Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution

21 February 2022

Papers citing "Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution"

42 / 492 papers shown

Title
DAFT: Distilling Adversarially Fine-tuned Models for Better OOD Generalization Anshul Nasery Sravanti Addepalli Praneeth Netrapalli Prateek Jain OOD FedML 88 1 0 19 Aug 2022
Patching open-vocabulary models by interpolating weights Gabriel Ilharco Mitchell Wortsman S. Gadre Shuran Song Hannaneh Hajishirzi Simon Kornblith Ali Farhadi Ludwig Schmidt VLM KELM 139 176 0 10 Aug 2022
On Transfer of Adversarial Robustness from Pretraining to Downstream Tasks Laura Fee Nern Harsh Raj Maurice Georgi Yash Sharma AAML 97 4 0 07 Aug 2022
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion Rinon Gal Yuval Alaluf Yuval Atzmon Or Patashnik Amit H. Bermano Gal Chechik Daniel Cohen-Or 176 1,903 0 02 Aug 2022
Exploring the Design of Adaptation Protocols for Improved Generalization and Machine Learning Safety Puja Trivedi Danai Koutra Jayaraman J. Thiagarajan AAML 57 0 0 26 Jul 2022
Discrete Key-Value Bottleneck Frederik Trauble Anirudh Goyal Nasim Rahaman Michael C. Mozer Kenji Kawaguchi Yoshua Bengio Bernhard Schölkopf CLL 92 23 0 22 Jul 2022
Two-Stage Fine-Tuning: A Novel Strategy for Learning Class-Imbalanced Data Taha ValizadehAslani Yiwen Shi Jing Wang Ping Ren Yi Zhang Meng Hu Lianggong Zhao Hualou Liang 68 7 0 22 Jul 2022
Assaying Out-Of-Distribution Generalization in Transfer Learning F. Wenzel Andrea Dittadi Peter V. Gehler Carl-Johann Simon-Gabriel Max Horn ... Chris Russell Thomas Brox Bernt Schiele Bernhard Schölkopf Francesco Locatello OOD OODD AAML 143 76 0 19 Jul 2022
Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift Ananya Kumar Tengyu Ma Percy Liang Aditi Raghunathan UQCV OODD OOD 104 39 0 18 Jul 2022
Contrastive Adapters for Foundation Model Group Robustness Michael Zhang Christopher Ré VLM 54 64 0 14 Jul 2022
A Data-Based Perspective on Transfer Learning Saachi Jain Hadi Salman Alaa Khaddaj Eric Wong Sung Min Park Aleksander Madry 84 39 0 12 Jul 2022
Test-Time Adaptation via Self-Training with Nearest Neighbor Information M-U Jang Sae-Young Chung Hye Won Chung OOD TTA 99 63 0 08 Jul 2022
Motley: Benchmarking Heterogeneity and Personalization in Federated Learning Shan-shan Wu Tian Li Zachary B. Charles Yu Xiao Ziyu Liu Zheng Xu Virginia Smith FedML 101 45 0 18 Jun 2022
Prefix Conditioning Unifies Language and Label Supervision Kuniaki Saito Kihyuk Sohn Xinming Zhang Chun-Liang Li Chen-Yu Lee Kate Saenko Tomas Pfister VLM CLIP 97 16 0 02 Jun 2022
Positive Unlabeled Contrastive Learning Anish Acharya Sujay Sanghavi Li Jing Bhargav Bhushanam Dhruv Choudhary Michael G. Rabbat Inderjit Dhillon SSL 65 11 0 01 Jun 2022
Understanding new tasks through the lens of training data via exponential tilting Subha Maity Mikhail Yurochkin Moulinath Banerjee Yuekai Sun 104 10 0 26 May 2022
An Empirical Study on Distribution Shift Robustness From the Perspective of Pre-Training and Data Augmentation Ziquan Liu Yi Tian Xu Yuanhong Xu Qi Qian Hao Li Rong Jin Xiangyang Ji Antoni B. Chan OOD 89 16 0 25 May 2022
Multimodal Knowledge Alignment with Reinforcement Learning Youngjae Yu Jiwan Chung Heeseung Yun Jack Hessel Jinho Park ... Prithviraj Ammanabrolu Rowan Zellers Ronan Le Bras Gunhee Kim Yejin Choi VLM 160 37 0 25 May 2022
ER-Test: Evaluating Explanation Regularization Methods for Language Models Brihi Joshi Aaron Chan Ziyi Liu Shaoliang Nie Maziar Sanjabi Hamed Firooz Xiang Ren AAML 93 6 0 25 May 2022
Linear Connectivity Reveals Generalization Strategies Jeevesh Juneja Rachit Bansal Kyunghyun Cho João Sedoc Naomi Saphra 331 48 0 24 May 2022
Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing Linlu Qiu Peter Shaw Panupong Pasupat Tianze Shi Jonathan Herzig Emily Pitler Fei Sha Kristina Toutanova AI4CE LRM 158 54 0 24 May 2022
Representation Projection Invariance Mitigates Representation Collapse Anastasia Razdaibiedina A. Khetan Zohar Karnin Daniel Khashabi Vishaal Kapoor V. Madan 98 5 0 23 May 2022
Test-Time Robust Personalization for Federated Learning Liang Jiang Tao R. Lin FedML OOD TTA 157 48 0 22 May 2022
Diverse Weight Averaging for Out-of-Distribution Generalization Alexandre Ramé Matthieu Kirchmeyer Thibaud Rahier A. Rakotomamonjy Patrick Gallinari Matthieu Cord OOD 258 138 0 19 May 2022
How to Fine-tune Models with Few Samples: Update, Data Augmentation, and Test-time Augmentation Yujin Kim Jaehoon Oh Sungnyun Kim Se-Young Yun 78 6 0 13 May 2022
Alleviating Representational Shift for Continual Fine-tuning Shibo Jie Zhi-Hong Deng Ziheng Li CLL 89 11 0 22 Apr 2022
Empirical Evaluation and Theoretical Analysis for Representation Learning: A Survey Kento Nozawa Issei Sato AI4TS 139 5 0 18 Apr 2022
Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations Polina Kirichenko Pavel Izmailov A. Wilson OOD 119 339 0 06 Apr 2022
Beyond Separability: Analyzing the Linear Transferability of Contrastive Representations to Related Subpopulations Jeff Z. HaoChen Colin Wei Ananya Kumar Tengyu Ma 77 39 0 06 Apr 2022
"This is my unicorn, Fluffy": Personalizing frozen vision-language representations Niv Cohen Rinon Gal E. Meirom Gal Chechik Yuval Atzmon VLM MLLM 122 88 0 04 Apr 2022
Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation Kendrick Shen Robbie Jones Ananya Kumar Sang Michael Xie Jeff Z. HaoChen Tengyu Ma Percy Liang SSL 119 89 0 01 Apr 2022
CADG: A Model Based on Cross Attention for Domain Generalization Chengqiu Dai Yingqiao Lin Fan Li Xiyao Li Don Xie OOD 57 3 0 31 Mar 2022
Domain Generalization by Mutual-Information Regularization with Pre-trained Models Junbum Cha Kyungjae Lee Sungrae Park Sanghyuk Chun OOD 118 138 0 21 Mar 2022
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time Mitchell Wortsman Gabriel Ilharco S. Gadre Rebecca Roelofs Raphael Gontijo-Lopes ... Hongseok Namkoong Ali Farhadi Y. Carmon Simon Kornblith Ludwig Schmidt MoMe 199 1,013 1 10 Mar 2022
Geodesic Multi-Modal Mixup for Robust Fine-Tuning Changdae Oh Junhyuk So Hoyoon Byun Yongtaek Lim Minchul Shin Jong-June Jeon Kyungwoo Song 139 30 0 08 Mar 2022
Delving Deeper into Cross-lingual Visual Question Answering Chen Cecilia Liu Jonas Pfeiffer Anna Korhonen Ivan Vulić Iryna Gurevych 105 8 0 15 Feb 2022
Provable Domain Generalization via Invariant-Feature Subspace Recovery Haoxiang Wang Haozhe Si Yue Liu Han Zhao OOD 137 35 0 30 Jan 2022
General Greedy De-bias Learning Xinzhe Han Shuhui Wang Chi Su Qingming Huang Qi Tian 109 9 0 20 Dec 2021
Twitter-COMMs: Detecting Climate, COVID, and Military Multimodal Misinformation Giscard Biamby Grace Luo Trevor Darrell Anna Rohrbach 68 26 0 16 Dec 2021
How Well Do Sparse Imagenet Models Transfer? Eugenia Iofinova Alexandra Peste Mark Kurtz Dan Alistarh 125 41 0 26 Nov 2021
Domain Prompt Learning for Efficiently Adapting CLIP to Unseen Domains Xinyu Zhang S. Gu Yutaka Matsuo Yusuke Iwasawa VLM 104 40 0 25 Nov 2021
Why Do Pretrained Language Models Help in Downstream Tasks? An Analysis of Head and Prompt Tuning Colin Wei Sang Michael Xie Tengyu Ma 148 100 0 17 Jun 2021