DeepAI AI Chat
Log In Sign Up

Distance-based Hyperspherical Classification for Multi-source Open-Set Domain Adaptation

by   Silvia Bucci, et al.
Politecnico di Torino

Vision systems trained in closed-world scenarios will inevitably fail when presented with new environmental conditions, new data distributions and novel classes at deployment time. How to move towards open-world learning is a long standing research question, but the existing solutions mainly focus on specific aspects of the problem (single domain Open-Set, multi-domain Closed-Set), or propose complex strategies which combine multiple losses and manually tuned hyperparameters. In this work we tackle multi-source Open-Set domain adaptation by introducing HyMOS: a straightforward supervised model that exploits the power of contrastive learning and the properties of its hyperspherical feature space to correctly predict known labels on the target, while rejecting samples belonging to any unknown class. HyMOS includes a tailored data balancing to enforce cross-source alignment and introduces style transfer among the instance transformations of contrastive learning for source-target adaptation, avoiding the risk of negative transfer. Finally a self-training strategy refines the model without the need for handcrafted thresholds. We validate our method over three challenging datasets and provide an extensive quantitative and qualitative experimental analysis. The obtained results show that HyMOS outperforms several Open-Set and universal domain adaptation approaches, defining the new state-of-the-art.


page 8

page 9


Unknown-Aware Domain Adversarial Learning for Open-Set Domain Adaptation

Open-Set Domain Adaptation (OSDA) assumes that a target domain contains ...

Learning Factorized Representations for Open-set Domain Adaptation

Domain adaptation for visual recognition has undergone great progress in...

Progressive Graph Learning for Open-Set Domain Adaptation

Domain shift is a fundamental problem in visual recognition which typica...

Transferrable Contrastive Learning for Visual Domain Adaptation

Self-supervised learning (SSL) has recently become the favorite among fe...

On the Effectiveness of Image Rotation for Open Set Domain Adaptation

Open Set Domain Adaptation (OSDA) bridges the domain gap between a label...

Learning Classifiers of Prototypes and Reciprocal Points for Universal Domain Adaptation

Universal Domain Adaptation aims to transfer the knowledge between the d...

Subsidiary Prototype Alignment for Universal Domain Adaptation

Universal Domain Adaptation (UniDA) deals with the problem of knowledge ...

Code Repositories