Multi-view Adversarial Discriminator: Mine the Non-causal Factors for Object Detection in Unseen Domains

TL;DR

This paper introduces a multi-view adversarial training approach to better isolate causal features for object detection, improving domain generalization by removing non-causal factors across multiple latent spaces.

Contribution

It proposes the Multi-view Adversarial Discriminator (MAD) framework, combining a Spurious Correlations Generator and Multi-View Domain Classifier to enhance domain-invariant feature learning.

Findings

Achieves state-of-the-art results on six benchmarks.

Effectively removes non-causal factors from features.

Improves robustness of object detection in unseen domains.

Abstract

Domain shift degrades the performance of object detection models in practical applications. To alleviate the influence of domain shift, plenty of previous work try to decouple and learn the domain-invariant (common) features from source domains via domain adversarial learning (DAL). However, inspired by causal mechanisms, we find that previous methods ignore the implicit insignificant non-causal factors hidden in the common features. This is mainly due to the single-view nature of DAL. In this work, we present an idea to remove non-causal factors from common features by multi-view adversarial training on source domains, because we observe that such insignificant non-causal factors may still be significant in other latent spaces (views) due to the multi-mode structure of data. To summarize, we propose a Multi-view Adversarial Discriminator (MAD) based domain generalization model, consisting of a Spurious Correlations Generator (SCG) that increases the diversity of source domain by random augmentation and a Multi-View Domain Classifier (MVDC) that maps features to multiple latent spaces, such that the non-causal factors are removed and the domain-invariant features are purified. Extensive experiments on six benchmarks show our MAD obtains state-of-the-art performance.