Trivial or impossible -- dichotomous data difficulty masks model
differences (on ImageNet and beyond)

v1v2v3 (latest)

Trivial or impossible -- dichotomous data difficulty masks model differences (on ImageNet and beyond)

International Conference on Learning Representations (ICLR), 2021

12 October 2021

Luca M. Schulze Buschoff

ArXiv (abs)PDF HTML

Papers citing "Trivial or impossible -- dichotomous data difficulty masks model differences (on ImageNet and beyond)"

18 / 18 papers shown

Title
Data Pruning by Information MaximizationInternational Conference on Learning Representations (ICLR), 2025 Haoru Tan Sitong Wu Wei Huang Shizhen Zhao Xiaojuan Qi 247 6 0 02 Jun 2025
Bridging Distribution Shift and AI Safety: Conceptual and Methodological Synergies Chenruo Liu Kenan Tang Yao Qin Qi Lei 166 1 0 28 May 2025
PEAKS: Selecting Key Training Examples Incrementally via Prediction Error Anchored by Kernel Similarity Mustafa Burak Gurbuz Xingyu Zheng C. Dovrolis OOD 368 0 0 07 Apr 2025
Not All Samples Should Be Utilized Equally: Towards Understanding and Improving Dataset Distillation Shaobo Wang Yantai Yang Qilong Wang Kaixin Li Linfeng Zhang Junchi Yan DD 252 10 0 22 Aug 2024
A Lightweight Measure of Classification Difficulty from Application Dataset Characteristics Bryan Bo Cao Abhinav Sharma Lawrence O'Gorman Michael J. Coss Shubham Jain 189 3 0 09 Apr 2024
How to Train Data-Efficient LLMs Noveen Sachdeva Benjamin Coleman Wang-Cheng Kang Jianmo Ni Lichan Hong Ed H. Chi James Caverlee Julian McAuley D. Cheng 171 88 0 15 Feb 2024
Data Optimization in Deep Learning: A SurveyIEEE Transactions on Knowledge and Data Engineering (TKDE), 2023 Ou Wu Rujing Yao 225 4 0 25 Oct 2023
Functional trustworthiness of AI systems by statistically valid testing Bernhard Nessler Thomas Doms Sepp Hochreiter 80 0 0 04 Oct 2023
D4: Improving LLM Pretraining via Document De-Duplication and DiversificationNeural Information Processing Systems (NeurIPS), 2023 Kushal Tirumala Daniel Simig Armen Aghajanyan Ari S. Morcos SyDa 132 147 0 23 Aug 2023
Are Deep Neural Networks Adequate Behavioural Models of Human Visual Perception?Annual Review of Vision Science (ARVS), 2023 Felix Wichmann Robert Geirhos 172 34 0 26 May 2023
SemDeDup: Data-efficient learning at web-scale through semantic deduplication Amro Abbas Kushal Tirumala Daniel Simig Surya Ganguli Ari S. Morcos 210 223 0 16 Mar 2023
ModelDiff: A Framework for Comparing Learning AlgorithmsInternational Conference on Machine Learning (ICML), 2022 Harshay Shah Sung Min Park Andrew Ilyas Aleksander Madry SyDa 160 33 0 22 Nov 2022
Similarity of Neural Architectures using Adversarial Attack TransferabilityEuropean Conference on Computer Vision (ECCV), 2022 Ian Ryu Dongyoon Han Byeongho Heo Song Park Sanghyuk Chun Jong-Seok Lee AAML 363 2 0 20 Oct 2022
Random initialisations performing above chance and how to find them Frederik Benzing Simon Schug Robert Meier J. Oswald Yassir Akram Nicolas Zucchet Laurence Aitchison Angelika Steger ODL 285 28 0 15 Sep 2022
On the Strong Correlation Between Model Invariance and GeneralizationNeural Information Processing Systems (NeurIPS), 2022 Weijian Deng Stephen Gould Liang Zheng OOD 168 24 0 14 Jul 2022
Beyond neural scaling laws: beating power law scaling via data pruningNeural Information Processing Systems (NeurIPS), 2022 Ben Sorscher Robert Geirhos Shashank Shekhar Surya Ganguli Ari S. Morcos 462 523 0 29 Jun 2022
A Tour of Visualization Techniques for Computer Vision Datasets B. Alsallakh P. Bhattacharya V. Feng Narine Kokhlikyan Orion Reblitz-Richardson Rahul Rajan David Yan 110 4 0 19 Apr 2022
Partial success in closing the gap between human and machine visionNeural Information Processing Systems (NeurIPS), 2021 Robert Geirhos Kantharaju Narayanappa Benjamin Mitzkus Tizian Thieringer Matthias Bethge Felix Wichmann Wieland Brendel VLM AAML 241 256 0 14 Jun 2021