[visionlist] CALL FOR PARTICIPATION - Learning from Limited and Imperfect Data (L2ID) Challenges

Tatiana Tommasi tommasi.t at gmail.com
Mon May 3 06:19:07 -04 2021

*Learning from Limited and Imperfect Data (L2ID) Challenges*
In conjunction with the L2ID Workshop at CVPR 2021
June 20, 2021 (Full Day, Virtual Online)

As part of the CVPR 2021 L2ID workshop, we have two sets of challenges on
weakly supervised learning and multi-domain few-shot classification.
We invite you to participate! Winners will be able to present their works
during the workshop.

Check the rules at https://l2id.github.io/challenge_localization.html

Track 1 - Weakly Supervised Semantic Segmentation
This track targets on learning to perform object semantic segmentation
using image-level annotations as supervision.

Track 2 - Weakly supervised product detection and retrieval
Given a photo containing multiple product instances and a user-provided
description, the track aims to detect the boxes of each product and
retrieve the correct single product image in the gallery.

Track 3 - Weakly-supervised Object Localization
This track targets on making the classification networks be equipped with
the ability of object localization.

Track 4 - High-resolution Human Parsing
This track aims to recognize human parts within high-resolution images by
learning with low-resolution ones.

*Multi-Domain Few Shot Classification*
Check the rules at https://l2id.github.io/challenge_classification.html

Track 1 - Cross Domain, small scale
This track calls for the development of cross-domain few-shot learning
models starting from multiple sources and with no explicit label overlap
between sources and target.

Track 2 - Cross Domain, large scale
In this track additional datasets to both source and target datasets have
been added for participants with sufficient compute resources. In addition
to the multiple sources, *multiple tasks* from which to draw source data or
models are provided.

Track 3 - Cross Domain, larger number of classes
In this track, the “wayness” of few-shot learning is increased, bringing it
closer to semi-supervised learning.


Submission Deadline: May 14th
Leaderboard Published / Invitations Sent: May 21th

Zsolt Kira (Georgia Tech, USA)
Shuai (Kyle) Zheng (Dawnlight Technologies Inc, USA)
Noel C. F. Codella (Microsoft, USA)
Yunchao Wei (University of Technology Sydney, AU)
Tatiana Tommasi (Politecnico di Torino, IT)
Ming-Ming Cheng (Nankai University, CN)
Judy Hoffman (Georgia Tech, USA)
Antonio Torralba (MIT, USA)
Xiaojuan Qi (University of Hong Kong, HK)
Sadeep Jayasumana (Google, USA)
Hang Zhao (MIT, USA)
Liwei Wang (Chinese University of Hong Kong, HK)
Yunhui Guo (UC Berkeley/ICSI, USA)
Lin-Zhuo Chen (Nankai University, CN)
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20210503/e310bc34/attachment.html>

More information about the visionlist mailing list