Ji Du — accepted AI-conference papers

2025

Beyond Single Images: Retrieval Self-Augmented Unsupervised Camouflaged Object Detection

Ji Du, Xin Wang, Fangwei Hao, Mingyang Yu, Chunyuan Chen, Jiesheng Wu +3

ICCV 2025poster

At the core of Camouflaged Object Detection (COD) lies segmenting objects from their highly similar surroundings. Previous efforts navigate this challenge primarily through image-level modeling or annotation-based optimization. Despite advancing considerably, this commonplace practice hardly taps va…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

Shift the Lens: Environment-Aware Unsupervised Camouflaged Object Detection

Ji Du, Fangwei Hao, Mingyang Yu, Desheng Kong, Jiesheng Wu, Bin Wang +2

CVPR 2025poster

Camouflaged Object Detection (COD) seeks to distinguish objects from their highly similar backgrounds. Existing work has essentially focused on isolating camouflaged objects from the environment, demonstrating ever-improving performance but at the cost of extensive annotations and complex optimizati…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗