Simultaneous Deep Transfer Across Domains and Tasks
This addresses the challenge of limited labeled data for fine-tuning deep models in new domains, which is critical for applications where labeled data is scarce.
The paper tackles the problem of dataset bias in deep CNN models by proposing a new architecture that simultaneously optimizes for domain invariance and uses soft label distribution matching to transfer information between tasks, achieving state-of-the-art performance on two standard benchmark visual domain adaptation tasks.
Recent reports suggest that a generic supervised deep CNN model trained on a large-scale dataset reduces, but does not remove, dataset bias. Fine-tuning deep models in a new domain can require a significant amount of labeled data, which for many applications is simply not available. We propose a new CNN architecture to exploit unlabeled and sparsely labeled target domain data. Our approach simultaneously optimizes for domain invariance to facilitate domain transfer and uses a soft label distribution matching loss to transfer information between tasks. Our proposed adaptation method offers empirical performance which exceeds previously published results on two standard benchmark visual domain adaptation tasks, evaluated across supervised and semi-supervised adaptation settings.