paper-with-me

Papers

Reshaping Visual Datasets for Domain Adaptation

2013-12-01 · NeurIPS 2013 12 · Boqing Gong, Kristen Grauman, Fei Sha

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.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Activity RecognitionDomain AdaptationHuman Activity RecognitionObject Recognition

Similar Papers 제목 키워드 기반

ReshapeGAN: Object Reshaping by Providing A Single Reference Image

2019-05-16 · Ziqiang Zheng, Yang Wu, Zhibin Yu, Yang Yang 외

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 NetworkObject

Structure-Aware Flow Generation for Human Body Reshaping

2022-03-09 · CVPR 2022 1 · Jianqiang Ren, Yuan YAO, Biwen Lei, Miaomiao Cui 외

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 Retouching

CALDA: Improving Multi-Source Time Series Domain Adaptation with Contrastive Adversarial Learning

2021-09-30 · Garrett Wilson, Janardhan Rao Doppa, Diane J. Cook

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+4

Cross-Dataset Adaptation for Visual Question Answering

2018-06-10 · CVPR 2018 6 · Wei-Lun Chao, Hexiang Hu, Fei Sha

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

2022-02-18 · Yue Tang, Xinyi Zhang, Peipei Zhou, Jingtong Hu

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