Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Grouping

About

Weakly-Supervised Concealed Object Segmentation (WSCOS) aims to segment objects well blended with surrounding environments using sparsely-annotated data for model training. It remains a challenging task since (1) it is hard to distinguish concealed objects from the background due to the intrinsic similarity and (2) the sparsely-annotated training data only provide weak supervision for model learning. In this paper, we propose a new WSCOS method to address these two challenges. To tackle the intrinsic similarity challenge, we design a multi-scale feature grouping module that first groups features at different granularities and then aggregates these grouping results. By grouping similar features together, it encourages segmentation coherence, helping obtain complete segmentation results for both single and multiple-object images. For the weak supervision challenge, we utilize the recently-proposed vision foundation model, Segment Anything Model (SAM), and use the provided sparse annotations as prompts to generate segmentation masks, which are used to train the model. To alleviate the impact of low-quality segmentation masks, we further propose a series of strategies, including multi-augmentation result ensemble, entropy-based pixel-level weighting, and entropy-based image-level selection. These strategies help provide more reliable supervision to train the segmentation model. We verify the effectiveness of our method on various WSCOS tasks, and experiments demonstrate that our method achieves state-of-the-art performance on these tasks.

Chunming He, Kai Li, Yachao Zhang, Guoxia Xu, Longxiang Tang, Yulun Zhang, Zhenhua Guo, Xiu Li• 2023

Related benchmarks

TaskDatasetResultRank
Camouflaged Object DetectionCOD10K (test)
S-measure (S_alpha)0.813
174
Polyp SegmentationETIS (test)
Mean Dice6.6
86
Camouflaged Object DetectionCAMO (test)
S_alpha0.759
85
Polyp SegmentationKvasir (test)--
73
Polyp SegmentationCVC-ColonDB (test)--
62
Camouflaged Object DetectionChameleon (test)
F-beta Score0.797
59
Camouflaged Object DetectionNC4K (test)--
57
Camouflaged Object DetectionCOD10K 1.0 (test)
MAE0.038
23
Camouflaged Object DetectionCAMO 1.0 (test)
MAE0.092
23
Camouflaged Object DetectionCOD10K 14 (test)
M Score3.8
21
Showing 10 of 15 rows

Other info

Follow for update