CVSep 16, 2023

Tightening Classification Boundaries in Open Set Domain Adaptation through Unknown Exploitation

arXiv:2309.08964v14 citationsh-index: 31
Originality Incremental advance
AI Analysis

This work addresses domain adaptation challenges in non-controllable environments with domain and category shifts, offering incremental improvements for computer vision applications.

The paper tackles the Open Set Domain Adaptation problem by proposing a method to tighten classification boundaries using high-confidence unknown instances, achieving absolute gains of up to 1.3% in Accuracy and H-Score on Office-31 and 5.8% in Accuracy and 4.7% in H-Score on Office-Home.

Convolutional Neural Networks (CNNs) have brought revolutionary advances to many research areas due to their capacity of learning from raw data. However, when those methods are applied to non-controllable environments, many different factors can degrade the model's expected performance, such as unlabeled datasets with different levels of domain shift and category shift. Particularly, when both issues occur at the same time, we tackle this challenging setup as Open Set Domain Adaptation (OSDA) problem. In general, existing OSDA approaches focus their efforts only on aligning known classes or, if they already extract possible negative instances, use them as a new category learned with supervision during the course of training. We propose a novel way to improve OSDA approaches by extracting a high-confidence set of unknown instances and using it as a hard constraint to tighten the classification boundaries of OSDA methods. Especially, we adopt a new loss constraint evaluated in three different means, (1) directly with the pristine negative instances; (2) with randomly transformed negatives using data augmentation techniques; and (3) with synthetically generated negatives containing adversarial features. We assessed all approaches in an extensive set of experiments based on OVANet, where we could observe consistent improvements for two public benchmarks, the Office-31 and Office-Home datasets, yielding absolute gains of up to 1.3% for both Accuracy and H-Score on Office-31 and 5.8% for Accuracy and 4.7% for H-Score on Office-Home.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes