Exploring the Limits of Weakly Supervised Pretraining

2 May 2018

Laurens van der Maaten

VLM

ArXiv (abs)PDF HTML

Papers citing "Exploring the Limits of Weakly Supervised Pretraining"

50 / 847 papers shown

Title
E^2VPT: An Effective and Efficient Approach for Visual Prompt TuningIEEE International Conference on Computer Vision (ICCV), 2023 Cheng Han Qifan Wang Yiming Cui Zhiwen Cao Wenguan Wang Siyuan Qi Dongfang Liu VPVLM VLM 262 88 0 25 Jul 2023
Foundational Models Defining a New Era in Vision: A Survey and Outlook Muhammad Awais Muzammal Naseer Salman Khan Rao Muhammad Anwer Hisham Cholakkal M. Shah Ming-Hsuan Yang Fahad Shahbaz Khan VLM 408 151 0 25 Jul 2023
A Holistic Assessment of the Reliability of Machine Learning Systems Anthony Corso David Karamadian Romeo Valentin Mary Cooper Mykel J. Kochenderfer 296 10 0 20 Jul 2023
Self-Supervised Learning for WiFi CSI-Based Human Activity Recognition: A Systematic Study Ke Xu Jiangtao Wang Erik Cambria Dingchang Zheng 152 8 0 19 Jul 2023
Alleviating the Effect of Data Imbalance on Adversarial Training Guanlin Li Guowen Xu Tianwei Zhang 226 3 0 14 Jul 2023
Class Instance Balanced Learning for Long-Tailed ClassificationCanadian Conference on Computer and Robot Vision (CRV), 2023 Marc-Antoine Lavoie Steven Waslander 185 0 0 11 Jul 2023
Co-Learning Meets Stitch-Up for Noisy Multi-label Visual RecognitionIEEE Transactions on Image Processing (IEEE TIP), 2023 Chao Liang Zongxin Yang Linchao Zhu Yezhou Yang NoLa 151 11 0 03 Jul 2023
Subclass-balancing Contrastive Learning for Long-tailed RecognitionIEEE International Conference on Computer Vision (ICCV), 2023 Chengkai Hou Jieyu Zhang Hong Wang Wanrong Zhu 176 43 0 28 Jun 2023
Can Continual Learning Improve Long-Tailed Recognition? Toward a Unified Framework Mahdiyar Molahasani Michael A. Greenspan Ali Etemad 121 2 0 23 Jun 2023
MOFI: Learning Image Representations from Noisy Entity Annotated ImagesInternational Conference on Learning Representations (ICLR), 2023 Wentao Wu Aleksei Timofeev Chen Chen Bowen Zhang Kun Duan ... Yantao Zheng Jonathon Shlens Xianzhi Du Zhe Gan Yinfei Yang VLM 210 9 0 13 Jun 2023
WSPAlign: Word Alignment Pre-training via Large-Scale Weakly Supervised Span PredictionAnnual Meeting of the Association for Computational Linguistics (ACL), 2023 Qiyu Wu Masaaki Nagata Yoshimasa Tsuruoka 130 8 0 09 Jun 2023
RDumb: A simple approach that questions our progress in continual test-time adaptationNeural Information Processing Systems (NeurIPS), 2023 Ori Press Steffen Schneider Matthias Kümmerer Matthias Bethge TTA 258 46 0 08 Jun 2023
Improved Probabilistic Image-Text RepresentationsInternational Conference on Learning Representations (ICLR), 2023 Sanghyuk Chun VLM 516 44 0 29 May 2023
Three Towers: Flexible Contrastive Learning with Pretrained Image ModelsNeural Information Processing Systems (NeurIPS), 2023 Jannik Kossen Mark Collier Basil Mustafa Tianlin Li Xiaohua Zhai Lucas Beyer Andreas Steiner Jesse Berent Rodolphe Jenatton Efi Kokiopoulou VLM 173 18 0 26 May 2023
On the Trade-off of Intra-/Inter-class Diversity for Supervised Pre-trainingNeural Information Processing Systems (NeurIPS), 2023 Jieyu Zhang Bohan Wang Zhengyu Hu Pang Wei Koh Alexander Ratner 160 11 0 20 May 2023
Efficient ConvBN Blocks for Transfer Learning and BeyondInternational Conference on Learning Representations (ICLR), 2023 Kaichao You Guo Qin Anchang Bao Mengsi Cao Ping Huang Jiulong Shan Mingsheng Long 232 2 0 19 May 2023
Adjusting Logit in Gaussian Form for Long-Tailed Visual RecognitionIEEE Transactions on Artificial Intelligence (IEEE TAI), 2023 Mengke Li Yiu-ming Cheung Yang Lu Zhikai Hu Weichao Lan Hui Huang 192 11 0 18 May 2023
Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?IEEE International Conference on Computer Vision (ICCV), 2023 Hasan Hammoud Christian Schroeder de Witt Ser-Nam Lim Juil Sock Adel Bibi Guohao Li CLL 274 21 0 16 May 2023
Online Continual Learning Without the Storage Constraint Christian Schroeder de Witt Yong Deng P. Dokania Juil Sock V. Koltun Ozan Sener CLL 351 40 0 16 May 2023
An Inverse Scaling Law for CLIP TrainingNeural Information Processing Systems (NeurIPS), 2023 Xianhang Li Zeyu Wang Cihang Xie VLM CLIP 261 75 0 11 May 2023
Enhancing Clinical Predictive Modeling through Model Complexity-Driven Class Proportion Tuning for Class Imbalanced Data: An Empirical Study on Opioid Overdose Prediction Yinan Liu Xinyu Dong Weimin Lyu R. Rosenthal Rachel Wong Tengfei Ma Fusheng Wang 100 0 0 09 May 2023
ImageBind: One Embedding Space To Bind Them AllComputer Vision and Pattern Recognition (CVPR), 2023 Rohit Girdhar Alaaeldin El-Nouby Zhuang Liu Mannat Singh Kalyan Vasudev Alwala Armand Joulin Ishan Misra VLM 512 1,281 0 09 May 2023
Class-Balancing Diffusion ModelsComputer Vision and Pattern Recognition (CVPR), 2023 Yiming Qin Huangjie Zheng Jiangchao Yao Mingyuan Zhou Ya Zhang DiffM 291 58 0 30 Apr 2023
The Emotions of the Crowd: Learning Image Sentiment from Tweets via Cross-modal DistillationEuropean Conference on Artificial Intelligence (ECAI), 2023 Alessio Serra F. Carrara Maurizio Tesconi Fabrizio Falchi 138 5 0 28 Apr 2023
End-to-End Spatio-Temporal Action Localisation with Video TransformersComputer Vision and Pattern Recognition (CVPR), 2023 A. Gritsenko Xuehan Xiong Josip Djolonga Mostafa Dehghani Chen Sun Mario Lucic Cordelia Schmid Anurag Arnab ViT 227 20 0 24 Apr 2023
Semantic-Aware Graph Matching Mechanism for Multi-Label Image Recognition Yanan Wu Songhe Feng Yang Wang 188 17 0 21 Apr 2023
Synthetic Data from Diffusion Models Improves ImageNet Classification Shekoofeh Azizi Simon Kornblith Chitwan Saharia Mohammad Norouzi David J. Fleet VLM DiffM 710 385 0 17 Apr 2023
DINOv2: Learning Robust Visual Features without Supervision Maxime Oquab Timothée Darcet Théo Moutakanni Huy Q. Vo Marc Szafraniec ... Edouard Grave Julien Mairal Patrick Labatut Armand Joulin Piotr Bojanowski VLM CLIP SSL 1.1K 5,829 0 14 Apr 2023
Unicom: Universal and Compact Representation Learning for Image RetrievalInternational Conference on Learning Representations (ICLR), 2023 Xiang An Jiankang Deng Kaicheng Yang Jaiwei Li Ziyong Feng Jia Guo Jing Yang Tongliang Liu VLM SSL 201 44 0 12 Apr 2023
Reweighted Mixup for Subpopulation Shift Zongbo Han Zhipeng Liang Fan Yang Liu Liu Lanqing Li ... P. Zhao Qinghua Hu Bing Wu Changqing Zhang Jianhua Yao 166 3 0 09 Apr 2023
Long-Tailed Visual Recognition via Self-Heterogeneous Integration with Knowledge ExcavationComputer Vision and Pattern Recognition (CVPR), 2023 Yang Jin Mengke Li Yang Lu Yiu-ming Cheung Hanzi Wang 225 46 0 03 Apr 2023
Towards Understanding the Effect of Pretraining Label Granularity Guanzhe Hong Huayu Chen Ariel Fuxman Stanley H. Chan Enming Luo 186 2 0 29 Mar 2023
VideoMAE V2: Scaling Video Masked Autoencoders with Dual MaskingComputer Vision and Pattern Recognition (CVPR), 2023 Limin Wang Bingkun Huang Zhiyu Zhao Zhan Tong Yinan He Yi Wang Yali Wang Yu Qiao VGen 311 518 0 29 Mar 2023
Towards Foundation Models and Few-Shot Parameter-Efficient Fine-Tuning for Volumetric Organ Segmentation Julio Silva-Rodríguez Jose Dolz Ismail Ben Ayed 414 18 0 29 Mar 2023
GeoNet: Benchmarking Unsupervised Adaptation across GeographiesComputer Vision and Pattern Recognition (CVPR), 2023 Tarun Kalluri Wangdong Xu Manmohan Chandraker OOD 179 18 0 27 Mar 2023
Mind the Backbone: Minimizing Backbone Distortion for Robust Object Detection Kuniaki Saito Donghyun Kim Piotr Teterwak Rogerio Feris Kate Saenko 218 3 0 26 Mar 2023
Joint fMRI Decoding and Encoding with Latent Embedding Alignment Xuelin Qian Yikai Wang Yanwei Fu Xinwei Sun Xiangyang Xue Jianfeng Feng 160 8 0 26 Mar 2023
Analyzing Effects of Mixed Sample Data Augmentation on Model InterpretabilityNeural Networks (Neural Netw.), 2023 Soyoun Won Sung-Ho Bae Seong Tae Kim 187 2 0 26 Mar 2023
The effectiveness of MAE pre-pretraining for billion-scale pretrainingIEEE International Conference on Computer Vision (ICCV), 2023 Mannat Singh Quentin Duval Kalyan Vasudev Alwala Haoqi Fan Vaibhav Aggarwal ... Piotr Dollár Christoph Feichtenhofer Ross B. Girshick Rohit Girdhar Ishan Misra LRM 345 85 0 23 Mar 2023
Open-Vocabulary Object Detection using Pseudo Caption Labels Han-Cheol Cho Won Young Jhoo Woohyun Kang Byungseok Roh VLM ObjD 149 20 0 23 Mar 2023
Large AI Models in Health Informatics: Applications, Challenges, and the FutureIEEE journal of biomedical and health informatics (IEEE JBHI), 2023 Jianing Qiu Lin Li Jiankai Sun Jiachuan Peng Peilun Shi ... Bo Xiao Wu Yuan Ningli Wang Dong Xu Benny Lo AI4MH LM&MA 244 180 0 21 Mar 2023
Computationally Budgeted Continual Learning: What Does Matter?Computer Vision and Pattern Recognition (CVPR), 2023 Christian Schroeder de Witt Hasan Hammoud P. Dokania Juil Sock Ser-Nam Lim Guohao Li Adel Bibi CLL 140 74 0 20 Mar 2023
SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel StorageIEEE International Conference on Computer Vision (ICCV), 2023 Song Park Sanghyuk Chun Byeongho Heo Wonjae Kim Sangdoo Yun VLM ViT 260 9 0 20 Mar 2023
VEIL: Vetting Extracted Image Labels from In-the-Wild Captions for Weakly-Supervised Object DetectionConference of the European Chapter of the Association for Computational Linguistics (EACL), 2023 Arushi Rai Adriana Kovashka 256 0 0 16 Mar 2023
Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset ReinforcementIEEE International Conference on Computer Vision (ICCV), 2023 Fartash Faghri Hadi Pouransari Sachin Mehta Mehrdad Farajtabar Ali Farhadi Mohammad Rastegari Oncel Tuzel 240 15 0 15 Mar 2023
Long-tailed Classification from a Bayesian-decision-theory Perspective Bolian Li Ruqi Zhang 244 1 0 10 Mar 2023
Adapting Contrastive Language-Image Pretrained (CLIP) Models for Out-of-Distribution Detection Tim Kaiser Félix D. P. Michels Nikolas Adaloglou M. Kollmann VLM 230 0 0 10 Mar 2023
Rethinking Self-Supervised Visual Representation Learning in Pre-training for 3D Human Pose and Shape EstimationInternational Conference on Learning Representations (ICLR), 2023 Hongsuk Choi Hyeongjin Nam T. Lee Gyeongsik Moon Kyoung Mu Lee 201 7 0 09 Mar 2023
Your representations are in the network: composable and parallel adaptation for large scale modelsNeural Information Processing Systems (NeurIPS), 2023 Yonatan Dukler Alessandro Achille Hao Yang Varsha Vivek Luca Zancato Benjamin Bowman Avinash Ravichandran Charless C. Fowlkes A. Swaminathan Stefano Soatto 261 3 0 07 Mar 2023
Visual Atoms: Pre-training Vision Transformers with Sinusoidal WavesComputer Vision and Pattern Recognition (CVPR), 2023 Sora Takashima Ryo Hayamizu Nakamasa Inoue Hirokatsu Kataoka Rio Yokota 224 25 0 02 Mar 2023