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"

50 / 492 papers shown

Title
FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning Kun Song Huimin Ma Bochao Zou Huishuai Zhang Weiran Huang 104 12 0 23 Oct 2023
Foundation Model's Embedded Representations May Detect Distribution Shift Max Vargas Adam Tsou A. Engel Tony Chiang 70 1 0 20 Oct 2023
Rethinking Class-incremental Learning in the Era of Large Pre-trained Models via Test-Time Adaptation Imad Eddine Marouf Subhankar Roy Enzo Tartaglione Stéphane Lathuilière CLL 104 3 0 17 Oct 2023
Domain Generalization Using Large Pretrained Models with Mixture-of-Adapters Gyuseong Lee Wooseok Jang Jin Hyeon Kim Jaewoo Jung Seungryong Kim MoE OOD 67 4 0 17 Oct 2023
Few-Shot Learning Patterns in Financial Time-Series for Trend-Following Strategies Kieran Wood Samuel Kessler Stephen J. Roberts S. Zohren AI4TS 85 2 0 16 Oct 2023
Self-Detoxifying Language Models via Toxification Reversal Chak Tou Leong Yi Cheng Jiashuo Wang Jian Wang Wenjie Li MU 47 38 0 14 Oct 2023
Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification Sravanti Addepalli Ashish Ramayee Asokan Lakshay Sharma R. V. Babu VLM 59 21 0 12 Oct 2023
Reset It and Forget It: Relearning Last-Layer Weights Improves Continual and Transfer Learning Lapo Frati Neil Traft Jeff Clune Nick Cheney CLL 79 1 0 12 Oct 2023
TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models Zuxin Liu Jesse Zhang Kavosh Asadi Yao Liu Ding Zhao Shoham Sabach Rasool Fakoor ALM AI4CE 111 30 0 09 Oct 2023
CAD Models to Real-World Images: A Practical Approach to Unsupervised Domain Adaptation in Industrial Object Classification Dennis Ritter Mike Hemberger Marc Hönig Volker Stopp Erik Rodner Kristian Hildebrand 70 0 0 07 Oct 2023
Profit: Benchmarking Personalization and Robustness Trade-off in Federated Prompt Tuning Liam Collins Shanshan Wu Sewoong Oh K. Sim FedML 94 10 0 06 Oct 2023
On the Embedding Collapse when Scaling up Recommendation Models Xingzhuo Guo Kai Yan Ximei Wang Baixu Chen Haohan Wang Mingsheng Long 103 25 0 06 Oct 2023
OpenPatch: a 3D patchwork for Out-Of-Distribution detection Paolo Rabino A. Alliegro Francesco Cappio Borlino Tatiana Tommasi 3DPC 82 1 0 05 Oct 2023
Tuning In to Neural Encoding: Linking Human Brain and Artificial Supervised Representations of Language Jingyuan Sun Xiaohan Zhang Marie-Francine Moens 115 7 0 05 Oct 2023
Sieve: Multimodal Dataset Pruning Using Image Captioning Models Anas Mahmoud Mostafa Elhoushi Amro Abbas Yu Yang Newsha Ardalani Hugh Leather Ari S. Morcos VLM CLIP 80 21 0 03 Oct 2023
Towards Stable Backdoor Purification through Feature Shift Tuning Rui Min Zeyu Qin Li Shen Minhao Cheng AAML 113 22 0 03 Oct 2023
Fine-tuned vs. Prompt-tuned Supervised Representations: Which Better Account for Brain Language Representations? Jingyuan Sun Marie-Francine Moens AAML 67 13 0 03 Oct 2023
Fusing Models with Complementary Expertise Hongyi Wang Felipe Maia Polo Yuekai Sun Souvik Kundu Eric Xing Mikhail Yurochkin FedML MoMe 94 33 0 02 Oct 2023
A Unified Framework for Generative Data Augmentation: A Comprehensive Survey Yunhao Chen Zihui Yan Yunjie Zhu 72 3 0 30 Sep 2023
Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks Hao Chen Jindong Wang Ankit Shah Ran Tao Hongxin Wei Berfin cSimcsek Masashi Sugiyama Bhiksha Raj 108 31 0 29 Sep 2023
Prompt-and-Align: Prompt-Based Social Alignment for Few-Shot Fake News Detection Jiaying Wu Xinyu Chen Haobin Yang Qi Zhao Yuhui Shi AAML 85 12 0 28 Sep 2023
Generative Speech Recognition Error Correction with Large Language Models and Task-Activating Prompting Chao-Han Huck Yang Yile Gu Yi-Chieh Liu Shalini Ghosh I. Bulyko A. Stolcke KELM LRM 120 52 0 27 Sep 2023
VPA: Fully Test-Time Visual Prompt Adaptation Jiachen Sun Mark Ibrahim Melissa Hall Ivan Evtimov Z. Morley Mao Cristian Canton Ferrer C. Hazirbas VLM 94 7 0 26 Sep 2023
Prompting and Fine-Tuning Open-Sourced Large Language Models for Stance Classification Iain J. Cruickshank Lynnette Hui Xian Ng 81 9 0 24 Sep 2023
Test-Time Training for Speech Sri Harsha Dumpala Chandramouli Shama Sastry Sageev Oore 100 1 0 19 Sep 2023
Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts Jiang-Xin Shi Tong Wei Zhi Zhou Jiejing Shao Xin-Yan Han Yu-Feng Li 102 36 0 18 Sep 2023
Mitigating the Alignment Tax of RLHF Yong Lin Hangyu Lin Wei Xiong Shizhe Diao Zeming Zheng ... Han Zhao Nan Jiang Heng Ji Yuan Yao Tong Zhang MoMe CLL 112 81 0 12 Sep 2023
Contrastive Learning as Kernel Approximation Konstantinos Christopher Tsiolis SSL 84 0 0 06 Sep 2023
CA2: Class-Agnostic Adaptive Feature Adaptation for One-class Classification Zilong Zhang Zhibin Zhao Deyu Meng Xingwu Zhang Xuefeng Chen VLM 51 1 0 04 Sep 2023
Do the Frankenstein, or how to achieve better out-of-distribution performance with manifold mixing model soup Hannes Fassold MoMe UQCV 43 2 0 28 Aug 2023
Exploring the Transfer Learning Capabilities of CLIP in Domain Generalization for Diabetic Retinopathy Sanoojan Baliah F. Maani Santosh Sanjeev M. H. Khan 68 8 0 27 Aug 2023
Fine-tuning can cripple your foundation model; preserving features may be the solution Jishnu Mukhoti Y. Gal Philip Torr P. Dokania CLL 130 47 0 25 Aug 2023
Opening the Vocabulary of Egocentric Actions Dibyadip Chatterjee Fadime Sener Shugao Ma Angela Yao VLM 101 18 0 22 Aug 2023
An Analysis of Initial Training Strategies for Exemplar-Free Class-Incremental Learning Grégoire Petit Michael Soumm Eva Feillet Adrian Daniel Popescu Bertrand Delezoide David Picard C´eline Hudelot CLL 89 8 0 22 Aug 2023
Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learning Filip Szatkowski Mateusz Pyla Marcin Przewiȩźlikowski Sebastian Cygert Bartlomiej Twardowski Tomasz Trzciñski CLL 96 11 0 18 Aug 2023
LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasters Ching Chang Wei-Yao Wang Wenjie Peng Tien-Fu Chen AI4TS 158 61 0 16 Aug 2023
A Foundation Language-Image Model of the Retina (FLAIR): Encoding Expert Knowledge in Text Supervision Julio Silva-Rodríguez H. Chakor Riadh Kobbi Jose Dolz Ismail Ben Ayed VLM MedIm 245 46 0 15 Aug 2023
Domain-Aware Fine-Tuning: Enhancing Neural Network Adaptability Seokhyeon Ha S. Jung Jungwook Lee 47 4 0 15 Aug 2023
SLPT: Selective Labeling Meets Prompt Tuning on Label-Limited Lesion Segmentation Fan Bai K. Yan Xiaoyu Bai Xinyu Mao Xiaoli Yin Jingren Zhou Yu Shi Le Lu Max Q.-H. Meng VLM 54 2 0 09 Aug 2023
Unlocking the Potential of Similarity Matching: Scalability, Supervision and Pre-training Yanis Bahroun Shagesh Sridharan Atithi Acharya D. Chklovskii Anirvan M. Sengupta 55 0 0 02 Aug 2023
Improving Generalization of Adversarial Training via Robust Critical Fine-Tuning Kaijie Zhu Jindong Wang Xixu Hu Xingxu Xie G. Yang AAML 74 25 0 01 Aug 2023
Pretrained deep models outperform GBDTs in Learning-To-Rank under label scarcity Charlie Hou K. K. Thekumparampil Michael Shavlovsky Giulia Fanti Yesh Dattatreya Sujay Sanghavi LMTD 129 1 0 31 Jul 2023
Evaluating the structure of cognitive tasks with transfer learning Bruno Aristimunha Raphael Y. de Camargo W. H. L. Pinaya Sylvain Chevallier Alexandre Gramfort Cédric Rommel 82 5 0 28 Jul 2023
PUMA: Secure Inference of LLaMA-7B in Five Minutes Ye Dong Wen-jie Lu Yancheng Zheng Haoqi Wu Derun Zhao Jin Tan Zhicong Huang Cheng Hong Tao Wei Wen-Chang Cheng 61 61 0 24 Jul 2023
GIST: Generating Image-Specific Text for Fine-grained Object Classification Kathleen M. Lewis Emily Mu Adrian Dalca John Guttag VLM 65 7 0 21 Jul 2023
FedBug: A Bottom-Up Gradual Unfreezing Framework for Federated Learning Chia-Hsiang Kao Yu-Chiang Frank Wang FedML 110 1 0 19 Jul 2023
Revisiting the Robustness of the Minimum Error Entropy Criterion: A Transfer Learning Case Study Luis P. Silvestrin Shujian Yu Mark Hoogendoorn OOD 97 1 0 17 Jul 2023
A Causal Framework to Unify Common Domain Generalization Approaches N. Zhang Kaican Li Han Gao Weiyan Xie Zhi Lin Zechao Li Luning Wang Yongxiang Huang FedML OOD AI4CE 83 3 0 13 Jul 2023
Large Class Separation is not what you need for Relational Reasoning-based OOD Detection L. Lu Giulia DÁscenzi Francesco Cappio Borlino Tatiana Tommasi OODD 46 1 0 12 Jul 2023
What Happens During Finetuning of Vision Transformers: An Invariance Based Investigation Gabriele Merlin Vedant Nanda Ruchit Rawal Mariya Toneva 61 3 0 12 Jul 2023