Can domain adaptation make object recognition work for everyone?
Despite the rapid progress in deep visual recognition, modern computer vision datasets significantly overrepresent the developed world and models trained on such datasets underperform on images from unseen geographies. We investigate the effectiveness of unsupervised domain adaptation (UDA) of such models across geographies at closing this performance gap. To do so, we first curate two shifts from existing datasets to study the Geographical DA problem, and discover new challenges beyond data distribution shift: context shift, wherein object surroundings may change significantly across geographies, and subpopulation shift, wherein the intra-category distributions may shift. We demonstrate the inefficacy of standard DA methods at Geographical DA, highlighting the need for specialized geographical adaptation solutions to address the challenge of making object recognition work for everyone.
Code (0)
등록된 구현이 없습니다.
Tasks
Domain AdaptationObjectObject RecognitionUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
Unsupervised Domain Adaptation through Inter-modal Rotation for RGB-D Object Recognition
Unsupervised Domain Adaptation (DA) exploits the supervision of a label-rich source dataset to make predictions on an unlabeled target dataset by aligning the two data distributions. In robotics, DA is used to take advan…
Domain AdaptationObject CategorizationObject RecognitionUnsupervised Domain AdaptationDomain-robust VQA with diverse datasets and methods but no target labels
The observation that computer vision methods overfit to dataset specifics has inspired diverse attempts to make object recognition models robust to domain shifts. However, similar work on domain-robust visual question an…
Domain AdaptationObject RecognitionQuestion AnsweringUnsupervised Domain Adaptation+2Reshaping Visual Datasets for Domain Adaptation
In visual recognition problems, the common data distribution mismatches between training and testing make domain adaptation essential. However, image data is difficult to manually divide into the discrete domains require…
Activity RecognitionDomain AdaptationHuman Activity RecognitionObject RecognitionDomain Adaptation on the Statistical Manifold
In this paper, we tackle the problem of unsupervised domain adaptation for classification. In the unsupervised scenario where no labeled samples from the target domain are provided, a popular approach consists in transfo…
Domain AdaptationObject RecognitionUnsupervised Domain AdaptationLearning Transferrable Representations for Unsupervised Domain Adaptation
Supervised learning with large scale labelled datasets and deep layered models has caused a paradigm shift in diverse areas in learning and recognition. However, this approach still suffers from generalization issues und…
Domain AdaptationObject RecognitionUnsupervised Domain Adaptation