Understanding Failures of Deep Networks via Robust Feature Extraction

3 December 2020

Papers citing "Understanding Failures of Deep Networks via Robust Feature Extraction"

49 / 49 papers shown

Title
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
On Large Multimodal Models as Open-World Image Classifiers Alessandro Conti Massimiliano Mancini Enrico Fini Yiming Wang Paolo Rota Elisa Ricci VLM Presented at ResearchTrend Connect \| VLM on 07 May 2025 84 0 0 27 Mar 2025
Attention IoU: Examining Biases in CelebA using Attention Maps Aaron Serianni Tyler Zhu Olga Russakovsky V. V. Ramaswamy 45 0 0 25 Mar 2025
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 46 6 0 06 Nov 2024
Unearthing Skill-Level Insights for Understanding Trade-Offs of Foundation Models Mazda Moayeri Vidhisha Balachandran Varun Chandrasekaran Safoora Yousefi Thomas Fel S. Feizi Besmira Nushi Neel Joshi Vibhav Vineet 32 2 0 17 Oct 2024
LADDER: Language Driven Slice Discovery and Error Rectification Shantanu Ghosh Rayan Syed Chenyu Wang Clare B. Poynton Kayhan Batmanghelich 39 0 0 31 Jul 2024
A Multimodal Automated Interpretability Agent Tamar Rott Shaham Sarah Schwettmann Franklin Wang Achyuta Rajaram Evan Hernandez Jacob Andreas Antonio Torralba 34 17 0 22 Apr 2024
Diffexplainer: Towards Cross-modal Global Explanations with Diffusion Models M. Pennisi Giovanni Bellitto S. Palazzo Mubarak Shah C. Spampinato DiffM 21 0 0 03 Apr 2024
Language-assisted Vision Model Debugger: A Sample-Free Approach to Finding and Fixing Bugs Chaoquan Jiang Jinqiang Wang Rui Hu Jitao Sang 24 0 0 09 Dec 2023
Identifying and Mitigating Model Failures through Few-shot CLIP-aided Diffusion Generation Atoosa Malemir Chegini S. Feizi VLM 40 4 0 09 Dec 2023
Error Discovery by Clustering Influence Embeddings Fulton Wang Julius Adebayo Sarah Tan Diego Garcia-Olano Narine Kokhlikyan 21 3 0 07 Dec 2023
Detecting algorithmic bias in medical-AI models using trees Jeffrey Smith Andre L. Holder Rishikesan Kamaleswaran Yao Xie 32 1 0 05 Dec 2023
Probing clustering in neural network representations Thao Nguyen Simon Kornblith 32 1 0 14 Nov 2023
Detecting Spurious Correlations via Robust Visual Concepts in Real and AI-Generated Image Classification Preetam Prabhu Srikar Dammu Chirag Shah 35 2 0 03 Nov 2023
FACTS: First Amplify Correlations and Then Slice to Discover Bias Sriram Yenamandra Baifeng Shi Trevor Darrell Judy Hoffman CML 23 22 0 29 Sep 2023
TorchQL: A Programming Framework for Integrity Constraints in Machine Learning Aaditya Naik Adam Stein Yinjun Wu Mayur Naik Eric Wong 35 3 0 13 Aug 2023
Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms Nari Johnson Ángel Alexander Cabrera Gregory Plumb Ameet Talwalkar 31 13 0 13 Jun 2023
Efficient Failure Pattern Identification of Predictive Algorithms Bao Nguyen Viet Anh Nguyen 22 0 0 01 Jun 2023
LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images Viraj Prabhu Sriram Yenamandra Prithvijit Chattopadhyay Judy Hoffman 22 37 0 30 May 2023
Mitigating Spurious Correlations in Multi-modal Models during Fine-tuning Yu Yang Besmira Nushi Hamid Palangi Baharan Mirzasoleiman 39 36 0 08 Apr 2023
Mitigating Source Bias for Fairer Weak Supervision Changho Shin Sonia Cromp Dyah Adila Frederic Sala 29 2 0 30 Mar 2023
Diagnosing and Rectifying Vision Models using Language Yuhui Zhang Jeff Z. HaoChen Shih-Cheng Huang Kuan-Chieh Jackson Wang James Zou Serena Yeung 25 45 0 08 Feb 2023
Discovering and Mitigating Visual Biases through Keyword Explanation Younghyun Kim Sangwoo Mo Minkyu Kim Kyungmin Lee Jaeho Lee Jinwoo Shin 40 32 0 26 Jan 2023
Look Beyond Bias with Entropic Adversarial Data Augmentation Thomas Duboudin Emmanuel Dellandréa Corentin Abgrall Gilles Hénaff Liming Luke Chen CML 35 4 0 10 Jan 2023
A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others Zhiheng Li Ivan Evtimov Albert Gordo C. Hazirbas Tal Hassner Cristian Canton Ferrer Chenliang Xu Mark Ibrahim 34 71 0 09 Dec 2022
Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet Yannic Neuhaus Maximilian Augustin Valentyn Boreiko Matthias Hein AAML 36 30 0 09 Dec 2022
Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases Mazda Moayeri Wenxiao Wang Sahil Singla S. Feizi 69 14 0 05 Dec 2022
AGRO: Adversarial Discovery of Error-prone groups for Robust Optimization Bhargavi Paranjape Pradeep Dasigi Vivek Srikumar Luke Zettlemoyer Hannaneh Hajishirzi 36 7 0 02 Dec 2022
Data-Centric Debugging: mitigating model failures via targeted data collection Sahil Singla Atoosa Malemir Chegini Mazda Moayeri Soheil Feiz 21 4 0 17 Nov 2022
Identifying Spurious Correlations and Correcting them with an Explanation-based Learning Misgina Tsighe Hagos Kathleen M. Curran Brian Mac Namee 20 10 0 15 Nov 2022
Demystify Self-Attention in Vision Transformers from a Semantic Perspective: Analysis and Application Leijie Wu Song Guo Yaohong Ding Junxiao Wang Wenchao Xu Richard Yi Da Xu Jiewei Zhang 38 2 0 13 Nov 2022
Discover, Explanation, Improvement: An Automatic Slice Detection Framework for Natural Language Processing Wenyue Hua Lifeng Jin Linfeng Song Haitao Mi Yongfeng Zhang Dong Yu 26 1 0 08 Nov 2022
Learning Less Generalizable Patterns with an Asymmetrically Trained Double Classifier for Better Test-Time Adaptation Thomas Duboudin Emmanuel Dellandréa Corentin Abgrall Gilles Hénaff Limin Chen TTA 27 1 0 17 Oct 2022
Why Deep Surgical Models Fail?: Revisiting Surgical Action Triplet Recognition through the Lens of Robustness Ya-Hsin Cheng Lihao Liu Shujun Wang Yueming Jin Carola-Bibiane Schönlieb Angelica I. Aviles-Rivero 24 7 0 18 Sep 2022
Explicit Tradeoffs between Adversarial and Natural Distributional Robustness Mazda Moayeri Kiarash Banihashem S. Feizi OOD 72 21 0 15 Sep 2022
Towards a More Rigorous Science of Blindspot Discovery in Image Classification Models Gregory Plumb Nari Johnson Ángel Alexander Cabrera Ameet Talwalkar 34 5 0 08 Jul 2022
Distilling Model Failures as Directions in Latent Space Saachi Jain Hannah Lawrence Ankur Moitra A. Madry 23 90 0 29 Jun 2022
Sparse Visual Counterfactual Explanations in Image Space Valentyn Boreiko Maximilian Augustin Francesco Croce Philipp Berens Matthias Hein BDL CML 30 26 0 16 May 2022
Missingness Bias in Model Debugging Saachi Jain Hadi Salman E. Wong Pengchuan Zhang Vibhav Vineet Sai H. Vemprala A. Madry 27 37 0 19 Apr 2022
Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations Polina Kirichenko Pavel Izmailov A. Wilson OOD 37 318 0 06 Apr 2022
Core Risk Minimization using Salient ImageNet Sahil Singla Mazda Moayeri S. Feizi 30 14 0 28 Mar 2022
Domino: Discovering Systematic Errors with Cross-Modal Embeddings Sabri Eyuboglu M. Varma Khaled Kamal Saab Jean-Benoit Delbrouck Christopher Lee-Messer Jared A. Dunnmon James Zou Christopher Ré 35 143 0 24 Mar 2022
A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes Mazda Moayeri Phillip E. Pope Yogesh Balaji S. Feizi VLM 33 52 0 26 Jan 2022
Thinking Beyond Distributions in Testing Machine Learned Models Negar Rostamzadeh B. Hutchinson Christina Greer Vinodkumar Prabhakaran TTA 37 6 0 06 Dec 2021
Salient ImageNet: How to discover spurious features in Deep Learning? Sahil Singla S. Feizi AAML VLM 21 115 0 08 Oct 2021
FOCUS: Familiar Objects in Common and Uncommon Settings Priyatham Kattakinda S. Feizi 18 10 0 07 Oct 2021
A Principled Approach to Failure Analysis and Model Repairment: Demonstration in Medical Imaging Thomas Henn Yasukazu Sakamoto Clément Jacquet Shunsuke Yoshizawa M. Andou ... R. Saga Hiroyuki Ishihara Katsuhiko Shimizu Yingzhen Li Ryutaro Tanno 113 9 0 25 Sep 2021
Encouraging Intra-Class Diversity Through a Reverse Contrastive Loss for Better Single-Source Domain Generalization Thomas Duboudin Emmanuel Dellandréa Corentin Abgrall Gilles Hénaff Liming Luke Chen 24 9 0 15 Jun 2021
Local Patch AutoAugment with Multi-Agent Collaboration Shiqi Lin Tao Yu Ruoyu Feng Xin Li Xin Jin Zhibo Chen 16 15 0 20 Mar 2021