ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection

TL;DR

ZoomNeXt introduces a unified pyramid network that mimics human zooming behavior to improve camouflaged object detection in images and videos, effectively handling scale, appearance, and occlusion challenges.

Contribution

The paper proposes a novel collaborative pyramid network with multi-scale integration and uncertainty-aware regularization for static and dynamic camouflaged object detection.

Findings

Outperforms state-of-the-art methods on image COD benchmarks.

Effective in static and dynamic camouflaged object detection.

Utilizes a zooming strategy to learn discriminative features across scales.

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}.