The recent success of deep learning has shown that a deep architecture in conjunction with abundant quantities of labeled training data is the most promising approach for many vision tasks. However, annotating a large-scale dataset for training such deep neural networks is costly and time-consuming, even with the availability of scalable crowdsourcing platforms like Amazon’s Mechanical Turk. As a result, there are relatively few public large-scale datasets (e.g., ImageNet and Places2) from which it is possible to learn generic visual representations from scratch.

Thus, it is unsurprising that there is continued interest in developing novel deep learning systems that trained on low-cost data for image and video recognition tasks. Among different solutions, crawling data from Internet and using the web as a source of supervision for learning deep representations has shown promising performance for a variety of important computer vision applications. However, the datasets and tasks differ in various ways, which makes it difficult to fairly evaluate different solutions, and identify the key issues when learning from web data.

This workshop aims at promoting the advance of learning state-of-the-art visual models directly from the web, and bringing together computer vision researchers in this field. To this end, we release a large scale web image dataset named WebVision or visual understanding by learning from web data. The datasets consists of 16 million of web images crawled from Internet for 5,000 visual concepts. A validation set consists of around 290K images with human annotation will be provided for the convenience of algorithmic development.

Based on this dataset, we also organize the 3rd Challenge on Visual Understanding by Learning from Web Data. The final results will be announced at the workshop, and the winners will be invited to present their approaches at the workshop. An invited paper tack will also be included in the workshop.

==> Call For Challenge Participants and Workshop Posters <==

News 03.03.2019: A benchmark model based on ResNet-50 is released for reference, which achieves 71.49% top5 accuracy on the validation set. Thank Mr. Qin Wang for producing this benchmark model.

News 26.02.2019: The WebVision 2019 challenge will start on March 1st, 2019.

News 03.01.2019: The workshop website is now online.

Important Dates

Challenge Launch Date March 1, 2019
Challenge Submissions Deadline June 7, 2019
Challenge Award Notification June 10, 2019
Paper Submission Deadline May 15, 2019
Paper Notification May 30, 2019
Workshop date (co-located with CVPR'19) June 16, 2019

All deadlines are at 23:59 Pacific Standard Time.

Workshop Overview

The WebVision workshop contains a challenge track and a poster track:

WebVision Challenge Track

Researchers are invited to participate the WebVision challenge, which aims to advance the area of mining knowledge from noisy web images and meta information. The challenge is based on the WebVision 2.0 dataset, which contains a training set, a validation set, and a test set. The training set is downloaded from Web without any human annotation. The validation and test set are human annotated, where the labels of validation data are provided and the labels of test data are withheld. To imitate the setting of learning from web data, the participants are required to learn their models solely on the training set and submit classification results on the test set. In this sense, the validation data and labels could be simply used to validate their models and cannot be used to learn the model weights.

The WebVision dataset provides the web images and their corresponding meta information (e.g., query, title, comments, etc.). Detailed information regarding the dataset can be found at the dataset page. Learning from web data poses several challenges such as

  1. Label Noise: we can infer pseudo-labels for each instance from web metadata. Such labels are inherently noisy due to inconsistency in the metadata, weak because they typically tag concepts at a coarser granularity than required, and incomplete because they are not reliably present.
  2. Better use of meta and cross-modal information: current approaches do not fully exploit either the semantic richness of the available metadata nor do they take advantage of much cross-modal information (e.g., audio and video) present in most web content. Addressing this requires us to consider research issues such as knowledge mining from unstructured data, joint representation learning from both images and language, joint models for audio-visual data, etc.
  3. Transfer Learning: the computer vision community recognizes that it is important to generalize the knowledge learnt from one dataset to new domains and new tasks. Therefore, effectively adapting the visual representations learned from the WebVision dataset to new tasks with low sample complexity is a key issue of significant theoretical interest and practical importance.

Participant are encouraged to design new methods to solve these challenges.

Poster Track

A poster session will be held at the workshop. The goal is to provide a stimulating space for researchers to share their works with scientific peers. We welcome researchers to submit their recent works on any topics related to learning from web data.

  • Submission to the poster paper track does not require participation in the challenge track.
  • The submission can be published or unpublished work, but have to be accessible publicly. We recommend authors to upload their paper on arXiv, but other publicly accessible link is also acceptable.
  • There is no requirement on paper format or page limitation. We recommend the CVPR formatting style with 4-8 pages.
  • The submission will be reviewed by workshop chairs. Accepted papers will be presented at the poster session at the workshop. Note that all accepted papers will be linked on the workshop website, but will NOT appear in the CVPR workshop proceedings.
  • Poster paper are reviewed in a rolling base until the places are fulfilled. Acceptance notification will be sent out once the decision has been made. We encourage people to submit as early as possible. For papers submitted before May 15, 2019, the acceptance notification will be sent out at the latest by May 30, 2019.
  • How to submit? For poster paper submission, please send an email titled with "[WebVision2019 Poster Paper Submission] Your Name - Your Paper Title" to The email should contain the following information
    • Paper Title
    • Author List
    • Keywords
    • Name of Main Contact
    • Email of Main Contact
    • Affiliation of Main Contact
    • Paper URL
  • You can also choose to enclose your submission in the attachment, and we will link it on the workshop website upon acceptance.


General Chairs

Jesse Berent
Abhinav Gupta
Rahul Sukthankar
Luc Van Gool

Program Chairs

Wen Li
Limin Wang
Wei Li
Eirikur Agustsson