Learning Classifiers of Prototypes and Reciprocal Points for Universal Domain Adaptation

by   Sungsu Hur, et al.

Universal Domain Adaptation aims to transfer the knowledge between the datasets by handling two shifts: domain-shift and category-shift. The main challenge is correctly distinguishing the unknown target samples while adapting the distribution of known class knowledge from source to target. Most existing methods approach this problem by first training the target adapted known classifier and then relying on the single threshold to distinguish unknown target samples. However, this simple threshold-based approach prevents the model from considering the underlying complexities existing between the known and unknown samples in the high-dimensional feature space. In this paper, we propose a new approach in which we use two sets of feature points, namely dual Classifiers for Prototypes and Reciprocals (CPR). Our key idea is to associate each prototype with corresponding known class features while pushing the reciprocals apart from these prototypes to locate them in the potential unknown feature space. The target samples are then classified as unknown if they fall near any reciprocals at test time. To successfully train our framework, we collect the partial, confident target samples that are classified as known or unknown through on our proposed multi-criteria selection. We then additionally apply the entropy loss regularization to them. For further adaptation, we also apply standard consistency regularization that matches the predictions of two different views of the input to make more compact target feature space. We evaluate our proposal, CPR, on three standard benchmarks and achieve comparable or new state-of-the-art results. We also provide extensive ablation experiments to verify our main design choices in our framework.


page 1

page 2

page 3

page 4


OVANet: One-vs-All Network for Universal Domain Adaptation

Universal Domain Adaptation (UNDA) aims to handle both domain-shift and ...

UMAD: Universal Model Adaptation under Domain and Category Shift

Learning to reject unknown samples (not present in the source classes) i...

Towards Adaptive Unknown Authentication for Universal Domain Adaptation by Classifier Paradox

Universal domain adaptation (UniDA) is a general unsupervised domain ada...

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

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

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

Vision systems trained in closed-world scenarios will inevitably fail wh...

A Primer on Domain Adaptation

Standard supervised machine learning assumes that the distribution of th...

Detecting Deepfakes with Self-Blended Images

In this paper, we present novel synthetic training data called self-blen...

Please sign up or login with your details

Forgot password? Click here to reset