and spatial attention is adopted to fuse region features in the temporal and spatial dimensions, respectively. Experiments are conducted on benchmark datasets to demonstrate the effectiveness of the proposed method to solve the misalignment problem and the superiority of the proposed method to the existing video-based person re-identification methods.
Deep convolutional neural networks have achieved competitive performance in salient object detection, in which how to learn effective and comprehensive features plays a critical role. Most of the previous works mainly adopted multiple-level feature integration yet ignored the gap between different features. Besides, there also exists a dilution process of high-level features as they passed on the top-down pathway. To remedy these issues, we propose a novel network named GCPANet to effectively integrate low-level appearance features, high-level semantic features, and global context features through some progressive context-aware Feature Interweaved Aggregation (FIA) modules and generate the saliency map in a supervised way. Moreover, a Head Attention (HA) module is used to reduce information redundancy and enhance the top layers features by leveraging the spatial and channel-wise attention, and the Self Refinement (SR) module is utilized to further refine and heighten the input features. Furthermore, we design the Global Context Flow (GCF) module to generate the global context information at different stages, which aims to learn the relationship among different salient regions and alleviate the dilution effect of high-level features. Experimental results on six benchmark datasets demonstrate that the proposed approach outperforms the state-of-the-art methods both quantitatively and qualitatively.
Learning to synthesize non-existing frames from the original consecutive video frames is a challenging task. Recent kernel-based interpolation methods predict pixels with a single convolution process to replace the dependency of optical flow. However, when scene motion is larger than the pre-defined kernel size, these methods yield poor results even though they take thousands of neighboring pixels into account. To solve this problem in this paper, we propose to use deformable separable convolution (DSepConv) to adaptively estimate kernels, offsets and masks to allow the network to obtain information with much fewer but more relevant pixels. In addition, we show that the kernel-based methods and conventional flow-based methods are specific instances of the proposed DSepConv. Experimental results demonstrate that our method significantly outperforms the other kernel-based interpolation methods and shows strong performance on par or even better than the state-of-the-art algorithms both qualitatively and quantitatively.
Depth Completion deals with the problem of converting a sparse depth map to a dense one, given the corresponding color image. Convolutional spatial propagation network (CSPN) is one of the state-of-the-art (SoTA) methods of depth completion, which recovers structural details of the scene. In this paper, we propose CSPN++, which further improves its effectiveness and efficiency by learning adaptive convolutional kernel sizes and the number of iterations for the propagation, thus the context and computational resource needed at each pixel could be dynamically assigned upon requests. Specifically, we formulate the learning of the two hyper-parameters as an architecture selection problem where various configurations of kernel sizes and numbers of iterations are first defined, and then a set of soft weighting parameters are trained to either properly assemble or select from the pre-defined configurations at each pixel. In our experiments, we find weighted assembling can lead to significant accuracy improvements, which we referred to as "context-aware CSPN", while weighted selection, "resource-aware CSPN" can reduce the computational resource significantly with similar or better accuracy. Besides, the resource needed for CSPN++ can be adjusted w.r.t. the computational budget automatically. Finally, to avoid the side effects of noise or inaccurate sparse depths, we embed a gated network inside CSPN++, which further improves the performance. We demonstrate the effectiveness of CSPN++ on the KITTI depth completion benchmark, where it significantly improves over CSPN and other SoTA methods 1.
Human gaze is essential for various appealing applications. Aiming at more accurate gaze estimation, a series of recent works propose to utilize face and eye images simultaneously. Nevertheless, face and eye images only serve as independent or parallel feature sources in those works, the intrinsic correlation between their features is overlooked. In this paper we make the following contributions: 1) We propose a coarse-to-fine strategy which estimates a basic gaze direction from face image and refines it with corresponding residual predicted from eye images. 2) Guided by the proposed strategy, we design a framework which introduces a bi-gram model to bridge gaze residual and basic gaze direction, and an attention component to adaptively acquire suitable fine-grained feature. 3) Integrating the above innovations, we construct a coarse-to-fine adaptive network named CA-Net and achieve state-of-the-art performances on MPIIGaze and EyeDiap.