Out-distribution aware Self-training in an Open World Setting
Deep Learning heavily depends on large labeled datasets which limits further improvements. While unlabeled data is available in large amounts, in particular in image recognition, it does not fulfill the closed world assumption of semi-supervised learning that all unlabeled data are task-related. The goal of this paper is to leverage unlabeled data in an open world setting to further improve prediction performance. For this purpose, we introduce out-distribution aware self-training, which includes a careful sample selection strategy based on the confidence of the classifier. While normal self-training deteriorates prediction performance, our iterative scheme improves using up to 15 times the amount of originally labeled data. Moreover, our classifiers are by design out-distribution aware and can thus distinguish task-related inputs from unrelated ones.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
The Needle in the haystack: Out-distribution aware Self-training in an Open-World Setting
Traditional semi-supervised learning (SSL) has focused on the closed world assumption where all unlabeled samples are task-related. In practice, this assumption is often violated when leveraging data from very large imag…
Out-of-Distribution DetectionSelf-LearningTowards Open-World Object-based Anomaly Detection via Self-Supervised Outlier Synthesis
Object detection is a pivotal task in computer vision that has received significant attention in previous years. Nonetheless, the capability of a detector to localise objects out of the training distribution remains unex…
Anomaly DetectionObjectobject-detectionObject Detection+1Known-class Aware Self-ensemble for Open Set Domain Adaptation
Existing domain adaptation methods generally assume different domains have the identical label space, which is quite restrict for real-world applications. In this paper, we focus on a more realistic and challenging case …
Domain AdaptationAn Empirical Exploration of Open-Set Recognition via Lightweight Statistical Pipelines
Machine-learned safety-critical systems need to be self-aware and reliably know their unknowns in the open-world. This is often explored through the lens of anomaly/outlier detection or out-of-distribution modeling. One …
open-set classificationOpen Set LearningOutlier DetectionRetrieval+1On the Robustness of Open-World Test-Time Training: Self-Training with Dynamic Prototype Expansion
Generalizing deep learning models to unknown target domain distribution with low latency has motivated research into test-time training/adaptation (TTT/TTA). Existing approaches often focus on improving test-time trainin…