Workshop
4th Workshop on Self-Supervised Learning: Theory and Practice
Tengda Han 路 Ishan Misra 路 Pengtao Xie 路 Mathilde Caron 路 Hilde Kuehne 路 Xingjian Bai 路 Vadim Tschernezki
Sat 16 Dec, 7 a.m. PST
The 4th Workshop on "Self-Supervised Learning: Theory and Practice" aims to discuss the theory and practice of self-supervised learning across multiple research areas like vision, NLP \& robotics.
Chat is not available.
Timezone: America/Los_Angeles
Schedule
|
Sat 7:00 a.m. - 7:15 a.m.
|
Welcome and introduction
(
Opening
)
>
SlidesLive Video |
馃敆 |
|
Sat 7:15 a.m. - 7:45 a.m.
|
Yuki M Asano
(
Invited Talk
)
>
SlidesLive Video |
馃敆 |
|
Sat 7:45 a.m. - 8:15 a.m.
|
Diane Larlus
(
Invited Talk
)
>
SlidesLive Video |
馃敆 |
|
Sat 8:15 a.m. - 8:45 a.m.
|
Alyosha Efros
(
Invited Talk
)
>
SlidesLive Video |
馃敆 |
|
Sat 9:00 a.m. - 9:30 a.m.
|
Abhinav Gupta
(
Invited Talk
)
>
SlidesLive Video |
馃敆 |
|
Sat 9:30 a.m. - 10:00 a.m.
|
Chelsea Finn
(
Invited Talk
)
>
SlidesLive Video |
馃敆 |
|
Sat 10:00 a.m. - 11:00 a.m.
|
Poster Session I
(
Poster
)
>
|
馃敆 |
|
Sat 12:15 p.m. - 12:45 p.m.
|
Xinyun Chen
(
Invited Talk
)
>
SlidesLive Video |
馃敆 |
|
Sat 2:10 p.m. - 3:00 p.m.
|
Poster Session II
(
Poster
)
>
|
馃敆 |
|
-
|
Improving Domain Generalization in Contrastive Learning Using Adaptive Temperature Control ( Poster ) > link | Katie Matton 路 Robert Lewis 路 Rosalind Picard 路 John Guttag 馃敆 |
|
-
|
Visualizing the loss landscape of Self-supervised Vision Transformer ( Poster ) > link | Youngwan Lee 路 Jeffrey Willette 路 Jonghee Kim 路 Sung Ju Hwang 馃敆 |
|
-
|
Adversarial perturbation based latent reconstruction for domain-agnostic self-supervised learning ( Poster ) > link | Kuilin Chen 路 Sijie Tian 路 Chi-Guhn Lee 馃敆 |
|
-
|
Evolving Graph Generalization Estimation via Self-Supervised Learning ( Poster ) > link | Bin Lu 路 Tingyan Ma 路 Xiaoying Gan 路 Luoyi Fu 路 Xinbing Wang 路 Chenghu Zhou 路 Shiyu Liang 馃敆 |
|
-
|
Uncertainty Quantification using Deep Ensembles for Safety-Critical Predictive Models ( Poster ) > link | Oishi Deb 路 Emmanouil Benetos 路 Philip Torr 馃敆 |
|
-
|
WERank: Rank Degradation Prevention for Self-Supervised Learning via Weight Regularization ( Poster ) > link | Ali Saheb Pasand 路 Reza Moravej 路 Mahdi Biparva 路 Ali Ghodsi 馃敆 |
|
-
|
Language-Conditioned Semantic Search-Based Policy for Robotic Manipulation Tasks ( Poster ) > link | Jannik Sheikh 路 Andrew Melnik 路 Gora Chand Nandi 路 Robert Haschke 馃敆 |
|
-
|
MeSa: Masked, Geometric, and Supervised Pre-training for Monocular Depth Estimation ( Poster ) > link | Muhammad Osama Khan 路 Junbang Liang 路 Chun-Kai Wang 路 Shan Yang 路 Yu Lou 馃敆 |
|
-
|
DAPO: Self-Supervised Domain Adaptation for 6DoF Pose Estimation ( Poster ) > link | Juseong Jin 路 Eunju Jeong 路 Joonmyun Cho 路 JUN HEE PARK 路 Young-Gon Kim 馃敆 |
|
-
|
Leveraging Uniformity of Normalized Embeddings for Sequential Recommendation ( Poster ) > link | Hyunsoo Chung 路 Jungtaek Kim 馃敆 |
|
-
|
Self-Supervised Learning Meets Liver Ultrasound Imaging ( Poster ) > link | Abder-Rahman Ali, PhD 路 Anthony E Samir 馃敆 |
|
-
|
Posterior Sampling on Simsiam: Rethinking Optimization in Siamese Self-Supervised Learning ( Poster ) > link | Daniel De Mello 路 Ruqi Zhang 路 Bruno Ribeiro 馃敆 |
|
-
|
No Free Lunch in Self Supervised Representation Learning ( Poster ) > link | Ihab Bendidi 路 Adrien Bardes 路 ethan cohen 路 Alexis Lamiable 路 Guillaume Bollot 路 Auguste Genovesio 馃敆 |
|
-
|
MOFO: MOtion FOcused Self-Supervision for Video Understanding ( Poster ) > link | Mona Ahmadian 路 Frank Guerin 路 Andrew Gilbert 馃敆 |
|
-
|
Learning to Embed Time Series Patches Independently ( Poster ) > link | Seunghan Lee 路 Taeyoung Park 路 Kibok Lee 馃敆 |
|
-
|
Unsupervised Segmentation of Colonoscopy Images ( Poster ) > link | Heming Yao 路 J茅r么me L眉scher 路 Benjamin Gutierrez Becker 路 Josep Ar煤s-Pous 路 Tommaso Biancalani 路 Amelie Bigorgne 路 David Richmond 馃敆 |
|
-
|
A Simple Framework for Self-Supervised Learning of Sample-Efficient World Models ( Poster ) > link | Jan Robine 路 Marc H枚ftmann 路 Stefan Harmeling 馃敆 |
|
-
|
Learning Beyond Similarities: Incorporating Dissimilarities between Positive Pairs in Self-Supervised Time Series Learning. ( Poster ) > link | Adrian Atienza 路 Jakob Bardram 路 Sadasivan Puthusserypady 馃敆 |
|
-
|
Learning Orthonormal Features in Self-Supervised Learning using Functional Maximal Correlation ( Poster ) > link | Bo Hu 路 Yuheng Bu 路 Jose C Principe 馃敆 |
|
-
|
Enhancing CLIP with a Third Modality ( Poster ) > link | Efthymios Tsaprazlis 路 Georgios Smyrnis 路 Alex Dimakis 路 Petros Maragos 馃敆 |
|
-
|
Generalization properties of contrastive world models ( Poster ) > link | Kandan Ramakrishnan 路 R. James Cotton 路 Xaq Pitkow 路 Andreas Tolias 馃敆 |
|
-
|
Adaptive Resolution Loss: An Efficient and Effective Loss for Time Series Hierarchical Contrastive Self-Supervised Learning Framework ( Poster ) > link | Kevin Garcia 路 Juan Manuel Perez Jr 路 Yifeng Gao 馃敆 |
|
-
|
How does semi-supervised learning with pseudo-labelers work? A case study ( Poster ) > link | Yiwen Kou 路 Zixiang Chen 路 Yuan Cao 路 Quanquan Gu 馃敆 |
|
-
|
Recycle-and-Distill: Universal Compression Strategy for Transformer-based Speech SSL Models with Attention Map Reusing and Masking Distillation ( Poster ) > link | Kangwook Jang 路 Sungnyun Kim 路 Se-Young Yun 路 HOI RIN KIM 馃敆 |
|
-
|
Ring Attention with Blockwise Transformers for Near-Infinite Context ( Poster ) > link | Hao Liu 路 Matei A Zaharia 路 Pieter Abbeel 馃敆 |
|
-
|
Soft Contrastive Learning for Time Series ( Poster ) > link | Seunghan Lee 路 Taeyoung Park 路 Kibok Lee 馃敆 |
|
-
|
SAMCLR: Contrastive pre-training on complex scenes using SAM for view sampling ( Poster ) > link | Benjamin Missaoui 路 Chongbin Yuan 馃敆 |
|
-
|
Language Model Training Paradigms for Clinical Feature Embeddings ( Poster ) > link | Yurong Hu 路 Manuel Burger 路 Gunnar R盲tsch 路 Rita Kuznetsova 馃敆 |
|
-
|
Structuring Representation Geometry with Rotationally Equivariant Contrastive Learning ( Poster ) > link | Sharut Gupta 路 Joshua Robinson 路 Derek Lim 路 Soledad Villar 路 Stefanie Jegelka 馃敆 |
|
-
|
Multimodal Distillation of CLIP Models ( Poster ) > link | Georgios Smyrnis 路 Sriram Ravula 路 Sujay Sanghavi 路 Alex Dimakis 馃敆 |
|
-
|
Augmentation matters: Representation learning for Strong Gravitational lensing ( Poster ) > link | Kuan-Wei Huang 路 Po-Wen Chang 路 Joshua Fagin 路 James Chan 路 Joshua Yao-Yu Lin 馃敆 |
|
-
|
Online Feature Updates Improve Online (Generalized) Label Shift Adaptation ( Poster ) > link | Ruihan Wu 路 Siddhartha Datta 路 Yi Su 路 Dheeraj Baby 路 Yu-Xiang Wang 路 Kilian Weinberger 馃敆 |
|
-
|
FroSSL: Frobenius Norm Minimization for Self-Supervised Learning ( Poster ) > link | Oscar Skean 路 Aayush Dhakal 路 Nathan Jacobs 路 Luis Sanchez Giraldo 馃敆 |
|
-
|
Spectral Temporal Contrastive Learning ( Poster ) > link | Sacha Morin 路 Somjit Nath 路 Samira Ebrahimi Kahou 路 Guy Wolf 馃敆 |
|
-
|
Self-Supervised Pretraining for Improved Downstream Decoding of Audio-Evoked fMRI Sequences ( Poster ) > link | Sean Paulsen 路 Mike Casey 馃敆 |
|
-
|
Exploring Target Representations for Masked Autoencoders ( Poster ) > link | xingbin liu 路 Jinghao Zhou 路 Tao Kong 馃敆 |
|
-
|
Non-Vacuous Generalization Bounds for Large Language Models ( Poster ) > link | Sanae Lotfi 路 Marc Finzi 路 Yilun Kuang 路 Tim G. J. Rudner 路 Micah Goldblum 路 Andrew Wilson 馃敆 |
|
-
|
Bootstrap Your Own Variance ( Poster ) > link | Polina Turishcheva 路 Jason Ramapuram 路 Sinead Williamson 路 Dan Busbridge 路 Eeshan Gunesh Dhekane 路 Russell Webb 馃敆 |
|
-
|
Self-supervised Representation Learning from Random Data Projectors ( Poster ) > link | Yi Sui 路 Tongzi Wu 路 Jesse Cresswell 路 Ga Wu 路 George Stein 路 Xiao Shi Huang 路 Xiaochen Zhang 路 Maksims Volkovs 馃敆 |
|
-
|
An Information-Theoretic Understanding of Maximum Manifold Capacity Representations ( Poster ) > link | Berivan Isik 路 Rylan Schaeffer 路 Victor Lecomte 路 Mikail Khona 路 Yann LeCun 路 Sanmi Koyejo 路 Andrey Gromov 路 Ravid Shwartz-Ziv 馃敆 |
|
-
|
Self-Distilled Representation Learning for Time Series ( Poster ) > link | Felix Pieper 路 Konstantin Ditschuneit 路 Martin Genzel 路 Alexandra Lindt 路 Johannes Otterbach 馃敆 |
|
-
|
Making Self-supervised Learning Robust to Spurious Correlation via Learning-speed Aware Sampling ( Poster ) > link | Weicheng Zhu 路 Sheng Liu 路 Carlos Fernandez-Granda 路 Narges Razavian 馃敆 |
|
-
|
Generalized Category Discovery with Hierarchical Label Smoothing ( Poster ) > link | Sarah Rastegar 路 Yuki M Asano 路 Hazel Doughty 路 Cees Snoek 馃敆 |
|
-
|
Benchmarking self-supervised video representation learning ( Poster ) > link | Akash Kumar 路 Ashlesha Kumar 路 Vibhav Vineet 路 Yogesh Rawat 馃敆 |
|
-
|
Neurosymbolic Grounding for Compositional Generalization ( Poster ) > link | Atharva Sehgal 路 Arya Grayeli 路 Jennifer J Sun 路 Swarat Chaudhuri 馃敆 |
|
-
|
No Representation Rules Them All in Category Discovery ( Poster ) > link | Sagar Vaze 路 Andrea Vedaldi 路 Andrew Zisserman 馃敆 |
|
-
|
Application of Self Supervised Vision Transformers for Multiplexed Microscopy Images and Its Challenges ( Poster ) > link | Gantugs Atarsaikhan 路 Isabel Mogollon 路 Katja V盲lim盲ki 路 Teijo Pellinen 路 Tuomas Mirtti 路 Lassi Paavolainen 馃敆 |
|
-
|
HyperMAE: Modulating Implicit Neural Representations for MAE Training ( Poster ) > link | Varun Belagali 路 Lei Zhou 路 Xiang Li 路 Dimitris Samaras 馃敆 |
|
-
|
The Triad of Failure Modes and a Possible Way Out ( Poster ) > link | Emanuele Sansone 馃敆 |
|
-
|
Identifiable attribution maps using regularized contrastive learning ( Poster ) > link | Steffen Schneider 路 Rodrigo Gonz谩lez Laiz 路 Markus Frey 路 Mackenzie Mathis 馃敆 |
|
-
|
On Improving the Sample Efficiency of Non-Contrastive SSL ( Poster ) > link | Kumar Krishna Agrawal 路 Arna Ghosh 路 Adam Oberman 路 Blake Richards 馃敆 |
|
-
|
Perceptual Group Tokenizer: Building Perception with Iterative Grouping ( Poster ) > link | Zhiwei Deng 路 Ting Chen 路 Yang Li 馃敆 |
|
-
|
On the Varied Faces of Overparameterization in Supervised and Self-Supervised Learning ( Poster ) > link | Matteo Gamba 路 Arna Ghosh 路 Kumar Krishna Agrawal 路 Blake Richards 路 Hossein Azizpour 路 M氓rten Bj枚rkman 馃敆 |
|
-
|
Learning Useful Representations of Recurrent Neural Network Weight Matrices ( Poster ) > link | Vincent Herrmann 路 Francesco Faccio 路 J眉rgen Schmidhuber 馃敆 |
|
-
|
MolSiam: Simple Siamese Self-supervised Representation Learning for Small Molecules ( Poster ) > link | Joshua Yao-Yu Lin 路 Michael Maser 路 Nathan Frey 路 Gabriele Scalia 路 Omar Mahmood 路 Pedro O. Pinheiro 路 Ji Won Park 路 Stephen Ra 路 Andrew Watkins 路 Kyunghyun Cho 馃敆 |
|
-
|
Self-Supervised Disentanglement by Leveraging Structure in Data Augmentations ( Poster ) > link | Cian Eastwood 路 Julius von K眉gelgen 路 Linus Ericsson 路 Diane Bouchacourt 路 Pascal Vincent 路 Bernhard Sch枚lkopf 路 Mark Ibrahim 馃敆 |
|
-
|
Does Unconstrained Unlabeled Data Help Semi-Supervised Learning? ( Poster ) > link | Shuvendu Roy 路 Ali Etemad 馃敆 |
|
-
|
Self-supervised Learning for User Sequence Modeling ( Poster ) > link | Yuhan Liu 路 Lin Ning 路 Neo Wu 路 Karan Singhal 路 Philip Mansfield 路 Devora Berlowitz 路 Bradley Green 馃敆 |
|
-
|
LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures ( Poster ) > link | Vimal Thilak 路 Chen Huang 路 Omid Saremi 路 Laurent Dinh 路 Hanlin Goh 路 Preetum Nakkiran 路 Joshua Susskind 路 Etai Littwin 馃敆 |
|
-
|
Multi-Task Learning with Self-Supervised Objectives can Improve Worst-Group Outcomes ( Poster ) > link | Atharva Kulkarni 路 Lucio M Dery 路 Amrith Setlur 路 Aditi Raghunathan 路 Ameet Talwalkar 路 Graham Neubig 馃敆 |
|
-
|
Can semi-supervised learning use all the data effectively? A lower bound perspective ( Poster ) > link | Alexandru Tifrea 路 Gizem Y眉ce 路 Amartya Sanyal 路 Fanny Yang 馃敆 |
|
-
|
Self-Supervised Image Captioning with CLIP ( Poster ) > link | Chuanyang Jin 馃敆 |
|
-
|
Exploring Data Augmentations on Self-/Semi-/Fully- Supervised Pre-trained Models ( Poster ) > link | Shentong Mo 路 Zhun Sun 路 Chao Li 馃敆 |
|
-
|
Simple Contrastive Representation Learning for Time Series Forecasting ( Poster ) > link | Xiaochen Zheng 路 Xingyu Chen 路 Manuel Sch眉rch 路 Maolaaisha Aminanmu 路 Ahmed Allam 路 Michael Krauthammer 馃敆 |
|
-
|
Iterated Piecewise Affine (IPA) Approximation for Language Modeling ( Poster ) > link | Davood Shamsi 路 Wen-yu Hua 路 Brian Williams 馃敆 |
|
-
|
CCA with Shared Weights for Self-Supervised Learning ( Poster ) > link | James Chapman 路 Lennie Wells 馃敆 |
|
-
|
Understanding Self-Supervised Features for Learning Unsupervised Instance Segmentation ( Poster ) > link | Paul Engstler 路 Luke Melas-Kyriazi 路 Christian Rupprecht 路 Iro Laina 馃敆 |
|
-
|
Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery ( Poster ) > link | Sarah Rastegar 路 Hazel Doughty 路 Cees Snoek 馃敆 |
|
-
|
Zero-shot Clustering of Embeddings with Self-Supervised Learnt Encoders ( Poster ) > link | Scott Lowe 路 Joakim Bruslund Haurum 路 Sageev Oore 路 Thomas Moeslund 路 Graham Taylor 馃敆 |
|
-
|
SurgMAE: Masked Autoencoders for Long Surgical Video Analysis ( Poster ) > link | Muhammad Abdullah Jamal 路 Omid Mohareri 馃敆 |
|
-
|
Bridging State and History Representations: Understanding Self-Predictive RL ( Poster ) > link | Tianwei Ni 路 Benjamin Eysenbach 路 Erfan Seyedsalehi 路 Michel Ma 路 Clement Gehring 路 Aditya Mahajan 路 Pierre-Luc Bacon 馃敆 |
|
-
|
Scaling may be all you need for achieving human-level object recognition with human-like visual experience ( Poster ) > link | Emin Orhan 馃敆 |
|
-
|
Augmentation-aware Self-Supervised Learning with Conditioned Projector ( Poster ) > link | Marcin Przewi臋藕likowski 路 Mateusz Pyla 路 Bartosz Zieli艅ski 路 Bart艂omiej Twardowski 路 Jacek Tabor 路 Marek 艢mieja 馃敆 |
|
-
|
BarcodeBERT: Transformers for Biodiversity Analysis ( Poster ) > link |
12 presentersPablo Millan Arias 路 Niousha Sadjadi 路 Monireh Safari 路 ZeMing Gong 路 Austin T. Wang 路 Scott Lowe 路 Joakim Bruslund Haurum 路 Iuliia Zarubiieva 路 Dirk Steinke 路 Lila Kari 路 Angel Chang 路 Graham Taylor |