Reshaping 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 required by adaptation algorithms, and the standard practice of equating datasets with domains is a weak proxy for all the real conditions that alter the statistics in complex ways (lighting, pose, background, resolution, etc.) We propose an approach to automatically discover latent domains in image or video datasets. Our formulation imposes two key properties on domains: maximum distinctiveness and maximum learnability. By maximum distinctiveness, we require the underlying distributions of the identified domains to be different from each other; by maximum learnability, we ensure that a strong discriminative model can be learned from the domain. We devise a nonparametric representation and efficient optimization procedure for distinctiveness, which, when coupled with our learnability constraint, can successfully discover domains among both training and test data. We extensively evaluate our approach on object recognition and human activity recognition tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
Activity RecognitionDomain AdaptationHuman Activity RecognitionObject RecognitionSimilar Papers 제목 키워드 기반
ReshapeGAN: Object Reshaping by Providing A Single Reference Image
The aim of this work is learning to reshape the object in an input image to an arbitrary new shape, by just simply providing a single reference image with an object instance in the desired shape. We propose a new Generat…
AllGenerative Adversarial NetworkObjectStructure-Aware Flow Generation for Human Body Reshaping
Body reshaping is an important procedure in portrait photo retouching. Due to the complicated structure and multifarious appearance of human bodies, existing methods either fall back on the 3D domain via body morphable m…
Photo RetouchingCALDA: Improving Multi-Source Time Series Domain Adaptation with Contrastive Adversarial Learning
Unsupervised domain adaptation (UDA) provides a strategy for improving machine learning performance in data-rich (target) domains where ground truth labels are inaccessible but can be found in related (source) domains. I…
Activity RecognitionContrastive LearningData AugmentationDomain Adaptation+4Cross-Dataset Adaptation for Visual Question Answering
We investigate the problem of cross-dataset adaptation for visual question answering (Visual QA). Our goal is to train a Visual QA model on a source dataset but apply it to another target one. Analogous to domain adaptat…
Domain AdaptationQuestion AnsweringVisual Question AnsweringVisual Question Answering (VQA)EF-Train: Enable Efficient On-device CNN Training on FPGA Through Data Reshaping for Online Adaptation or Personalization
Conventionally, DNN models are trained once in the cloud and deployed in edge devices such as cars, robots, or unmanned aerial vehicles (UAVs) for real-time inference. However, there are many cases that require the model…
Domain Adaptation