ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection

Abstract

Recent camouflaged object detection (COD) attempts to segment objects visually blended into their surroundings, which is extremely complex and difficult in real-world scenarios. Apart from the high intrinsic similarity between camouflaged objects and their background, objects are usually diverse in scale, fuzzy in appearance, and even severely occluded. To this end, we propose an effective unified collaborative pyramid network that mimics human behavior when observing vague images and videos, \ie zooming in and out. Specifically, our approach employs the zooming strategy to learn discriminative mixed-scale semantics by the multi-head scale integration and rich granularity perception units, which are designed to fully explore imperceptible clues between candidate objects and background surroundings. The former's intrinsic multi-head aggregation provides more diverse visual patterns. The latter's routing mechanism can effectively propagate inter-frame differences in spatiotemporal scenarios and be adaptively deactivated and output all-zero results for static representations. They provide a solid foundation for realizing a unified architecture for static and dynamic COD. Moreover, considering the uncertainty and ambiguity derived from indistinguishable textures, we construct a simple yet effective regularization, uncertainty awareness loss, to encourage predictions with higher confidence in candidate regions. Our highly task-friendly framework consistently outperforms existing state-of-the-art methods in image and video COD benchmarks. Our code can be found at {https://github.com/lartpang/ZoomNeXt}.

arXiv commentExtensions to the conference version accepted by TPAMI 2024. Fixed value errors. arXiv admin note: substantial text overlap with arXiv:2203.02688

References in corpus (20)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Res2Net: A New Multi-scale Backbone Architecture
• Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
• Fully Convolutional Networks for Semantic Segmentation
• PVT v2: Improved Baselines with Pyramid Vision Transformer
• Concealed Object Detection
• Anabranch Network for Camouflaged Object Segmentation
• Salient Object Detection: A Survey
• Boundary-Guided Camouflaged Object Detection
• Deep Gradient Learning for Efficient Camouflaged Object Detection
• Video Polyp Segmentation: A Deep Learning Perspective
• Progressively Normalized Self-Attention Network for Video Polyp Segmentation
• MirrorNet: Bio-Inspired Camouflaged Object Segmentation
• Advances in Deep Concealed Scene Understanding
• Simultaneously Localize, Segment and Rank the Camouflaged Objects
• CamoFormer: Masked Separable Attention for Camouflaged Object Detection
• Trichomonas Vaginalis Segmentation in Microscope Images
• Self-Supervised Pretraining for RGB-D Salient Object Detection
• Cross-token Modeling with Conditional Computation
• It's Moving! A Probabilistic Model for Causal Motion Segmentation in Moving Camera Videos

Cited by in corpus (4)

• Towards Real Zero-Shot Camouflaged Object Segmentation without Camouflaged Annotations
• Weakly Supervised Camouflaged Object Detection Based on the SAM Model and Mask Guidance
• Fine-grained spatial-temporal perception for gas leak segmentation
• CamoNAS: Neural Architecture Search for Enhanced Camouflaged Object Detection