On the importance of single directions for generalization

19 March 2018

Papers citing "On the importance of single directions for generalization"

50 / 181 papers shown

Title
Natural Language Descriptions of Deep Visual Features Evan Hernandez Sarah Schwettmann David Bau Teona Bagashvili Antonio Torralba Jacob Andreas MILM 206 117 0 26 Jan 2022
Disentangled Latent Transformer for Interpretable Monocular Height Estimation Zhitong Xiong Sining Chen Sining Chen Yilei Shi Xiaoxiang Zhu ViT 24 6 0 17 Jan 2022
Reflash Dropout in Image Super-Resolution Xiangtao Kong Xina Liu Jinjin Gu Yu Qiao Chao Dong UQCV 29 58 0 22 Dec 2021
ReAct: Out-of-distribution Detection With Rectified Activations Yiyou Sun Chuan Guo Yixuan Li OODD 43 457 0 24 Nov 2021
Separating Content and Style for Unsupervised Image-to-Image Translation Yunfei Liu Haofei Wang Yang Yue Feng Lu 27 3 0 27 Oct 2021
UniFed: A Unified Framework for Federated Learning on Non-IID Image Features Meirui Jiang Xiaoxiao Li Xiaofei Zhang Michael Kamp Qianming Dou FedML OOD 34 0 0 19 Oct 2021
On the Pitfalls of Analyzing Individual Neurons in Language Models Omer Antverg Yonatan Belinkov MILM 30 50 0 14 Oct 2021
Quantifying Local Specialization in Deep Neural Networks Shlomi Hod Daniel Filan Stephen Casper Andrew Critch Stuart J. Russell 62 10 0 13 Oct 2021
On the Noise Stability and Robustness of Adversarially Trained Networks on NVM Crossbars Chun Tao Deboleena Roy I. Chakraborty Kaushik Roy AAML 32 2 0 19 Sep 2021
All Bark and No Bite: Rogue Dimensions in Transformer Language Models Obscure Representational Quality William Timkey Marten van Schijndel 226 111 0 09 Sep 2021
Understanding of Kernels in CNN Models by Suppressing Irrelevant Visual Features in Images Jiafan Zhuang Wanying Tao Jianfei Xing Wei Shi Ruixuan Wang Weishi Zheng FAtt 45 3 0 25 Aug 2021
Towards Interpretable Deep Networks for Monocular Depth Estimation Zunzhi You Yi-Hsuan Tsai W. Chiu Guanbin Li FAtt 40 17 0 11 Aug 2021
Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability Roman Levin Manli Shu Eitan Borgnia Furong Huang Micah Goldblum Tom Goldstein FAtt AAML 28 10 0 03 Aug 2021
Distribution of Classification Margins: Are All Data Equal? Andrzej Banburski Fernanda De La Torre Nishka Pant Ishana Shastri T. Poggio 33 4 0 21 Jul 2021
Handcrafted Backdoors in Deep Neural Networks Sanghyun Hong Nicholas Carlini Alexey Kurakin 19 71 0 08 Jun 2021
Fidelity Estimation Improves Noisy-Image Classification With Pretrained Networks Xiaoyu Lin Deblina Bhattacharjee Majed El Helou Sabine Süsstrunk 15 6 0 01 Jun 2021
XOmiVAE: an interpretable deep learning model for cancer classification using high-dimensional omics data Eloise Withnell Xiaoyu Zhang Kai Sun Yike Guo 12 64 0 26 May 2021
Probabilistic Selective Encryption of Convolutional Neural Networks for Hierarchical Services Jinyu Tian Jiantao Zhou Jia Duan AAML 16 9 0 26 May 2021
AFINet: Attentive Feature Integration Networks for Image Classification Xinglin Pan Jing Xu Yu Pan Liangjiang Wen Wenxiang Lin Kun Bai Zenglin Xu 46 10 0 10 May 2021
Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety Sebastian Houben Stephanie Abrecht Maram Akila Andreas Bär Felix Brockherde ... Serin Varghese Michael Weber Sebastian J. Wirkert Tim Wirtz Matthias Woehrle AAML 13 58 0 29 Apr 2021
Estimating the Generalization in Deep Neural Networks via Sparsity Yang Zhao Hao Zhang 48 2 0 02 Apr 2021
Neural Response Interpretation through the Lens of Critical Pathways Ashkan Khakzar Soroosh Baselizadeh Saurabh Khanduja Christian Rupprecht Seong Tae Kim Nassir Navab 29 32 0 31 Mar 2021
Quantitative Performance Assessment of CNN Units via Topological Entropy Calculation Yang Zhao Hao Zhang 24 7 0 17 Mar 2021
Intraclass clustering: an implicit learning ability that regularizes DNNs Simon Carbonnelle Christophe De Vleeschouwer 60 8 0 11 Mar 2021
Robustness to Pruning Predicts Generalization in Deep Neural Networks Lorenz Kuhn Clare Lyle Aidan Gomez Jonas Rothfuss Y. Gal 43 14 0 10 Mar 2021
FedBN: Federated Learning on Non-IID Features via Local Batch Normalization Xiaoxiao Li Meirui Jiang Xiaofei Zhang Michael Kamp Qi Dou OOD FedML 168 790 0 15 Feb 2021
Network Pruning using Adaptive Exemplar Filters Mingbao Lin Rongrong Ji Shaojie Li Yan Wang Yongjian Wu Feiyue Huang QiXiang Ye VLM 19 53 0 20 Jan 2021
Global Context Networks Yue Cao Jiarui Xu Stephen Lin Fangyun Wei Han Hu ISeg 36 96 0 24 Dec 2020
Why Unsupervised Deep Networks Generalize Anita de Mello Koch E. Koch R. Koch OOD 16 8 0 07 Dec 2020
Representation Based Complexity Measures for Predicting Generalization in Deep Learning Parth Natekar Manik Sharma 6 36 0 04 Dec 2020
Learning Class Unique Features in Fine-Grained Visual Classification Runkai Zheng Zhijia Yu Yinqi Zhang C. Ding Hei Victor Cheng Li Liu 16 0 0 22 Nov 2020
Role Taxonomy of Units in Deep Neural Networks Yang Zhao Hao Zhang Xiuyuan Hu 13 1 0 02 Nov 2020
Exemplary Natural Images Explain CNN Activations Better than State-of-the-Art Feature Visualization Judy Borowski Roland S. Zimmermann Judith Schepers Robert Geirhos Thomas S. A. Wallis Matthias Bethge Wieland Brendel FAtt 47 7 0 23 Oct 2020
Towards falsifiable interpretability research Matthew L. Leavitt Ari S. Morcos AAML AI4CE 21 67 0 22 Oct 2020
Linking average- and worst-case perturbation robustness via class selectivity and dimensionality Matthew L. Leavitt Ari S. Morcos AAML 19 2 0 14 Oct 2020
Learning Optimal Representations with the Decodable Information Bottleneck Yann Dubois Douwe Kiela D. Schwab Ramakrishna Vedantam 26 43 0 27 Sep 2020
Implicit Gradient Regularization David Barrett Benoit Dherin 22 147 0 23 Sep 2020
Contextual Semantic Interpretability Diego Marcos Ruth C. Fong Sylvain Lobry Rémi Flamary Nicolas Courty D. Tuia SSL 20 27 0 18 Sep 2020
Understanding the Role of Individual Units in a Deep Neural Network David Bau Jun-Yan Zhu Hendrik Strobelt Àgata Lapedriza Bolei Zhou Antonio Torralba GAN 14 436 0 10 Sep 2020
Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networks Nilaksh Das Haekyu Park Zijie J. Wang Fred Hohman Robert Firstman Emily Rogers Duen Horng Chau AAML 28 26 0 05 Sep 2020
Semantics-aware Adaptive Knowledge Distillation for Sensor-to-Vision Action Recognition Yang Liu Keze Wang Guanbin Li Liang Lin 29 87 0 01 Sep 2020
Self-supervised learning through the eyes of a child A. Orhan Vaibhav Gupta Brenden M. Lake SSL 27 100 0 31 Jul 2020
When and how CNNs generalize to out-of-distribution category-viewpoint combinations Spandan Madan Timothy M. Henry Jamell Dozier Helen Ho Nishchal Bhandari Tomotake Sasaki F. Durand Hanspeter Pfister Xavier Boix OOD 41 24 0 15 Jul 2020
On the relationship between class selectivity, dimensionality, and robustness Matthew L. Leavitt Ari S. Morcos 16 6 0 08 Jul 2020
Are there any óbject detectors' in the hidden layers of CNNs trained to identify objects or scenes? E. Gale Nicholas Martin R. Blything Anh Nguyen J. Bowers 13 14 0 02 Jul 2020
Video Representation Learning with Visual Tempo Consistency Ceyuan Yang Yinghao Xu Bo Dai Bolei Zhou 13 89 0 28 Jun 2020
Towards Understanding Hierarchical Learning: Benefits of Neural Representations Minshuo Chen Yu Bai J. Lee T. Zhao Huan Wang Caiming Xiong R. Socher SSL 20 48 0 24 Jun 2020
New Interpretations of Normalization Methods in Deep Learning Jiacheng Sun Xiangyong Cao Hanwen Liang Weiran Huang Zewei Chen Zhenguo Li 21 35 0 16 Jun 2020
MMA Regularization: Decorrelating Weights of Neural Networks by Maximizing the Minimal Angles Zhennan Wang Canqun Xiang Wenbin Zou Chen Xu 12 19 0 06 Jun 2020
Geometric algorithms for predicting resilience and recovering damage in neural networks G. Raghavan Jiayi Li Matt Thomson AAML 14 0 0 23 May 2020