Æȷοì
Ameya Prabhu
Ameya Prabhu
Tübingen AI Center, University of Tübingen
bethgelab.orgÀÇ À̸ÞÀÏ È®ÀÎµÊ - ȨÆäÀÌÁö
Á¦¸ñ
Àοë
Àοë
¿¬µµ
GDumb: A Simple Approach that Questions Our Progress in Continual Learning
A Prabhu, PHS Torr, PK Dokania
Proceedings of the European Conference on Computer Vision (ECCV) 2020, 2020
6712020
Towards sub-word level compositions for sentiment analysis of hindi-english code mixed text
A Joshi, A Prabhu, M Shrivastava, V Varma
Proceedings of COLING 2016, the 26th International Conference on ¡¦, 2016
217*2016
Inverse scaling: When bigger isn't better
IR McKenzie, A Lyzhov, M Pieler, A Parrish, A Mueller, A Prabhu, ...
Transactions of Machine Learning Research (TMLR), 2023
136*2023
Simple unsupervised multi-object tracking
S Karthik, A Prabhu, V Gandhi
arXiv preprint arXiv:2006.02609, 2020
1032020
Deep expander networks: Efficient deep networks from graph theory
A Prabhu, G Varma, A Namboodiri
Proceedings of the European Conference on Computer Vision (ECCV), 20-35, 2018
912018
Sampling Bias in Deep Active Classification: An Empirical Study
A Prabhu, C Dognin, M Singh
2019 Conference on Empirical Methods in Natural Language Processing (EMNLP ¡¦, 2019
722019
Real-time evaluation in online continual learning: A new hope
Y Ghunaim, A Bibi, K Alhamoud, M Alfarra, HA Al Kader Hammoud, ...
Proceedings of the IEEE/CVF conference on computer vision and pattern ¡¦, 2023
65*2023
Towards deep learning in hindi ner: An approach to tackle the labelled data scarcity
V Athavale, S Bharadwaj, M Pamecha, A Prabhu, M Shrivastava
arXiv preprint arXiv:1610.09756, 2016
632016
Computationally budgeted continual learning: What does matter?
A Prabhu, HA Al Kader Hammoud, PK Dokania, PHS Torr, SN Lim, ...
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern ¡¦, 2023
622023
Towards adversarial evaluations for inexact machine unlearning
S Goel, A Prabhu, A Sanyal, SN Lim, P Torr, P Kumaraguru
arXiv preprint arXiv:2201.06640, 2022
55*2022
No" zero-shot" without exponential data: Pretraining concept frequency determines multimodal model performance
V Udandarao, A Prabhu, A Ghosh, Y Sharma, P Torr, A Bibi, S Albanie, ...
The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024
412024
Online continual learning without the storage constraint
A Prabhu, Z Cai, P Dokania, P Torr, V Koltun, O Sener
arXiv preprint arXiv:2305.09253, 2023
352023
Corrective machine unlearning
S Goel, A Prabhu, P Torr, P Kumaraguru, A Sanyal
arXiv preprint arXiv:2402.14015, 2024
252024
No Cost Likelihood Manipulation at Test Time for Making Better Mistakes in Deep Networks
S Karthik, A Prabhu, PK Dokania, V Gandhi
International Conference on Learning Representations (ICLR), 2021, 2021
232021
Hybrid binary networks: optimizing for accuracy, efficiency and memory
A Prabhu, V Batchu, R Gajawada, SA Munagala, A Namboodiri
2018 IEEE Winter Conference on Applications of Computer Vision (WACV), 821-829, 2018
182018
Rapid Adaptation in Online Continual Learning: Are We Evaluating It Right?
HA Al Kader Hammoud, A Prabhu, SN Lim, PHS Torr, A Bibi, B Ghanem
Proceedings of the IEEE/CVF International Conference on Computer Vision ¡¦, 2023
16*2023
From categories to classifier: Name-only continual learning by exploring the web
A Prabhu, HAAK Hammoud, SN Lim, B Ghanem, PHS Torr, A Bibi
Third Conference on Lifelong Learning Agents (CoLLAs) - Oral, 2023
62023
A Practitioner's Guide to Continual Multimodal Pretraining
K Roth, V Udandarao, S Dziadzio, A Prabhu, M Cherti, O Vinyals, ...
The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024
52024
Wu's Method can Boost Symbolic AI to Rival Silver Medalists and AlphaGeometry to Outperform Gold Medalists at IMO Geometry
S Sinha, A Prabhu, P Kumaraguru, S Bhat, M Bethge
arXiv preprint arXiv:2404.06405, 2024
52024
Efficient Lifelong Model Evaluation in an Era of Rapid Progress
A Prabhu, V Udandarao, P Torr, M Bethge, A Bibi, S Albanie
The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024
5*2024
ÇöÀç ½Ã½ºÅÛÀÌ ÀÛµ¿µÇÁö ¾Ê½À´Ï´Ù. ³ªÁß¿¡ ´Ù½Ã ½ÃµµÇØ ÁÖ¼¼¿ä.
ÇмúÀÚ·á 1–20