Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration Network

TL;DR

This paper introduces ERRNet, an edge-based reversible re-calibration network inspired by biological vision, which effectively detects camouflaged objects by modeling visual perception and integrating diverse priors, outperforming existing methods in accuracy and speed.

Contribution

The paper proposes a novel ERRNet with SEA and RRU modules that enhance camouflaged object detection by modeling visual perception and incorporating comprehensive priors, achieving superior performance.

Findings

ERRNet outperforms state-of-the-art models on multiple datasets.

ERRNet achieves approximately 6% improvement in mean E-measure over SINet.

ERRNet operates at 79.3 FPS, demonstrating high efficiency.

Abstract

Camouflaged Object Detection (COD) aims to detect objects with similar patterns (e.g., texture, intensity, colour, etc) to their surroundings, and recently has attracted growing research interest. As camouflaged objects often present very ambiguous boundaries, how to determine object locations as well as their weak boundaries is challenging and also the key to this task. Inspired by the biological visual perception process when a human observer discovers camouflaged objects, this paper proposes a novel edge-based reversible re-calibration network called ERRNet. Our model is characterized by two innovative designs, namely Selective Edge Aggregation (SEA) and Reversible Re-calibration Unit (RRU), which aim to model the visual perception behaviour and achieve effective edge prior and cross-comparison between potential camouflaged regions and background. More importantly, RRU incorporates diverse priors with more comprehensive information comparing to existing COD models. Experimental results show that ERRNet outperforms existing cutting-edge baselines on three COD datasets and five medical image segmentation datasets. Especially, compared with the existing top-1 model SINet, ERRNet significantly improves the performance by $\sim$6% (mean E-measure) with notably high speed (79.3 FPS), showing that ERRNet could be a general and robust solution for the COD task.