Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization

by   Junbao Zhuo, et al.

We address the unsupervised open domain recognition (UODR) problem, where categories in labeled source domain S is only a subset of those in unlabeled target domain T. The task is to correctly classify all samples in T including known and unknown categories. UODR is challenging due to the domain discrepancy, which becomes even harder to bridge when a large number of unknown categories exist in T. Moreover, the classification rules propagated by graph CNN (GCN) may be distracted by unknown categories and lack generalization capability. To measure the domain discrepancy for asymmetric label space between S and T, we propose Semantic-Guided Matching Discrepancy (SGMD), which first employs instance matching between S and T, and then the discrepancy is measured by a weighted feature distance between matched instances. We further design a limited balance constraint to achieve a more balanced classification output on known and unknown categories. We develop Unsupervised Open Domain Transfer Network (UODTN), which learns both the backbone classification network and GCN jointly by reducing the SGMD, enforcing the limited balance constraint and minimizing the classification loss on S. UODTN better preserves the semantic structure and enforces the consistency between the learned domain invariant visual features and the semantic embeddings. Experimental results show superiority of our method on recognizing images of both known and unknown categories.


page 4

page 6

page 7


Towards Novel Target Discovery Through Open-Set Domain Adaptation

Open-set domain adaptation (OSDA) considers that the target domain conta...

Learning Cross-domain Semantic-Visual Relation for Transductive Zero-Shot Learning

Zero-Shot Learning (ZSL) aims to learn recognition models for recognizin...

Open-Set Hypothesis Transfer with Semantic Consistency

Unsupervised open-set domain adaptation (UODA) is a realistic problem wh...

Unsupervised Domain Adaptation in the Wild: Dealing with Asymmetric Label Sets

The goal of domain adaptation is to adapt models learned on a source dom...

Bridging the Theoretical Bound and Deep Algorithms for Open Set Domain Adaptation

In the unsupervised open set domain adaptation (UOSDA), the target domai...

Attention-Aware Age-Agnostic Visual Place Recognition

A cross-domain visual place recognition (VPR) task is proposed in this w...

Neural Network-based Object Classification by Known and Unknown Features (Based on Text Queries)

The article presents a method that improves the quality of classificatio...

Please sign up or login with your details

Forgot password? Click here to reset