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
Control-CLIP: Decoupling Category and Style Guidance in CLIP for Specific-Domain Generation Zexi Jia Chuanwei Huang Hongyan Fei Yeshuang Zhu Zhiqiang Yuan Jinchao Zhang Jie Zhou DiffM VLM 86 0 0 17 Feb 2025
The Best Instruction-Tuning Data are Those That Fit Dylan Zhang Qirun Dai Hao Peng ALM 223 7 0 06 Feb 2025
Safety Reasoning with Guidelines Haoyu Wang Zeyu Qin Li Shen Xueqian Wang Minhao Cheng Dacheng Tao 182 4 0 06 Feb 2025
The Capabilities and Limitations of Weak-to-Strong Generalization: Generalization and Calibration Wei Yao Wenkai Yang Ziyi Wang Yankai Lin Yong Liu Yong Liu ELM 338 3 0 03 Feb 2025
Fine Tuning without Catastrophic Forgetting via Selective Low Rank Adaptation Reza Akbarian Bafghi Carden Bagwell Avinash Ravichandran Ashish Shrivastava M. Raissi 82 2 0 28 Jan 2025
Enhancing Virtual Try-On with Synthetic Pairs and Error-Aware Noise Scheduling Nannan Li Kevin J. Shih Bryan A. Plummer DiffM 127 0 0 08 Jan 2025
Pointmap-Conditioned Diffusion for Consistent Novel View Synthesis Thang-Anh-Quan Nguyen Nathan Piasco Luis Roldão Moussâb Bennehar D. Tsishkou Laurent Caraffa J. Tarel R. Brémond DiffM 112 1 0 06 Jan 2025
Fine-Tuning Games: Bargaining and Adaptation for General-Purpose Models Benjamin Laufer Jon M. Kleinberg Hoda Heidari 161 11 0 03 Jan 2025
Adaptive Concept Bottleneck for Foundation Models Under Distribution Shifts Jihye Choi Jayaram Raghuram Yixuan Li Somesh Jha 155 5 0 18 Dec 2024
Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes Aodi Li Liansheng Zhuang Xiao Long Minghong Yao Shafei Wang 521 1 0 18 Dec 2024
Meta Curvature-Aware Minimization for Domain Generalization Zhaoyu Chen Yiwen Ye Feilong Tang Yongsheng Pan Yong-quan Xia BDL 449 1 0 16 Dec 2024
Transliterated Zero-Shot Domain Adaptation for Automatic Speech Recognition Han Zhu Gaofeng Cheng Qingwei Zhao Pengyuan Zhang VLM 134 0 0 15 Dec 2024
Financial Fine-tuning a Large Time Series Model Xinghong Fu Masanori Hirano Kentaro Imajo AI4TS AIFin 131 1 0 13 Dec 2024
Dual Risk Minimization: Towards Next-Level Robustness in Fine-tuning Zero-Shot Models Kaican Li Weiyan Xie Yongxiang Huang Didan Deng Lanqing Hong Zechao Li Ricardo Silva N. Zhang 148 0 0 29 Nov 2024
DoubleCCA: Improving Foundation Model Group Robustness with Random Sentence Embeddings Hong Liu Yitong Lu 198 0 0 25 Nov 2024
LAGUNA: LAnguage Guided UNsupervised Adaptation with structured spaces Anxhelo Diko Antonino Furnari Luigi Cinque G. Farinella 359 0 0 23 Nov 2024
Ghost-Connect Net: A Generalization-Enhanced Guidance For Sparse Deep Networks Under Distribution Shifts Mary Isabelle Wisell Salimeh Yasaei Sekeh 73 0 0 14 Nov 2024
Robust Fine-tuning of Zero-shot Models via Variance Reduction B. Zhu Jiequan Cui Han Zhang VLM OODD 100 3 0 11 Nov 2024
DRIFTS: Optimizing Domain Randomization with Synthetic Data and Weight Interpolation for Fetal Brain Tissue Segmentation Vladyslav Zalevskyi Thomas Sanchez Margaux Roulet Hélène Lajous Jordina Aviles Verdera ... Georg Langs Gregor Kasprian Jana Hutter Hamza Kebiri Meritxell Bach Cuadra OOD 128 1 0 11 Nov 2024
Gradient Localization Improves Lifelong Pretraining of Language Models Jared Fernandez Yonatan Bisk Emma Strubell KELM 94 2 0 07 Nov 2024
Exploring the Stability Gap in Continual Learning: The Role of the Classification Head Wojciech Łapacz Daniel Marczak Filip Szatkowski Tomasz Trzciñski 94 1 0 06 Nov 2024
Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models Junjiao Tian Chengyue Huang Z. Kira 61 2 0 03 Nov 2024
FEET: A Framework for Evaluating Embedding Techniques Simon A. Lee John Lee Jeffrey N. Chiang 82 4 0 02 Nov 2024
Label Noise: Ignorance Is Bliss Yilun Zhu Jianxin Zhang Aditya Gangrade Clayton Scott NoLa 94 2 0 31 Oct 2024
Preserving Pre-trained Representation Space: On Effectiveness of Prefix-tuning for Large Multi-modal Models Donghoon Kim Gusang Lee Kyuhong Shim B. Shim 97 1 0 29 Oct 2024
FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion Zhenheng Tang Yonggang Zhang Peijie Dong Y. Cheung Amelie Chi Zhou Bo Han Xiaowen Chu FedML MoMe AI4CE 136 9 0 27 Oct 2024
Any Other Thoughts, Hedgehog? Linking Deliberation Chains in Collaborative Dialogues Abhijnan Nath Videep Venkatesha Mariah Bradford Avyakta Chelle Austin Youngren Carlos Mabrey Nathaniel Blanchard Nikhil Krishnaswamy 83 3 0 25 Oct 2024
Diffusion Curriculum: Synthetic-to-Real Generative Curriculum Learning via Image-Guided Diffusion Yijun Liang Shweta Bhardwaj Dinesh Manocha 87 0 0 17 Oct 2024
Guarantees for Nonlinear Representation Learning: Non-identical Covariates, Dependent Data, Fewer Samples Thomas T. Zhang Bruce D. Lee Ingvar M. Ziemann George J. Pappas Nikolai Matni CML OOD 145 0 0 15 Oct 2024
COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement Yuxi Xie Anirudh Goyal Xiaobao Wu Xunjian Yin Xiao Xu Min-Yen Kan Liangming Pan William Yang Wang LRM 358 1 0 12 Oct 2024
Debiasing Vison-Language Models with Text-Only Training Yunfan Yang Chaoquan Jiang Zhiyu Lin Jinlin Xiao Jiaming Zhang Jitao Sang VLM 78 1 0 12 Oct 2024
Zeroth-Order Fine-Tuning of LLMs in Random Subspaces Ziming Yu Pan Zhou Sike Wang Jia Li Hua Huang 77 0 0 11 Oct 2024
Simultaneous Reward Distillation and Preference Learning: Get You a Language Model Who Can Do Both Abhijnan Nath Changsoo Jung Ethan Seefried Nikhil Krishnaswamy 489 4 0 11 Oct 2024
LatteCLIP: Unsupervised CLIP Fine-Tuning via LMM-Synthetic Texts Anh-Quan Cao M. Jaritz Matthieu Guillaumin Raoul de Charette Loris Bazzani VLM CLIP 105 2 0 10 Oct 2024
Features are fate: a theory of transfer learning in high-dimensional regression Javan Tahir Surya Ganguli Grant M. Rotskoff 71 2 0 10 Oct 2024
VehicleSDF: A 3D generative model for constrained engineering design via surrogate modeling Hayata Morita Kohei Shintani Chenyang Yuan Frank Permenter AI4CE 143 2 0 09 Oct 2024
Does RoBERTa Perform Better than BERT in Continual Learning: An Attention Sink Perspective Xueying Bai Yifan Sun Niranjan Balasubramanian CLL 68 0 0 08 Oct 2024
A Cross-Lingual Meta-Learning Method Based on Domain Adaptation for Speech Emotion Recognition David-Gabriel Ion Razvan-Alexandru Smadu Dumitru-Clementin Cercel Florin-Catalin Pop Mihaela-Claudia Cercel 65 0 0 06 Oct 2024
Adjusting Pretrained Backbones for Performativity Berker Demirel Lingjing Kong Kun Zhang Theofanis Karaletsos Celestine Mendler-Dünner Francesco Locatello KELM 67 0 0 06 Oct 2024
Implicit to Explicit Entropy Regularization: Benchmarking ViT Fine-tuning under Noisy Labels Maria Marrium Arif Mahmood Mohammed Bennamoun NoLa AAML 102 0 0 05 Oct 2024
SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation Mucong Ding Bang An Yuancheng Xu Anirudh Satheesh Furong Huang 70 1 0 03 Oct 2024
DaWin: Training-free Dynamic Weight Interpolation for Robust Adaptation Changdae Oh Yixuan Li Kyungwoo Song Sangdoo Yun Dongyoon Han OOD MoMe 91 10 0 03 Oct 2024
Investigating the Impact of Model Complexity in Large Language Models Jing Luo Huiyuan Wang Weiran Huang 69 0 0 01 Oct 2024
Lessons and Insights from a Unifying Study of Parameter-Efficient Fine-Tuning (PEFT) in Visual Recognition Zheda Mai Ping Zhang Cheng-Hao Tu Hong-You Chen Li Zhang Wei-Lun Chao 52 1 0 24 Sep 2024
Zero-shot forecasting of chaotic systems Yuanzhao Zhang William Gilpin AI4TS 262 8 0 24 Sep 2024
Not Only the Last-Layer Features for Spurious Correlations: All Layer Deep Feature Reweighting Humza Wajid Hameed Géraldin Nanfack Eugene Belilovsky 72 1 0 23 Sep 2024
LARE: Latent Augmentation using Regional Embedding with Vision-Language Model Kosuke Sakurai Tatsuya Ishii Ryotaro Shimizu Linxin Song Masayuki Goto VLM 76 0 0 19 Sep 2024
EFCM: Efficient Fine-tuning on Compressed Models for deployment of large models in medical image analysis Shaojie Li Zhaoshuo Diao 61 0 0 18 Sep 2024
Finetuning CLIP to Reason about Pairwise Differences Dylan Sam Devin Willmott João Dias Semedo J. Zico Kolter VLM 115 4 0 15 Sep 2024
Minimizing Embedding Distortion for Robust Out-of-Distribution Performance Tom Shaked Yuval Goldman Oran Shayer OODD 74 0 0 11 Sep 2024