Distilling Model Failures as Directions in Latent Space

29 June 2022

Papers citing "Distilling Model Failures as Directions in Latent Space"

50 / 67 papers shown

Title
Fine-Grained Bias Exploration and Mitigation for Group-Robust Classification Miaoyun Zhao Qiang Zhang C. Li 18 0 0 11 May 2025
Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifiers Quentin Guimard Moreno DÍncà Massimiliano Mancini Elisa Ricci SSL 72 0 0 29 Apr 2025
Class-Conditional Distribution Balancing for Group Robust Classification Miaoyun Zhao Qiang Zhang C. Li 60 0 0 24 Apr 2025
Learning from Reasoning Failures via Synthetic Data Generation Gabriela Ben-Melech Stan Estelle Aflalo Avinash Madasu Vasudev Lal Phillip Howard SyDa LRM 39 0 0 20 Apr 2025
Severing Spurious Correlations with Data Pruning Varun Mulchandani Jung-Eun Kim 58 0 0 24 Mar 2025
When does a predictor know its own loss? Aravind Gollakota Parikshit Gopalan Aayush Karan Charlotte Peale Udi Wieder UQCV FaML 63 0 0 27 Feb 2025
Interpreting CLIP with Hierarchical Sparse Autoencoders Vladimir Zaigrajew Hubert Baniecki P. Biecek 49 0 0 27 Feb 2025
Detecting Systematic Weaknesses in Vision Models along Predefined Human-Understandable Dimensions Sujan Sai Gannamaneni Rohil Prakash Rao Michael Mock Maram Akila Stefan Wrobel AAML 62 0 0 17 Feb 2025
Dataset Augmentation by Mixing Visual Concepts Abdullah Al Rahat Hemanth Venkateswara DiffM 68 0 0 19 Dec 2024
RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models Maya Varma Jean-Benoit Delbrouck Zhihong Chen Akshay S. Chaudhari C. Langlotz VLM 29 6 0 06 Nov 2024
DISCERN: Decoding Systematic Errors in Natural Language for Text Classifiers Rakesh R Menon Shashank Srivastava 26 1 0 29 Oct 2024
LLM-Assisted Red Teaming of Diffusion Models through "Failures Are Fated, But Can Be Faded" Som Sagar Aditya Taparia Ransalu Senanayake 13 0 0 22 Oct 2024
SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation Mucong Ding Bang An Yuancheng Xu Anirudh Satheesh Furong Huang 14 1 0 03 Oct 2024
DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanation Rakshith Subramanyam Kowshik Thopalli V. Narayanaswamy Jayaraman J.Thiagarajan 18 2 0 01 Aug 2024
LADDER: Language Driven Slice Discovery and Error Rectification Shantanu Ghosh Rayan Syed Chenyu Wang Clare B. Poynton Kayhan Batmanghelich 27 1 0 31 Jul 2024
Evaluating Model Bias Requires Characterizing its Mistakes Isabela Albuquerque Jessica Schrouff David Warde-Farley Ali Taylan Cemgil Sven Gowal Olivia Wiles 42 2 0 15 Jul 2024
Data Debiasing with Datamodels (D3M): Improving Subgroup Robustness via Data Selection Saachi Jain Kimia Hamidieh Kristian Georgiev Andrew Ilyas Marzyeh Ghassemi Aleksander Madry 27 2 0 24 Jun 2024
Slicing Through Bias: Explaining Performance Gaps in Medical Image Analysis using Slice Discovery Methods Vincent Olesen Nina Weng Aasa Feragen Eike Petersen 26 0 0 17 Jun 2024
Failures Are Fated, But Can Be Faded: Characterizing and Mitigating Unwanted Behaviors in Large-Scale Vision and Language Models Som Sagar Aditya Taparia Ransalu Senanayake 34 10 0 11 Jun 2024
Simplicity Bias of Two-Layer Networks beyond Linearly Separable Data Nikita Tsoy Nikola Konstantinov 24 4 0 27 May 2024
Identification of Fine-grained Systematic Errors via Controlled Scene Generation Valentyn Boreiko Matthias Hein J. H. Metzen 19 1 0 10 Apr 2024
Controlled Training Data Generation with Diffusion Models Teresa Yeo Andrei Atanov Harold Benoit Aleksandr Alekseev Ruchira Ray Pooya Esmaeil Akhoondi Amir Zamir 26 4 0 22 Mar 2024
Discover and Mitigate Multiple Biased Subgroups in Image Classifiers Zeliang Zhang Mingqian Feng Zhiheng Li Chenliang Xu 41 8 0 19 Mar 2024
Distributionally Generative Augmentation for Fair Facial Attribute Classification Fengda Zhang Qianpei He Kun Kuang Jiashuo Liu Long Chen Chao-Xiang Wu Jun Xiao Hanwang Zhang CVBM 27 8 0 11 Mar 2024
Revisiting Confidence Estimation: Towards Reliable Failure Prediction Fei Zhu Xu-Yao Zhang Zhen Cheng Cheng-Lin Liu UQCV 39 10 0 05 Mar 2024
A hierarchical decomposition for explaining ML performance discrepancies Jean Feng Harvineet Singh Fan Xia Adarsh Subbaswamy Alexej Gossmann CML 25 0 0 22 Feb 2024
Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization James Oldfield Markos Georgopoulos Grigorios G. Chrysos Christos Tzelepis Yannis Panagakis M. Nicolaou Jiankang Deng Ioannis Patras MoE 32 8 0 19 Feb 2024
Clarify: Improving Model Robustness With Natural Language Corrections Yoonho Lee Michelle S. Lam Helena Vasconcelos Michael S. Bernstein Chelsea Finn 18 6 0 06 Feb 2024
An Ambiguity Measure for Recognizing the Unknowns in Deep Learning Roozbeh Yousefzadeh AAML UQCV 18 0 0 11 Dec 2023
Language-assisted Vision Model Debugger: A Sample-Free Approach to Finding and Fixing Bugs Chaoquan Jiang Jinqiang Wang Rui Hu Jitao Sang 8 0 0 09 Dec 2023
Identifying and Mitigating Model Failures through Few-shot CLIP-aided Diffusion Generation Atoosa Malemir Chegini S. Feizi VLM 25 2 0 09 Dec 2023
Error Discovery by Clustering Influence Embeddings Fulton Wang Julius Adebayo Sarah Tan Diego Garcia-Olano Narine Kokhlikyan 11 3 0 07 Dec 2023
Describing Differences in Image Sets with Natural Language Lisa Dunlap Yuhui Zhang Xiaohan Wang Ruiqi Zhong Trevor Darrell Jacob Steinhardt Joseph E. Gonzalez Serena Yeung-Levy CoGe VLM 23 30 0 05 Dec 2023
GeNIe: Generative Hard Negative Images Through Diffusion Soroush Abbasi Koohpayegani Anuj Singh K. Navaneet Hadi Jamali Rad Hamed Pirsiavash VLM DiffM 18 4 0 05 Dec 2023
Concept Distillation: Leveraging Human-Centered Explanations for Model Improvement Avani Gupta Saurabh Saini P. J. Narayanan 10 6 0 26 Nov 2023
On original and latent space connectivity in deep neural networks Boyang Gu Anastasia Borovykh GNN 3DPC 17 1 0 12 Nov 2023
Effective Human-AI Teams via Learned Natural Language Rules and Onboarding Hussein Mozannar Jimin J Lee Dennis L. Wei P. Sattigeri Subhro Das David Sontag 39 11 0 02 Nov 2023
PRIME: Prioritizing Interpretability in Failure Mode Extraction Keivan Rezaei Mehrdad Saberi Mazda Moayeri S. Feizi 17 6 0 29 Sep 2023
FACTS: First Amplify Correlations and Then Slice to Discover Bias Sriram Yenamandra Baifeng Shi Trevor Darrell Judy Hoffman CML 14 21 0 29 Sep 2023
Identifying Systematic Errors in Object Detectors with the SCROD Pipeline Valentyn Boreiko Matthias Hein J. H. Metzen 6 5 0 23 Sep 2023
Dream the Impossible: Outlier Imagination with Diffusion Models Xuefeng Du Yiyou Sun Xiaojin Zhu Yixuan Li 11 52 0 23 Sep 2023
PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning Florian Bordes Shashank Shekhar Mark Ibrahim Diane Bouchacourt Pascal Vincent Ari S. Morcos 23 24 0 08 Aug 2023
Mass-Producing Failures of Multimodal Systems with Language Models Shengbang Tong Erik Jones Jacob Steinhardt 20 33 0 21 Jun 2023
LOVM: Language-Only Vision Model Selection O. Zohar Shih-Cheng Huang Kuan-Chieh Jackson Wang Serena Yeung MLLM 24 12 0 15 Jun 2023
LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images Viraj Prabhu Sriram Yenamandra Prithvijit Chattopadhyay Judy Hoffman 13 37 0 30 May 2023
Diversify Your Vision Datasets with Automatic Diffusion-Based Augmentation Lisa Dunlap Alyssa Umino Han Zhang Jiezhi Yang Joseph E. Gonzalez Trevor Darrell DiffM 12 70 0 25 May 2023
Text-To-Concept (and Back) via Cross-Model Alignment Mazda Moayeri Keivan Rezaei Maziar Sanjabi S. Feizi CLIP 31 39 0 10 May 2023
The Role of Data Curation in Image Captioning Wenyan Li Jonas F. Lotz Chen Qiu Desmond Elliott DiffM 19 6 0 05 May 2023
Discover and Cure: Concept-aware Mitigation of Spurious Correlation Shirley Wu Mert Yuksekgonul Linjun Zhang James Y. Zou 65 54 0 01 May 2023
Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning Yu Yang Besmira Nushi Hamid Palangi Baharan Mirzasoleiman 18 36 0 08 Apr 2023