How hard are computer vision datasets? Calibrating dataset difficulty to viewing time D Mayo, J Cummings, X Lin, D Gutfreund, B Katz, A Barbu Advances in Neural Information Processing Systems 36, 11008-11036, 2023 | 4 | 2023 |
Developing a series of ai challenges for the united states department of the air force V Gadepally, G Angelides, A Barbu, A Bowne, LJ Brattain, T Broderick, ... 2022 IEEE High Performance Extreme Computing Conference (HPEC), 1-7, 2022 | 2 | 2022 |
ObjectNet Captions: Models are not superhuman captioners J Cummings, D Mayo, IA Palmer, JR Glass, B Katz, A Barbu | | 2023 |
Detecting Dataset Drift and Non-IID Sampling via k-Nearest Neighbors J Cummings, E Snorrason, J Mueller arXiv preprint arXiv:2305.15696, 2023 | | 2023 |
Image recognition time for humans predicts adversarial vulnerability for models D Mayo, J Cummings, X Lin, B Katz, A Barbu NeurIPS ML Safety Workshop, 2022 | | 2022 |
Workshop version: How hard are computer vision datasets? Calibrating dataset difficulty to viewing time D Mayo, J Cummings, X Lin, D Gutfreund, B Katz, A Barbu SVRHM 2022 Workshop@ NeurIPS, 2022 | | 2022 |
Growing ObjectNet: Adding speech, VQA, occlusion, and measuring dataset difficulty D Mayo, D Lu, C Zhang, J Cummings, X Lin, B Katz, JR Glass, A Barbu ICML 2022 Shift Happens Workshop, 2022 | | 2022 |