Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ko, Seung Woo, Hong, Joopyo, Kim, Suyoung, Bang, Seungjai, Cho, Sungzoon, Kwak, Nojun, Kim, Hyung-Sin, Lee, Joonseok
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2503.14035
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909541030952960
author Ko, Seung Woo
Hong, Joopyo
Kim, Suyoung
Bang, Seungjai
Cho, Sungzoon
Kwak, Nojun
Kim, Hyung-Sin
Lee, Joonseok
author_facet Ko, Seung Woo
Hong, Joopyo
Kim, Suyoung
Bang, Seungjai
Cho, Sungzoon
Kwak, Nojun
Kim, Hyung-Sin
Lee, Joonseok
contents Camouflaged object detection (COD) aims to generate a fine-grained segmentation map of camouflaged objects hidden in their background. Due to the hidden nature of camouflaged objects, it is essential for the decoder to be tailored to effectively extract proper features of camouflaged objects and extra-carefully generate their complex boundaries. In this paper, we propose a novel architecture that augments the prevalent decoding strategy in COD with Enrich Decoder and Retouch Decoder, which help to generate a fine-grained segmentation map. Specifically, the Enrich Decoder amplifies the channels of features that are important for COD using channel-wise attention. Retouch Decoder further refines the segmentation maps by spatially attending to important pixels, such as the boundary regions. With extensive experiments, we demonstrate that ENTO shows superior performance using various encoders, with the two novel components playing their unique roles that are mutually complementary.
format Preprint
id arxiv_https___arxiv_org_abs_2503_14035
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Revisit to the Decoder for Camouflaged Object Detection
Ko, Seung Woo
Hong, Joopyo
Kim, Suyoung
Bang, Seungjai
Cho, Sungzoon
Kwak, Nojun
Kim, Hyung-Sin
Lee, Joonseok
Computer Vision and Pattern Recognition
Camouflaged object detection (COD) aims to generate a fine-grained segmentation map of camouflaged objects hidden in their background. Due to the hidden nature of camouflaged objects, it is essential for the decoder to be tailored to effectively extract proper features of camouflaged objects and extra-carefully generate their complex boundaries. In this paper, we propose a novel architecture that augments the prevalent decoding strategy in COD with Enrich Decoder and Retouch Decoder, which help to generate a fine-grained segmentation map. Specifically, the Enrich Decoder amplifies the channels of features that are important for COD using channel-wise attention. Retouch Decoder further refines the segmentation maps by spatially attending to important pixels, such as the boundary regions. With extensive experiments, we demonstrate that ENTO shows superior performance using various encoders, with the two novel components playing their unique roles that are mutually complementary.
title A Revisit to the Decoder for Camouflaged Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.14035