activity
20162026
most citedUnderstanding the Role of Training Regimes in Continual Learning

90 citations · 362 across the 42 of their papers we have counts for

collaborators
Showing cs.CVShow all

7 papers · 1 filter

cs.CV2024

CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data

Sachin Mehta, Maxwell Horton, Fartash Faghri +5

Contrastive learning has emerged as a transformative method for learning effective visual representations through the alignment of image and text embeddings. However, pairwise simi…

cs.CV2023

Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models

Raviteja Vemulapalli, Hadi Pouransari, Fartash Faghri +4

Vision Foundation Models (VFMs) pretrained on massive datasets exhibit impressive performance on various downstream tasks, especially with limited labeled target data. However, due…

cs.CV20231 cited

TiC-CLIP: Continual Training of CLIP Models

Saurabh Garg, Mehrdad Farajtabar, Hadi Pouransari +5

Keeping large foundation models up to date on latest data is inherently expensive. To avoid the prohibitive costs of constantly retraining, it is imperative to continually train th…

cs.CV202313 cited

SAM-CLIP: Merging Vision Foundation Models towards Semantic and Spatial Understanding

Haoxiang Wang, Pavan Kumar Anasosalu Vasu, Fartash Faghri +6

The landscape of publicly available vision foundation models (VFMs), such as CLIP and Segment Anything Model (SAM), is expanding rapidly. VFMs are endowed with distinct capabilitie…

cs.CV2023

On the Efficacy of Multi-scale Data Samplers for Vision Applications

Elvis Nunez, Thomas Merth, Anish Prabhu +4

Multi-scale resolution training has seen an increased adoption across multiple vision tasks, including classification and detection. Training with smaller resolutions enables faste…

cs.CV2023

Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement

Fartash Faghri, Hadi Pouransari, Sachin Mehta +4

We propose Dataset Reinforcement, a strategy to improve a dataset once such that the accuracy of any model architecture trained on the reinforced dataset is improved at no addition…