no code implementations • 6 Feb 2024 • Netta Ollikka, Amro Abbas, Andrea Perin, Markku Kilpeläinen, Stéphane Deny
Deep learning is closing the gap with humans on several object recognition benchmarks.
1 code implementation • 9 Jan 2024 • Amro Abbas, Evgenia Rusak, Kushal Tirumala, Wieland Brendel, Kamalika Chaudhuri, Ari S. Morcos
Using a simple and intuitive complexity measure, we are able to reduce the training cost to a quarter of regular training.
1 code implementation • 3 Oct 2023 • Anas Mahmoud, Mostafa Elhoushi, Amro Abbas, Yu Yang, Newsha Ardalani, Hugh Leather, Ari Morcos
We propose a pruning signal, Sieve, that employs synthetic captions generated by image-captioning models pretrained on small, diverse, and well-aligned image-text pairs to evaluate the alignment of noisy image-text pairs.
1 code implementation • 16 Mar 2023 • Amro Abbas, Kushal Tirumala, Dániel Simig, Surya Ganguli, Ari S. Morcos
Analyzing a subset of LAION, we show that SemDeDup can remove 50% of the data with minimal performance loss, effectively halving training time.
1 code implementation • 16 Jul 2022 • Amro Abbas, Stéphane Deny
We show that classifying these images is still a challenge for all networks tested, with an average accuracy drop of 29. 5% compared to when the objects are presented upright.