Multi-view Adversarial Discriminator: Mine the Non-causal Factors for Object Detection in Unseen Domains
This work addresses domain generalization for object detection, which is crucial for deploying models in unseen domains, but it appears incremental as it builds on existing adversarial learning methods.
The paper tackles the problem of domain shift degrading object detection models by proposing a Multi-view Adversarial Discriminator (MAD) to remove non-causal factors from domain-invariant features, achieving state-of-the-art performance on six benchmarks.
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.