Towards Single-Source Domain Generalized Object Detection via Causal Visual Prompts

TL;DR

This paper introduces Cauvis, a novel method using causal visual prompts and dual-branch adapters to improve single-source domain generalized object detection, significantly reducing reliance on spurious features and enhancing robustness.

Contribution

The paper proposes Cauvis, a new approach combining visual prompts and causal disentanglement for better domain generalization in object detection from a single source.

Findings

Achieves 15.9-31.4% performance gains over existing methods.

Enhances robustness in complex interference environments.

Effectively disentangles causal and spurious features.

Abstract

Single-source Domain Generalized Object Detection (SDGOD), as a cutting-edge research topic in computer vision, aims to enhance model generalization capability in unseen target domains through single-source domain training. Current mainstream approaches attempt to mitigate domain discrepancies via data augmentation techniques. However, due to domain shift and limited domain-specific knowledge, models tend to fall into the pitfall of spurious correlations. This manifests as the model's over-reliance on simplistic classification features (e.g., color) rather than essential domain-invariant representations like object contours. To address this critical challenge, we propose the Cauvis (Causal Visual Prompts) method. First, we introduce a Cross-Attention Prompts module that mitigates bias from spurious features by integrating visual prompts with cross-attention. To address the inadequate domain knowledge coverage and spurious feature entanglement in visual prompts for single-domain generalization, we propose a dual-branch adapter that disentangles causal-spurious features while achieving domain adaptation via high-frequency feature extraction. Cauvis achieves state-of-the-art performance with 15.9-31.4% gains over existing domain generalization methods on SDGOD datasets, while exhibiting significant robustness advantages in complex interference environments.