[visionlist] CFP: Self-supervised Learning for Next-Generation Industry-level Autonomous Driving Workshop @ ICCV 2021

Michael Kampffmeyer michael.c.kampffmeyer at uit.no
Sat Jul 31 17:31:30 -04 2021


CFP: Self-supervised Learning for Next-Generation Industry-level Autonomous Driving Workshop @ ICCV 2021
https://sslad2021.github.io/
Paper submission deadline: August 22, 2021

Call for Submissions:
The workshop is expected to attract research on self-supervised, semi-supervised and self-training techniques for achieving industry-level autonomous driving solutions, which will cover but are not limited to the following topics:
- Self-supervised learning techniques
-Life-long/incremental visual recognition methods
-Weakly supervised learning algorithms
-One/few/zero shot learning for perception tasks in self-driving
-Learning in the presence of noisy data
-Domain adaptation
-Weakly supervised learning for 3D Lidar and 2D images
-Real world self-driving image applications, e.g. lane detection, anomaly detection, object semantic segmentation/detection/localization, scene parsing, etc.
-Vision-based localization and tracking
-Safety/explainability/robustness for self-driving cars in the abovementioned settings

We invite submissions of full papers, as well as works-in-progress, position papers, and papers describing open problems and challenges. While original contributions are preferred, we also invite submissions of high-quality work that has recently been published in other venues or is concurrently submitted. Papers should not be longer than 4 pages (excluding references) formatted using the ICCV template. All the submissions should be anonymous. An optional appendix can be added in the submission, after references. There is no page limit for the appendix. The accepted papers are allowed to get submitted to other conference venues. This workshop has no archival proceedings.

Papers can be submitted through CMT https://cmt3.research.microsoft.com/SSLAD2021

Important Dates:
Paper submission deadline: August 22, 2021 (11:59PM Pacific Time)
Author notification: September 12, 2021 (11:59PM Pacific Time)
Camera-ready papers due: September 26, 2021 (11:59PM Pacific Time)

Keynote speakers:
- Raquel Urtasun (University of Toronto)
- Laura Leal-Taixé (Technical University of Munich)
- Peter Kontschieder (Facebook)
- Chunhua Shen (University of Adelaide)
- Alex Kendall (University of Cambridge)

Challenge:
As part of the workshop, we also release a new Self-training Self-Driving (SSD) challenge, which to the best of our knowledge is the largest of its kind. It includes three competition tasks and contains 10 million 2D images and 1 million video frames collected from real-world driving scenarios. Note, multimodal information is available for the video data, where each frame is accompanied by 1 lidar image and 6 other view angles. This SSD challenge aims to provide a standard industry-level benchmark for examining the generalization and robustness ability of self-supervised/semi-supervised perception models on large-scale real-world self-driving applications. More information at: https://sslad2021.github.io/pages/challenge.html

Contact:
sslad2021 at googlegroups.com
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://visionscience.com/pipermail/visionlist_visionscience.com/attachments/20210731/e85c0607/attachment.html>


More information about the visionlist mailing list