nSldadGGY5@OpenReview

Total: 1

#1 EFDTR: Learnable Elliptical Fourier Descriptor Transformer for Instance Segmentation [PDF2] [Copy] [Kimi] [REL]

Authors: Jiawei Cao, Chaochen Gu, Hao Cheng, Xiaofeng Zhang, Kaijie Wu, Changsheng Lu

Polygon-based object representations efficiently model object boundaries but are limited by high optimization complexity, which hinders their adoption compared to more flexible pixel-based methods. In this paper, we introduce a novel vertex regression loss grounded in Fourier elliptic descriptors, which removes the need for rasterization or heuristic approximations and resolves ambiguities in boundary point assignment through frequency-domain matching.To advance polygon-based instance segmentation, we further propose EFDTR (\textbf{E}lliptical \textbf{F}ourier \textbf{D}escriptor \textbf{Tr}ansformer), an end-to-end learnable framework that leverages the expressiveness of Fourier-based representations. The model achieves precise contour predictions through a two-stage approach: the first stage predicts elliptical Fourier descriptors for global contour modeling, while the second stage refines contours for fine-grained accuracy. Experimental results on the COCO dataset show that EFDTR outperforms existing polygon-based methods, offering a promising alternative to pixel-based approaches. Code is available at \url{https://github.com/chrisclear3/EFDTR}.

Subject: ICML.2025 - Poster