Gradually Vanishing Gap in Prototypical Network for Unsupervised Domain Adaptation

TL;DR

This paper introduces GVG-PN, a novel unsupervised domain adaptation framework that progressively reduces distribution gaps by combining global domain alignment, local feature relationships via GCN, and a contrastive loss, leading to superior performance.

Contribution

The paper proposes a new UDA method that integrates global and local alignment strategies with a pro-contrastive loss to better preserve distribution and semantic structures.

Findings

GVG-PN outperforms state-of-the-art models on multiple benchmarks.

The combination of global and local alignment improves distribution preservation.

Pro-contrastive loss enhances discriminability of feature relationships.

Abstract

Unsupervised domain adaptation (UDA) is a critical problem for transfer learning, which aims to transfer the semantic information from labeled source domain to unlabeled target domain. Recent advancements in UDA models have demonstrated significant generalization capabilities on the target domain. However, the generalization boundary of UDA models remains unclear. When the domain discrepancy is too large, the model can not preserve the distribution structure, leading to distribution collapse during the alignment. To address this challenge, we propose an efficient UDA framework named Gradually Vanishing Gap in Prototypical Network (GVG-PN), which achieves transfer learning from both global and local perspectives. From the global alignment standpoint, our model generates a domain-biased intermediate domain that helps preserve the distribution structures. By entangling cross-domain features, our model progressively reduces the risk of distribution collapse. However, only relying on global alignment is insufficient to preserve the distribution structure. To further enhance the inner relationships of features, we introduce the local perspective. We utilize the graph convolutional network (GCN) as an intuitive method to explore the internal relationships between features, ensuring the preservation of manifold structures and generating domain-biased prototypes. Additionally, we consider the discriminability of the inner relationships between features. We propose a pro-contrastive loss to enhance the discriminability at the prototype level by separating hard negative pairs. By incorporating both GCN and the pro-contrastive loss, our model fully explores fine-grained semantic relationships. Experiments on several UDA benchmarks validated that the proposed GVG-PN can clearly outperform the SOTA models.