CATP: Confidence-Aware Token Pruning for Camouflaged Object Detection

TL;DR

This paper introduces CATP, a hierarchical token pruning framework for camouflaged object detection that reduces computational cost while preserving accuracy by focusing on boundary tokens and compensating for pruned information.

Contribution

The paper proposes a novel confidence-aware token pruning method with feature compensation, improving efficiency of Transformer-based COD models without sacrificing accuracy.

Findings

Significant reduction in computational complexity on multiple benchmarks.

Maintains high accuracy comparable to state-of-the-art methods.

Effective boundary-focused token pruning enhances efficiency.

Abstract

Camouflaged Object Detection (COD) aims to segment targets that share extreme textural and structural similarities with their complex environments. Leveraging their capacity for long-range dependency modeling, Transformer-based detectors have become the mainstream approach and achieve state-of-the-art (SoTA) accuracy, yet their substantial computational overhead severely limits practical deployment. To address this, we propose a hierarchical Confidence-Aware Token Pruning framework (CATP) tailored for COD. Our approach hierarchically identifies and discards easily distinguishable tokens from both background and object interiors, focusing computations on critical boundary tokens. To compensate for information loss from pruning, we introduce a dual-path feature compensation mechanism that aggregates contextual knowledge from pruned tokens into enriched features. Extensive experiments on multiple COD benchmarks demonstrate that our method significantly reduces computational complexity while maintaining high accuracy, offering a promising research direction for the efficient deployment of COD models in real-world scenarios. The code will be released.