Pre-train, Adapt and Detect: Multi-Task Adapter Tuning for Camouflaged Object Detection

TL;DR

This paper introduces a novel multi-task adapter tuning approach for camouflaged object detection, leveraging large pre-trained models and multi-task learning to improve detection accuracy and generalization across challenging datasets.

Contribution

It proposes a new 'pre-train, adapt and detect' paradigm with a lightweight adapter and multi-task learning scheme, enhancing camouflaged object detection performance and generalization.

Findings

Outperforms state-of-the-art COD models on four benchmarks.

Multi-task adapter tuning improves model generalization.

The method effectively leverages multi-modal pre-training knowledge.

Abstract

Camouflaged object detection (COD), aiming to segment camouflaged objects which exhibit similar patterns with the background, is a challenging task. Most existing works are dedicated to establishing specialized modules to identify camouflaged objects with complete and fine details, while the boundary can not be well located for the lack of object-related semantics. In this paper, we propose a novel ``pre-train, adapt and detect" paradigm to detect camouflaged objects. By introducing a large pre-trained model, abundant knowledge learned from massive multi-modal data can be directly transferred to COD. A lightweight parallel adapter is inserted to adjust the features suitable for the downstream COD task. Extensive experiments on four challenging benchmark datasets demonstrate that our method outperforms existing state-of-the-art COD models by large margins. Moreover, we design a multi-task learning scheme for tuning the adapter to exploit the shareable knowledge across different semantic classes. Comprehensive experimental results showed that the generalization ability of our model can be substantially improved with multi-task adapter initialization on source tasks and multi-task adaptation on target tasks.