We warmly invite all machine learning researchers to participate in the upcoming IJCAI 2021 First International Workshop on Continual Semi-Supervised Learning

https://sites.google.com/view/sscl-workshop-ijcai-2021/

The aim of this workshop is to formalise this new continual semi-supervised learning paradigm, and to introduce it to the machine learning community in order to mobilise effort in this direction. We present the first two benchmark datasets for this problem, derived from significant computer vision scenarios, and propose the first Continual Semi-Supervised Learning Challenges to the research community.

To attend, please follow IJCAI guidelines for workshop registration (early bird $80):

https://ijcai-21.org/registration-information/

Format -----------------------------------------------------------------------------------------------------------------

The workshop is a full-day event, scheduled in two halves (see below) taking place on��Thursday 19th August and Friday 20th August.

The event will be hosted on Gather Town, and will also be recorded via Zoom.

The programme is a blend of invited talks, oral presentations from the two award-winning papers, two poster sessions and a panel on the future of continual learning.

��

August 19 �� 14:00 �� 18:00 UTC

14:00

Opening remarks

��

14:10-15:10

��

Presentation of the benchmarks and challenges

��

15:10-15:40

��

Invited talk #1 �� Razvan Pascanu

��

15:40-16:10

��

Invited talk #2 �� Bing Liu

��

16:10-16:30

��

Coffee break

��

16:30-17:30

��

Poster session 1

��

17:30:18:00

��

Best student paper award oral presentation

��

August 20 - 14:00 �� 18:00 UTC

��

14:00-14:30

��

Best paper oral presentation

��

14:30-15:30

��

Poster session 2

��

15:30-15:50

��

Coffee break

��

15:50-16:20

��

Invited talk #3 �� Tinne Tuytelaars

��

16:20-16:50

��

Invited talk #4 �� Chelsea Finn

��

16:50-17:50

��

Panel on future of continual learning

��

17:50-18:00

��

Award ceremony and closing remarks

Challenges ------------------------------------------------------------------------------------------------------------

With��this workshop we intend to propose to the community both a continual activity recognition (CAR) challenge and a continual crowd counting (CCC) challenge.

https://sites.google.com/view/sscl-workshop-ijcai-2021/challenges

based on a newly released Continual Activity Recognition (CAR) dataset, derived from a fraction of the MEVA (Multiview Extended Video with Activities) activity detection dataset (https://mevadata.org/), and a Continual Crowd Counting (CCC) dataset, derived from sequences from the Mall, UCSD and��FDST datasets.

Invited speakers -----------------------------------------------------------------------------------------------------

Razvan Pascanu (Deepmind)
Tinne Tuytelaars (KU Leuven)
Chelsea Finn (Stanford)
Bing Liu (University of Illinois at Chicago)

Accepted Papers ----------------------------------------------------------------------------------------------------

Lucas Caccia and Joelle Pineau ��

SPeCiaL: Self-Supervised Pretraining for Continual Learning
(Best Paper Award)

Dhanajit Brahma, Vinay Kumar Verma and Piyush Rai
Hypernetworks for Continual Semi-Supervised Learning ��

(Best Student Paper Award)

Jiangpeng He and Fengqing Zhu��

Unsupervised Continual Learning Via Pseudo Labels

Luca Monorchio, Marco Capotondi, Mario Corsanici, Wilson Villa, Alessandro De Luca and Francesco Puja��

Transfer and Continual Supervised Learning for Robotic Grasping through Grasping Features

Mahardhika Pratama, Andri Ashfahani and Edwin Lughofer��

Unsupervised Continual Learning via Self-Adaptive Deep Clustering Approach

Enrico Meloni, Alessandro Betti, Lapo Faggi, Simone Marullo, Matteo Tiezzi and Stefano Melacci��

Evaluating Continual Learning Algorithms by Generating 3D Virtual Environments

Qihan Yang, Fan Feng and Rosa H.M. Chan��

A Benchmark and Empirical Analysis for Replay Methods in Continual Learning

Andrea Rosasco, Antonio Carta, Andrea Cossu, Vicenzo Lomonaco and Davide Bacciu��

Distilled Replay: Overcoming Forgetting through Synthetic Samples

Jingbo Sun, Li Yang, Jiaxin Zhang, Frank Liu, Mahantesh Halappanavar, Deliang Fan and Yu Cao��

Self-supervised Novelty Detection for Continual Learning: A Gradient-based Approach Boosted by Binary Classification

Hermann Blum, Francesco Milano, Ren�� Zurbr��gg, Roland Siegwart, Cesar Cadena and Abel Gawel��

Self-Improving Semantic Perception for Indoor Localisation

Sungmin Cha, Beomyoung Kim, Youngjoon Yoo and Taesup Moon��

SSUL: Semantic Segmentation with Unknown Label for Exemplar-based Class-Incremental Learning

Ajmal Shahbaz, Salman Khan, Mohamad Asiful Hossain, Vincenzo Lomonaco, Kevin Cannons, Zhan Xu and Fabio Cuzzolin

International Workshop on Continual Semi-Supervised Learning: Introduction, Benchmarks and Baselines

��

Organising committee ----------------------------------------------------------------------------------------------

Fabio Cuzzolin (Oxford Brookes University)
Kevin Cannons (Huawei Technologies Canada)
Vincenzo Lomonaco (University of Pisa and ContinualAI)
Irina Rish (University of Montreal and MILA)
Salman Khan (Oxford Brookes University)
Mohamad Asiful Hossain (Huawei Technologies Canada)
Ajmal Shahbaz (Oxford Brookes University)