no code implementations • 30 Nov 2023 • Raviteja Vemulapalli, Hadi Pouransari, Fartash Faghri, Sachin Mehta, Mehrdad Farajtabar, Mohammad Rastegari, Oncel Tuzel
Motivated by this, we ask the following important question, "How can we leverage the knowledge from a large VFM to train a small task-specific model for a new target task with limited labeled training data?
1 code implementation • 28 Nov 2023 • Pavan Kumar Anasosalu Vasu, Hadi Pouransari, Fartash Faghri, Raviteja Vemulapalli, Oncel Tuzel
We further demonstrate the effectiveness of our multi-modal reinforced training by training a CLIP model based on ViT-B/16 image backbone and achieving +2. 9% average performance improvement on 38 evaluation benchmarks compared to the previous best.
1 code implementation • 24 Oct 2023 • Saurabh Garg, Mehrdad Farajtabar, Hadi Pouransari, Raviteja Vemulapalli, Sachin Mehta, Oncel Tuzel, Vaishaal Shankar, Fartash Faghri
We introduce the first set of web-scale Time-Continual (TiC) benchmarks for training vision-language models: TiC-DataComp, TiC-YFCC, and TiC-Redcaps.
no code implementations • 23 Oct 2023 • Haoxiang Wang, Pavan Kumar Anasosalu Vasu, Fartash Faghri, Raviteja Vemulapalli, Mehrdad Farajtabar, Sachin Mehta, Mohammad Rastegari, Oncel Tuzel, Hadi Pouransari
By applying our method to SAM and CLIP, we obtain SAM-CLIP: a unified model that combines the capabilities of SAM and CLIP into a single vision transformer.
no code implementations • 21 Oct 2023 • Mohammadreza Salehi, Mehrdad Farajtabar, Maxwell Horton, Fartash Faghri, Hadi Pouransari, Raviteja Vemulapalli, Oncel Tuzel, Ali Farhadi, Mohammad Rastegari, Sachin Mehta
While CLIP is scalable, promptable, and robust to distribution shifts on image classification tasks, it lacks object localization capabilities.
1 code implementation • 12 Sep 2023 • Ran Liu, Ellen L. Zippi, Hadi Pouransari, Chris Sandino, Jingping Nie, Hanlin Goh, Erdrin Azemi, Ali Moin
To achieve effective pretraining in the presence of potential distributional shifts, we propose a frequency-aware masked autoencoder ($\texttt{bio}$FAME) that learns to parameterize the representation of biosignals in the frequency space.
1 code implementation • ICCV 2023 • Fartash Faghri, Hadi Pouransari, Sachin Mehta, Mehrdad Farajtabar, Ali Farhadi, Mohammad Rastegari, Oncel Tuzel
Models pretrained on ImageNet+ and fine-tuned on CIFAR-100+, Flowers-102+, and Food-101+, reach up to 3. 4% improved accuracy.
1 code implementation • 8 Mar 2023 • Florian Jaeckle, Fartash Faghri, Ali Farhadi, Oncel Tuzel, Hadi Pouransari
The task of retrieving the most similar data from a gallery set to a given query data is performed through a similarity comparison on features.
no code implementations • 8 Oct 2022 • Elan Rosenfeld, Preetum Nakkiran, Hadi Pouransari, Oncel Tuzel, Fartash Faghri
Recent advances in learning aligned multimodal representations have been primarily driven by training large neural networks on massive, noisy paired-modality datasets.
1 code implementation • CVPR 2022 • Vivek Ramanujan, Pavan Kumar Anasosalu Vasu, Ali Farhadi, Oncel Tuzel, Hadi Pouransari
To avoid the cost of backfilling, BCT modifies training of the new model to make its representations compatible with those of the old model.
no code implementations • 30 Jun 2020 • Hadi Pouransari, Mojan Javaheripi, Vinay Sharma, Oncel Tuzel
We propose extracurricular learning, a novel knowledge distillation method, that bridges this gap by (1) modeling student and teacher output distributions; (2) sampling examples from an approximation to the underlying data distribution; and (3) matching student and teacher output distributions over this extended set including uncertain samples.
1 code implementation • 9 Jan 2020 • Hadi Pouransari, Zhucheng Tu, Oncel Tuzel
We conduct experiments on the ImageNet dataset and show a reduced accuracy gap when using the proposed least squares quantization algorithms.
no code implementations • 25 Sep 2019 • Hadi Pouransari, Oncel Tuzel
We conduct experiments on the ImageNet dataset and show a reduced accuracy gap when using the proposed optimal quantization algorithms.
no code implementations • 31 Oct 2018 • Minghuang Ma, Hadi Pouransari, Daniel Chao, Saurabh Adya, Santiago Akle Serrano, Yi Qin, Dan Gimnicher, Dominic Walsh
The interest and demand for training deep neural networks have been experiencing rapid growth, spanning a wide range of applications in both academia and industry.