Open Set Domain Recognition via Attention-Based GCN and Semantic Matching Optimization

TL;DR

This paper introduces an end-to-end attention-based GCN model with semantic matching optimization for open set domain recognition, effectively classifying known and unknown target domain samples despite domain discrepancies.

Contribution

It proposes a novel attention-based GCN and semantic matching approach to improve open set recognition across domains, addressing domain discrepancy and unknown class detection.

Findings

Superior recognition of known and unknown classes demonstrated

Effective adaptation to various target domain openness levels

Bridges domain gap through semantic matching optimization

Abstract

Open set domain recognition has got the attention in recent years. The task aims to specifically classify each sample in the practical unlabeled target domain, which consists of all known classes in the manually labeled source domain and target-specific unknown categories. The absence of annotated training data or auxiliary attribute information for unknown categories makes this task especially difficult. Moreover, exiting domain discrepancy in label space and data distribution further distracts the knowledge transferred from known classes to unknown classes. To address these issues, this work presents an end-to-end model based on attention-based GCN and semantic matching optimization, which first employs the attention mechanism to enable the central node to learn more discriminating representations from its neighbors in the knowledge graph. Moreover, a coarse-to-fine semantic matching optimization approach is proposed to progressively bridge the domain gap. Experimental results validate that the proposed model not only has superiority on recognizing the images of known and unknown classes, but also can adapt to various openness of the target domain.