Advances in deep concealed scene understanding

DP Fan, GP Ji, P Xu, MM Cheng, C Sakaridis… - Visual Intelligence, 2023 - Springer
Concealed scene understanding (CSU) is a hot computer vision topic aiming to perceive
objects exhibiting camouflage. The current boom in terms of techniques and applications …

Camouflaged object detection with feature decomposition and edge reconstruction

C He, K Li, Y Zhang, L Tang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Camouflaged object detection (COD) aims to address the tough issue of identifying
camouflaged objects visually blended into the surrounding backgrounds. COD is a …

Weakly-supervised concealed object segmentation with sam-based pseudo labeling and multi-scale feature grou**

C He, K Li, Y Zhang, G Xu, L Tang… - Advances in …, 2023 - proceedings.neurips.cc
Abstract Weakly-Supervised Concealed Object Segmentation (WSCOS) aims to segment
objects well blended with surrounding environments using sparsely-annotated data for …

Segment anything is not always perfect: An investigation of sam on different real-world applications

W Ji, J Li, Q Bi, T Liu, W Li, L Cheng - 2024 - Springer
Abstract Recently, Meta AI Research approaches a general, promptable segment anything
model (SAM) pre-trained on an unprecedentedly large segmentation dataset (SA-1B) …

A systematic review of image-level camouflaged object detection with deep learning

Y Liang, G Qin, M Sun, X Wang, J Yan, Z Zhang - Neurocomputing, 2024 - Elsevier
Camouflaged object detection (COD) aims to search and identify disguised objects that are
hidden in their surrounding environment, thereby deceiving the human visual system. As an …

Feature shrinkage pyramid for camouflaged object detection with transformers

Z Huang, H Dai, TZ **ang, S Wang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Vision transformers have recently shown strong global context modeling capabilities in
camouflaged object detection. However, they suffer from two major limitations: less effective …

Can sam segment anything? when sam meets camouflaged object detection

L Tang, H **ao, B Li - arxiv preprint arxiv:2304.04709, 2023 - arxiv.org
SAM is a segmentation model recently released by Meta AI Research and has been gaining
attention quickly due to its impressive performance in generic object segmentation …

Pixels, regions, and objects: Multiple enhancement for salient object detection

Y Wang, R Wang, X Fan, T Wang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Salient object detection (SOD) aims to mimic the human visual system (HVS) and cognition
mechanisms to identify and segment salient objects. However, due to the complexity of …

Deep gradient learning for efficient camouflaged object detection

GP Ji, DP Fan, YC Chou, D Dai, A Liniger… - Machine Intelligence …, 2023 - Springer
This paper introduces deep gradient network (DGNet), a novel deep framework that exploits
object gradient supervision for camouflaged object detection (COD). It decouples the task …

Camoformer: Masked separable attention for camouflaged object detection

B Yin, X Zhang, DP Fan, S Jiao… - … on Pattern Analysis …, 2024 - ieeexplore.ieee.org
How to identify and segment camouflaged objects from the background is challenging.
Inspired by the multi-head self-attention in Transformers, we present a simple masked …