UCOD-DPL: Unsupervised Camouflaged Object Detection via Dynamic Pseudo-label Learning
Preprint
Abstract
Unsupervised Camoflaged Object Detection (UCOD) has gained attention since it doesn't need to rely on extensive pixel-level labels. Existing UCOD methods typically generate pseudo-labels using fixed strategies and train 1 x1 convolutional layers as a simple decoder, leading to low performance compared to fully-supervised methods. We emphasize two drawbacks in these approaches: 1). The model is prone to fitting incorrect knowledge due to the pseudo-label containing substantial noise. 2). The simple decoder fails to capture and learn the semantic features of camouflaged objects, especially for small-sized objects, due to the low-resolution pseudo-labels and severe confusion between foreground and background pixels. To this end, we propose a UCOD method with a teacher-student framework via Dynamic Pseudo-label Learning called UCOD-DPL, which contains an Adaptive Pseudo-label Module (APM), a Dual-Branch Adversarial (DBA) decoder, and a Look-Twice mechanism. The APM module adaptively combines pseudo-labels generated by fixed strategies and the teacher model to prevent the model from overfitting incorrect knowledge while preserving the ability for self-correction; the DBA decoder takes adversarial learning of different segmentation objectives, guides the model to overcome the foreground-background confusion of camouflaged objects, and the Look-Twice mechanism mimics the human tendency to zoom in on camouflaged objects and performs secondary refinement on small-sized objects. Extensive experiments show that our method demonstrates outstanding performance, even surpassing some existing fully supervised methods. The code is available now.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- Hierarchical Graph Interaction Transformer With Dynamic Token Clustering for Camouflaged Object DetectionIEEE Transactions on Image Processing, 2024
- GLCONet: Learning Multisource Perception Representation for Camouflaged Object DetectionIEEE Transactions on Neural Networks and Learning Systems, 2024
- ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2024
- Edge-Aware Mirror Network for Camouflaged Object Detection2023
- Frequency-aware Camouflaged Object DetectionACM Transactions on Multimedia Computing, Communications, and Applications, 2023
- Deep Gradient Learning for Efficient Camouflaged Object DetectionMachine Intelligence Research, 2023
- CubeNet: X-shape connection for camouflaged object detectionPattern Recognition, 2022
- Segmentation-based deep-learning approach for surface-defect detectionJournal of Intelligent Manufacturing, 2019
- The Adaptive Significance of Coloration in MammalsBioScience, 2005
- A model of saliency-based visual attention for rapid scene analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998