TransCoop: Cooperation of Transformers and CNNs for Camouflaged Object Segmentation
Lists
Only you see this
Abstract
Camouflaged object segmentation (COS) is a challenging task due to the existence of high intrinsic similarities between the object and background. To overcome this challenge, we pro-pose a new framework, called TransCoop, for COS through the cooperation of Transformers and convolutional neural net-works (CNNs). Specifically, Transformer is used to model global context and structural information for accurately positioning potential target objects. Meanwhile, a well-designed texture feature fusion module (TFFM) is used to fuse the features encoded by CNN with the shallow Transformer to fully mine the low-level features in the scene. Furthermore, we propose a noise removal module (NRM), which can eliminate the background noise of low-level features with the guidance of precise target location. Notably, our TFFM and NRM can effectively realize the interaction between Transformer and CNN features. Extensive experiments on four benchmark datasets demonstrate the superiority of our TransCoop against existing state-of-the-art methods.
BibTeX
@inproceedings{wu2022transcoop,
author = {Fucai Wu and Xuanya Li and Yuan Zhang and Kai Hu},
title = {{TransCoop: Cooperation of Transformers and CNNs for Camouflaged Object Segmentation}},
booktitle = {ICME},
year = {2022},
url = {https://openreview.net/forum?id=vQnzDXTUwy},
}Loading related content...