Domain Generalization for Object Recognition with Multi-task Autoencoders

TLDR

Domain generalization seeks to transfer knowledge learned from multiple related domains to unseen target domains. This work introduces the Multi‑Task Autoencoder (MTAE) to improve cross‑domain object recognition. MTAE extends denoising autoencoders by replacing artificial corruption with natural inter‑domain variability, learning to map an image to analogs in multiple domains and producing features that are robust to domain shifts, which are then fed to a classifier. On benchmark image recognition datasets, MTAE outperforms other autoencoder‑based models and the current state‑of‑the‑art domain generalization algorithms.

Abstract

The problem of domain generalization is to take knowledge acquired from a number of related domains, where training data is available, and to then successfully apply it to previously unseen domains. We propose a new feature learning algorithm, Multi-Task Autoencoder (MTAE), that provides good generalization performance for cross-domain object recognition. The algorithm extends the standard denoising autoencoder framework by substituting artificially induced corruption with naturally occurring inter-domain variability in the appearance of objects. Instead of reconstructing images from noisy versions, MTAE learns to transform the original image into analogs in multiple related domains. It thereby learns features that are robust to variations across domains. The learnt features are then used as inputs to a classifier. We evaluated the performance of the algorithm on benchmark image recognition datasets, where the task is to learn features from multiple datasets and to then predict the image label from unseen datasets. We found that (denoising) MTAE outperforms alternative autoencoder-based models as well as the current state-of-the-art algorithms for domain generalization.