Cross-level Attention with Overlapped Windows for Camouflaged Object Detection

TL;DR

This paper introduces OWinCA, a novel cross-level attention mechanism using overlapped windows to enhance low-level features for improved camouflaged object detection, significantly outperforming existing methods.

Contribution

The paper proposes a new overlapped window cross-level attention (OWinCA) to better enhance low-level features guided by high-level semantics for camouflaged object detection.

Findings

OWinCANet outperforms state-of-the-art COD methods on three datasets.

The overlapped window strategy improves global information retention.

Enhanced low-level features lead to more accurate camouflaged object segmentation.

Abstract

Camouflaged objects adaptively fit their color and texture with the environment, which makes them indistinguishable from the surroundings. Current methods revealed that high-level semantic features can highlight the differences between camouflaged objects and the backgrounds. Consequently, they integrate high-level semantic features with low-level detailed features for accurate camouflaged object detection (COD). Unlike previous designs for multi-level feature fusion, we state that enhancing low-level features is more impending for COD. In this paper, we propose an overlapped window cross-level attention (OWinCA) to achieve the low-level feature enhancement guided by the highest-level features. By sliding an aligned window pair on both the highest- and low-level feature maps, the high-level semantics are explicitly integrated into the low-level details via cross-level attention. Additionally, it employs an overlapped window partition strategy to alleviate the incoherence among windows, which prevents the loss of global information. These adoptions enable the proposed OWinCA to enhance low-level features by promoting the separability of camouflaged objects. The associated proposed OWinCANet fuses these enhanced multi-level features by simple convolution operation to achieve the final COD. Experiments conducted on three large-scale COD datasets demonstrate that our OWinCANet significantly surpasses the current state-of-the-art COD methods.