Boosting Novel Category Discovery Over Domains with Soft Contrastive Learning and All-in-One Classifier

TL;DR

This paper introduces SAN, a framework for open-set and universal domain adaptation that uses soft contrastive learning and an all-in-one classifier to improve novel category discovery across domains.

Contribution

The paper proposes SAN, a novel framework combining soft contrastive learning and an all-in-one classifier to enhance novel category discovery in domain adaptation tasks.

Findings

SAN outperforms state-of-the-art methods in ODA and UNDA.

The SCL loss reduces view-noise effects in contrastive learning.

The AIO classifier mitigates overconfidence in novel class detection.

Abstract

Unsupervised domain adaptation (UDA) has proven to be highly effective in transferring knowledge from a label-rich source domain to a label-scarce target domain. However, the presence of additional novel categories in the target domain has led to the development of open-set domain adaptation (ODA) and universal domain adaptation (UNDA). Existing ODA and UNDA methods treat all novel categories as a single, unified unknown class and attempt to detect it during training. However, we found that domain variance can lead to more significant view-noise in unsupervised data augmentation, which affects the effectiveness of contrastive learning (CL) and causes the model to be overconfident in novel category discovery. To address these issues, a framework named Soft-contrastive All-in-one Network (SAN) is proposed for ODA and UNDA tasks. SAN includes a novel data-augmentation-based soft contrastive learning (SCL) loss to fine-tune the backbone for feature transfer and a more human-intuitive classifier to improve new class discovery capability. The SCL loss weakens the adverse effects of the data augmentation view-noise problem which is amplified in domain transfer tasks. The All-in-One (AIO) classifier overcomes the overconfidence problem of current mainstream closed-set and open-set classifiers. Visualization and ablation experiments demonstrate the effectiveness of the proposed innovations. Furthermore, extensive experiment results on ODA and UNDA show that SAN outperforms existing state-of-the-art methods.