Object Detection with OOD Generalizable Neural Architecture Search

Fan Wu, Kaican Li, Jinling Gao, Chensheng Peng, Lanqing HONG, Enze Xie, Zhenguo Li, Nanyang Ye

Keywords: Out-of-Distribution, neural architecture search

Abstract: To improve the Out-of-Distribution (OOD) Generalization on Object Detection, we present a Neural Architecture Search (NAS) framework guided by feature orthogonalization. We believe that the failure to generalize on OOD data is due to the spurious correlations of category-related features and context-related features. The category-related features describe the causal information for predicting the target objects, such as "a car with four wheels'', while the context-related features describe the non-causal information, such as "a car driving at night''. However, due to the distinct data distribution between training and testing sets, the context-related features are often mistaken for causal information. To address this, we aim to automatically discover an optimal architecture that can disentangle the category-related features and the context-related features with a novel weight-based detector head. Both theoretical and experimental results show that the proposed scheme can achieve disentanglement and better performance on both IID and OOD.

Submission Number: 11