VisDA: The Visual Domain Adaptation Challenge

10/18/2017
by   Xingchao Peng, et al.
0

We present the 2017 Visual Domain Adaptation (VisDA) dataset and challenge, a large-scale testbed for unsupervised domain adaptation across visual domains. Unsupervised domain adaptation aims to solve the real-world problem of domain shift, where machine learning models trained on one domain must be transferred and adapted to a novel visual domain without additional supervision. The VisDA2017 challenge is focused on the simulation-to-reality shift and has two associated tasks: image classification and image segmentation. The goal in both tracks is to first train a model on simulated, synthetic data in the source domain and then adapt it to perform well on real image data in the unlabeled test domain. Our dataset is the largest one to date for cross-domain object classification, with over 280K images across 12 categories in the combined training, validation and testing domains. The image segmentation dataset is also large-scale with over 30K images across 18 categories in the three domains. We compare VisDA to existing cross-domain adaptation datasets and provide a baseline performance analysis using various domain adaptation models that are currently popular in the field.

READ FULL TEXT

page 4

page 7

page 12

page 13

page 14

page 15

page 16

page 17

research
09/01/2020

A Review of Single-Source Deep Unsupervised Visual Domain Adaptation

Large-scale labeled training datasets have enabled deep neural networks ...
research
07/23/2021

VisDA-2021 Competition Universal Domain Adaptation to Improve Performance on Out-of-Distribution Data

Progress in machine learning is typically measured by training and testi...
research
06/26/2018

Syn2Real: A New Benchmark forSynthetic-to-Real Visual Domain Adaptation

Unsupervised transfer of object recognition models from synthetic to rea...
research
05/09/2023

Fashion CUT: Unsupervised domain adaptation for visual pattern classification in clothes using synthetic data and pseudo-labels

Accurate product information is critical for e-commerce stores to allow ...
research
11/17/2021

Cryo-shift: Reducing domain shift in cryo-electron subtomograms with unsupervised domain adaptation and randomization

Cryo-Electron Tomography (cryo-ET) is a 3D imaging technology that enabl...
research
12/08/2021

Burn After Reading: Online Adaptation for Cross-domain Streaming Data

In the context of online privacy, many methods propose complex privacy a...
research
08/20/2013

Towards Adapting ImageNet to Reality: Scalable Domain Adaptation with Implicit Low-rank Transformations

Images seen during test time are often not from the same distribution as...

Please sign up or login with your details

Forgot password? Click here to reset