CamoFormer: Masked Separable Attention for Camouflaged Object Detection

TL;DR

CamoFormer introduces a masked separable attention mechanism in a Transformer-based model to improve camouflaged object detection, achieving state-of-the-art results by effectively distinguishing objects from complex backgrounds.

Contribution

The paper proposes a novel masked separable attention module and a top-down decoder architecture for enhanced camouflaged object detection.

Findings

CamoFormer outperforms existing methods on three benchmarks.

Achieves around 5% relative improvement in S-measure and weighted F-measure.

Demonstrates the effectiveness of masked separable attention in complex scenes.

Abstract

How to identify and segment camouflaged objects from the background is challenging. Inspired by the multi-head self-attention in Transformers, we present a simple masked separable attention (MSA) for camouflaged object detection. We first separate the multi-head self-attention into three parts, which are responsible for distinguishing the camouflaged objects from the background using different mask strategies. Furthermore, we propose to capture high-resolution semantic representations progressively based on a simple top-down decoder with the proposed MSA to attain precise segmentation results. These structures plus a backbone encoder form a new model, dubbed CamoFormer. Extensive experiments show that CamoFormer surpasses all existing state-of-the-art methods on three widely-used camouflaged object detection benchmarks. There are on average around 5% relative improvements over previous methods in terms of S-measure and weighted F-measure.