α-Former: Local-Feature-Aware (L-FA) Transformer

Zhi Xu, Bin Sun, Yue Bai, Yun Fu

Keywords: Camouflaged instance segmentation

Abstract: Despite the success of current segmentation models powered by the transformer, the camouflaged instance segmentation (CIS) task remains a challenge due to the similarity between the target and the background. To address this issue, we propose a novel approach called the local-feature-aware transformer ($\alpha$-Former) that incorporates traditional computer vision descriptors to extract critical edge features in camouflaged instances. Specifically, we introduce an adapter to merge local features into the transformer framework. Using the proposed transformer-based encoder-decoder architecture, our $\alpha$-Former surpasses state-of-the-art performance on the COD10K and NC4K datasets. Additionally, we introduce an edge-aware feature fusion module to improve boundary results in the segmentation model.

Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 3701