v1v2v3 (latest)

ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness

29 November 2018

Wieland Brendel

Papers citing "ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness"

50 / 1,487 papers shown

Title
MiMu: Mitigating Multiple Shortcut Learning Behavior of Transformers Lili Zhao Qi Liu Wei-neng Chen Xiaoou Liu R.-H. Sun Min Hou Yang Wang Shijin Wang 411 2 0 14 Apr 2025
Learning Object Focused AttentionInternational Conference on Pattern Recognition (ICPR), 2025 Vivek Trivedy A. Almalki Longin Jan Latecki 188 0 0 10 Apr 2025
Intermediate Layer Classifiers for OOD generalizationInternational Conference on Learning Representations (ICLR), 2025 Arnas Uselis Seong Joon Oh OOD 784 7 0 07 Apr 2025
Contour Integration Underlies Human-Like Vision Ben Lonnqvist Elsa Scialom Abdülkadir Gökce Zehra Merchant Michael H. Herzog Martin Schrimpf VLM 250 3 0 07 Apr 2025
Malware Detection in Docker Containers: An Image is Worth a Thousand Logs Akis Nousias Efklidis Katsaros Evangelos Syrmos Panagiotis I. Radoglou-Grammatikis T. Lagkas Vasileios Argyriou Ioannis D. Moscholios Evangelos Markakis Sotirios K Goudos Panagiotis G. Sarigiannidis 99 3 0 04 Apr 2025
v-CLR: View-Consistent Learning for Open-World Instance SegmentationComputer Vision and Pattern Recognition (CVPR), 2025 Chang-Bin Zhang Jinhong Ni Yujie Zhong Kai Han 3DV VLM 410 2 0 02 Apr 2025
Spectral-Adaptive Modulation Networks for Visual Perception Guhnoo Yun J. Yoo Kijung Kim Jeongho Lee Paul Hongsuck Seo Dong Hwan Kim 378 0 0 31 Mar 2025
Attention IoU: Examining Biases in CelebA using Attention MapsComputer Vision and Pattern Recognition (CVPR), 2025 Aaron Serianni Tyler Zhu Olga Russakovsky V. V. Ramaswamy 273 1 0 25 Mar 2025
DDB: Diffusion Driven Balancing to Address Spurious Correlations Aryan Yazdan Parast Basim Azam Naveed Akhtar 295 0 0 21 Mar 2025
Beyond Accuracy: What Matters in Designing Well-Behaved Models? Robin Hesse Doğukan Bağcı Bernt Schiele Simone Schaub-Meyer Stefan Roth VLM 285 0 0 21 Mar 2025
EasyRobust: A Comprehensive and Easy-to-use Toolkit for Robust and Generalized Vision Xiaofeng Mao YueFeng Chen Rong Zhang Hui Xue Zhao Li Hang Su AAML VLM 266 0 0 21 Mar 2025
Global Renewables Watch: A Temporal Dataset of Solar and Wind Energy Derived from Satellite Imagery Caleb Robinson Anthony Ortiz Allen Kim Rahul Dodhia Andrew Zolli Shivaprakash K. Nagaraju J. O J. Kiesecker J. L. Ferres 214 3 0 19 Mar 2025
Test-Time Backdoor Detection for Object Detection ModelsComputer Vision and Pattern Recognition (CVPR), 2025 Hangtao Zhang Yichen Wang Shihui Yan Chenyu Zhu Ziqi Zhou Linshan Hou Shengshan Hu Minghui Li Yanjun Zhang L. Zhang AAML 183 9 0 19 Mar 2025
GSBA $^K$ : $top$ - $K$ Geometric Score-based Black-box Attack Md. Farhamdur Reza Richeng Jin Tianfu Wu H. Dai AAML 299 0 0 17 Mar 2025
MAME: Multidimensional Adaptive Metamer Exploration with Human Perceptual Feedback Mina Kamao Hayato Ono Ayumu Yamashita Kaoru Amano Masataka Sawayama 200 0 0 17 Mar 2025
Do Vision Models Develop Human-Like Progressive Difficulty Understanding? Zeyi Huang Utkarsh Ojha Zeyi Huang Donghyun Lee Yong Jae Lee OOD VLM 364 0 1 17 Mar 2025
Neural Edge Histogram Descriptors for Underwater Acoustic Target Recognition Atharva Agashe Davelle Carreiro A. V. Dine Joshua Peeples 123 0 0 17 Mar 2025
Shape Bias and Robustness Evaluation via Cue Decomposition for Image Classification and Segmentation Edgar Heinert Thomas Gottwald Annika Mütze Matthias Rottmann 340 1 0 16 Mar 2025
Do computer vision foundation models learn the low-level characteristics of the human visual system?Computer Vision and Pattern Recognition (CVPR), 2025 Yancheng Cai Fei Yin Dounia Hammou Rafal Mantiuk VLM 429 7 0 13 Mar 2025
Robust Asymmetric Heterogeneous Federated Learning with Corrupted ClientsIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025 Xiuwen Fang Mang Ye Di Lin FedML 358 4 0 12 Mar 2025
ForAug: Recombining Foregrounds and Backgrounds to Improve Vision Transformer Training with Bias Mitigation Tobias Christian Nauen Brian B. Moser Federico Raue Stanislav Frolov Andreas Dengel ViT 445 0 0 12 Mar 2025
Debiased Prompt Tuning in Vision-Language Model without Annotations Chaoquan Jiang Yunfan Yang Rui Hu Jitao Sang VLM 222 0 0 11 Mar 2025
Trend-Aware Supervision: On Learning Invariance for Semi-Supervised Facial Action Unit Intensity EstimationAAAI Conference on Artificial Intelligence (AAAI), 2024 Yingjie Chen Jiarui Zhang Tao Wang Yun Liang 246 1 0 11 Mar 2025
i-WiViG: Interpretable Window Vision GNN Ivica Obadic D. Kangin Dario Augusto Borges Oliveira Plamen Angelov Xiao Xiang Zhu 271 1 0 11 Mar 2025
Robusto-1 Dataset: Comparing Humans and VLMs on real out-of-distribution Autonomous Driving VQA from Peru Dunant Cusipuma David Ortega Victor Flores-Benites Arturo Deza OOD 262 0 0 10 Mar 2025
Generalizable Image Repair for Robust Visual Control Carson Sobolewski Zhenjiang Mao Kshitij Vejre Ivan Ruchkin 251 0 0 07 Mar 2025
Visual Cues of Gender and Race are Associated with Stereotyping in Vision-Language Models Messi H.J. Lee Soyeon Jeon Jacob M. Montgomery Calvin K. Lai VLM CoGe 233 1 0 07 Mar 2025
Do ImageNet-trained models learn shortcuts? The impact of frequency shortcuts on generalizationComputer Vision and Pattern Recognition (CVPR), 2025 Shunxin Wang Raymond N. J. Veldhuis N. Strisciuglio VLM 408 0 0 05 Mar 2025
Reduced Spatial Dependency for More General Video-level Deepfake DetectionIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2025 Beilin Chu Xuan Xu Yanzhe Zhang Weike You Linna Zhou 178 2 0 05 Mar 2025
On the Relationship Between Double Descent of CNNs and Shape/Texture Bias Under Learning ProcessInternational Conference on Pattern Recognition (ICPR), 2025 Shun Iwase Shuya Takahashi Nakamasa Inoue Rio Yokota Ryo Nakamura Hirokatsu Kataoka 238 0 0 04 Mar 2025
A Causal Framework for Aligning Image Quality Metrics and Deep Neural Network Robustness Nathan G. Drenkow Mathias Unberath OOD 299 0 0 04 Mar 2025
Seeing Eye to AI? Applying Deep-Feature-Based Similarity Metrics to Information VisualizationInternational Conference on Human Factors in Computing Systems (CHI), 2025 Sheng Long Angelos Chatzimparmpas Emma Alexander Matthew Kay Jessica Hullman 300 0 0 28 Feb 2025
Data Distributional Properties As Inductive Bias for Systematic GeneralizationComputer Vision and Pattern Recognition (CVPR), 2025 Felipe del-Rio Alain Raymond-Sáez Daniel Florea Rodrigo Toro Icarte Julio Hurtado Cristian B. Calderon Á. Soto AI4CE 398 1 0 27 Feb 2025
Bridging Critical Gaps in Convergent Learning: How Representational Alignment Evolves Across Layers, Training, and Distribution Shifts Chaitanya Kapoor Sudhanshu Srivastava Meenakshi Khosla 342 1 0 26 Feb 2025
PhysAug: A Physical-guided and Frequency-based Data Augmentation for Single-Domain Generalized Object DetectionAAAI Conference on Artificial Intelligence (AAAI), 2024 Xiaoran Xu Jiangang Yang Wenhui Shi Siyuan Ding Luqing Luo Jian Liu 447 6 0 24 Feb 2025
Adversarially Robust CLIP Models Can Induce Better (Robust) Perceptual Metrics Francesco Croce Christian Schlarmann Naman D. Singh Matthias Hein 436 13 0 17 Feb 2025
Alignment and Adversarial Robustness: Are More Human-Like Models More Secure? Blaine Hoak Kunyang Li Patrick McDaniel AAML 135 0 0 17 Feb 2025
Why does my medical AI look at pictures of birds? Exploring the efficacy of transfer learning across domain boundaries F. Jonske M. Kim Enrico Nasca J. Evers Johannes Haubold ... F. Nensa Michael Kamp C. Seibold Jan Egger Jens Kleesiek 315 4 0 17 Feb 2025
We Can't Understand AI Using our Existing Vocabulary John Hewitt Robert Geirhos Been Kim 291 13 0 11 Feb 2025
Towards Fair and Robust Face Parsing for Generative AI: A Multi-Objective ApproachIEEE International Conference on Automatic Face & Gesture Recognition (FG), 2025 Sophia J. Abraham Jonathan D. Hauenstein Walter J. Scheirer CVBM 180 0 0 06 Feb 2025
Dual-Flow: Transferable Multi-Target, Instance-Agnostic Attacks via In-the-wild Cascading Flow Optimization Yixiao Chen Shikun Sun Jianshu Li Ruoyu Li Zhe Li Junliang Xing AAML 587 1 0 04 Feb 2025
Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization Simone Bombari Marco Mondelli 698 5 0 03 Feb 2025
The in-context inductive biases of vision-language models differ across modalities Kelsey Allen Ishita Dasgupta Eliza Kosoy Andrew Kyle Lampinen 369 2 0 03 Feb 2025
Sebra: Debiasing Through Self-Guided Bias RankingInternational Conference on Learning Representations (ICLR), 2025 Adarsh Kappiyath Abhra Chaudhuri Ajay Jaiswal Ziquan Liu Yunpeng Li Xiatian Zhu L. Yin CML 823 2 1 30 Jan 2025
Self-supervised Benchmark Lottery on ImageNet: Do Marginal Improvements Translate to Improvements on Similar Datasets?IEEE International Joint Conference on Neural Network (IJCNN), 2024 Utku Ozbulak Esla Timothy Anzaku Solha Kang W. D. Neve J. Vankerschaver 273 2 0 28 Jan 2025
Dimensions underlying the representational alignment of deep neural networks with humansNature Machine Intelligence (Nat. Mach. Intell.), 2024 F. Mahner Lukas Muttenthaler Umut Güçlü M. Hebart 347 22 0 28 Jan 2025
Benchmarking Image Perturbations for Testing Automated Driving Assistance SystemsInternational Conference on Information Control Systems & Technologies (ICICST), 2025 Stefano Carlo Lambertenghi Hannes Leonhard Andrea Stocco AAML 894 4 0 21 Jan 2025
Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and InsightsNeural Information Processing Systems (NeurIPS), 2025 Sy-Tuyen Ho Tuan Van Vo Somayeh Ebrahimkhani Ngai-Man Cheung 296 1 0 08 Jan 2025
Measuring Error Alignment for Decision-Making SystemsAAAI Conference on Artificial Intelligence (AAAI), 2024 Binxia Xu Antonis Bikakis Daniel Onah A. Vlachidis Luke Dickens 372 1 0 03 Jan 2025
Low-Biased General Annotated Dataset GenerationComputer Vision and Pattern Recognition (CVPR), 2024 Dengyang Jiang Haoyu Wang Lei Zhang Wei Wei Guang Dai Mengmeng Wang Jiangming Wang Yanning Zhang 313 0 0 14 Dec 2024