no code implementations • 6 Dec 2023 • Ivona Najdenkoska, Animesh Sinha, Abhimanyu Dubey, Dhruv Mahajan, Vignesh Ramanathan, Filip Radenovic
We propose Context Diffusion, a diffusion-based framework that enables image generation models to learn from visual examples presented in context.
no code implementations • 17 Nov 2023 • Animesh Sinha, Bo Sun, Anmol Kalia, Arantxa Casanova, Elliot Blanchard, David Yan, Winnie Zhang, Tony Nelli, Jiahui Chen, Hardik Shah, Licheng Yu, Mitesh Kumar Singh, Ankit Ramchandani, Maziar Sanjabi, Sonal Gupta, Amy Bearman, Dhruv Mahajan
Evaluation results show our method improves visual quality by 14%, prompt alignment by 16. 2% and scene diversity by 15. 3%, compared to prompt engineering the base Emu model for stickers generation.
no code implementations • 27 Sep 2023 • Xiaoliang Dai, Ji Hou, Chih-Yao Ma, Sam Tsai, Jialiang Wang, Rui Wang, Peizhao Zhang, Simon Vandenhende, Xiaofang Wang, Abhimanyu Dubey, Matthew Yu, Abhishek Kadian, Filip Radenovic, Dhruv Mahajan, Kunpeng Li, Yue Zhao, Vladan Petrovic, Mitesh Kumar Singh, Simran Motwani, Yi Wen, Yiwen Song, Roshan Sumbaly, Vignesh Ramanathan, Zijian He, Peter Vajda, Devi Parikh
Training text-to-image models with web scale image-text pairs enables the generation of a wide range of visual concepts from text.
1 code implementation • CVPR 2023 • Filip Radenovic, Abhimanyu Dubey, Abhishek Kadian, Todor Mihaylov, Simon Vandenhende, Yash Patel, Yi Wen, Vignesh Ramanathan, Dhruv Mahajan
Vision-language models trained with contrastive learning on large-scale noisy data are becoming increasingly popular for zero-shot recognition problems.
1 code implementation • CVPR 2023 • Vignesh Ramanathan, Anmol Kalia, Vladan Petrovic, Yi Wen, Baixue Zheng, Baishan Guo, Rui Wang, Aaron Marquez, Rama Kovvuri, Abhishek Kadian, Amir Mousavi, Yiwen Song, Abhimanyu Dubey, Dhruv Mahajan
This motivates the need for large datasets which go beyond traditional object masks and provide richer annotations such as part masks and attributes.
1 code implementation • 27 May 2022 • Filip Radenovic, Abhimanyu Dubey, Dhruv Mahajan
However, these models are typically black-box deep neural networks, explained post-hoc via methods with known faithfulness limitations.
1 code implementation • 27 May 2022 • Abhimanyu Dubey, Filip Radenovic, Dhruv Mahajan
We demonstrate by human subject evaluations that SPAMs are demonstrably more interpretable in practice, and are hence an effortless replacement for DNNs for creating interpretable and high-performance systems suitable for large-scale machine learning.
1 code implementation • 24 Mar 2022 • Simon Vandenhende, Dhruv Mahajan, Filip Radenovic, Deepti Ghadiyaram
A visual counterfactual explanation replaces image regions in a query image with regions from a distractor image such that the system's decision on the transformed image changes to the distractor class.
2 code implementations • CVPR 2022 • Mannat Singh, Laura Gustafson, Aaron Adcock, Vinicius de Freitas Reis, Bugra Gedik, Raj Prateek Kosaraju, Dhruv Mahajan, Ross Girshick, Piotr Dollár, Laurens van der Maaten
Model pre-training is a cornerstone of modern visual recognition systems.
Ranked #1 on Out-of-Distribution Generalization on ImageNet-W (using extra training data)
Fine-Grained Image Classification Out-of-Distribution Generalization +3
1 code implementation • 9 Dec 2021 • Xavier Thomas, Dhruv Mahajan, Alex Pentland, Abhimanyu Dubey
In this paper, we propose a domain-adaptive approach to this problem, which operates in two steps: (a) we cluster training data within a carefully chosen feature space to create pseudo-domains, and (b) using these pseudo-domains we learn a domain-adaptive classifier that makes predictions using information about both the input and the pseudo-domain it belongs to.
Ranked #16 on Domain Generalization on PACS
no code implementations • 24 May 2021 • Filip Radenovic, Animesh Sinha, Albert Gordo, Tamara Berg, Dhruv Mahajan
We study the problem of learning how to predict attribute-object compositions from images, and its generalization to unseen compositions missing from the training data.
no code implementations • CVPR 2021 • Abhimanyu Dubey, Vignesh Ramanathan, Alex Pentland, Dhruv Mahajan
We show that the existing approaches either do not scale to this dataset or underperform compared to the simple baseline of training a model on the union of data from all training domains.
no code implementations • CVPR 2021 • Qing Liu, Vignesh Ramanathan, Dhruv Mahajan, Alan Yuille, Zhenheng Yang
However, existing approaches which rely only on image-level class labels predominantly suffer from errors due to (a) partial segmentation of objects and (b) missing object predictions.
no code implementations • ICCV 2021 • Vignesh Ramanathan, Rui Wang, Dhruv Mahajan
State-of-the-art object detection approaches typically rely on pre-trained classification models to achieve better performance and faster convergence.
no code implementations • 13 Aug 2020 • Rui Wang, Dhruv Mahajan, Vignesh Ramanathan
It is lucrative to train a good proposal model, that generalizes to unseen classes.
1 code implementation • CVPR 2020 • Krishna Kumar Singh, Dhruv Mahajan, Kristen Grauman, Yong Jae Lee, Matt Feiszli, Deepti Ghadiyaram
Our key idea is to decorrelate feature representations of a category from its co-occurring context.
1 code implementation • 21 Dec 2019 • Yin Cui, Zeqi Gu, Dhruv Mahajan, Laurens van der Maaten, Serge Belongie, Ser-Nam Lim
We also investigate the interplay between dataset granularity with a variety of factors and find that fine-grained datasets are more difficult to learn from, more difficult to transfer to, more difficult to perform few-shot learning with, and more vulnerable to adversarial attacks.
2 code implementations • CVPR 2020 • Zhenqiang Ying, Haoran Niu, Praful Gupta, Dhruv Mahajan, Deepti Ghadiyaram, Alan Bovik
Blind or no-reference (NR) perceptual picture quality prediction is a difficult, unsolved problem of great consequence to the social and streaming media industries that impacts billions of viewers daily.
Ranked #4 on Video Quality Assessment on MSU SR-QA Dataset
1 code implementation • CVPR 2020 • Xueting Yan, Ishan Misra, Abhinav Gupta, Deepti Ghadiyaram, Dhruv Mahajan
Pre-training convolutional neural networks with weakly-supervised and self-supervised strategies is becoming increasingly popular for several computer vision tasks.
Ranked #53 on Image Classification on iNaturalist 2018
1 code implementation • NeurIPS 2020 • Humam Alwassel, Dhruv Mahajan, Bruno Korbar, Lorenzo Torresani, Bernard Ghanem, Du Tran
To the best of our knowledge, XDC is the first self-supervised learning method that outperforms large-scale fully-supervised pretraining for action recognition on the same architecture.
2 code implementations • ICCV 2019 • Priya Goyal, Dhruv Mahajan, Abhinav Gupta, Ishan Misra
Self-supervised learning aims to learn representations from the data itself without explicit manual supervision.
3 code implementations • CVPR 2019 • Deepti Ghadiyaram, Matt Feiszli, Du Tran, Xueting Yan, Heng Wang, Dhruv Mahajan
Second, frame-based models perform quite well on action recognition; is pre-training for good image features sufficient or is pre-training for spatio-temporal features valuable for optimal transfer learning?
Ranked #2 on Egocentric Activity Recognition on EPIC-KITCHENS-55 (Actions Top-1 (S2) metric)
4 code implementations • 2 May 2019 • I. Zeki Yalniz, Hervé Jégou, Kan Chen, Manohar Paluri, Dhruv Mahajan
This paper presents a study of semi-supervised learning with large convolutional networks.
Ranked #6 on Image Classification on OmniBenchmark (using extra training data)
no code implementations • CVPR 2019 • Zhenheng Yang, Dhruv Mahajan, Deepti Ghadiyaram, Ram Nevatia, Vignesh Ramanathan
Weakly supervised object detection aims at reducing the amount of supervision required to train detection models.
Ranked #1 on Weakly Supervised Object Detection on Charades
no code implementations • CVPR 2019 • Abhimanyu Dubey, Laurens van der Maaten, Zeki Yalniz, Yixuan Li, Dhruv Mahajan
Empirical evaluations of this defense strategy on ImageNet suggest that it is very effective in attack settings in which the adversary does not have access to the image database.
no code implementations • CVPR 2018 • De-An Huang, Vignesh Ramanathan, Dhruv Mahajan, Lorenzo Torresani, Manohar Paluri, Li Fei-Fei, Juan Carlos Niebles
The ability to capture temporal information has been critical to the development of video understanding models.
4 code implementations • ECCV 2018 • Dhruv Mahajan, Ross Girshick, Vignesh Ramanathan, Kaiming He, Manohar Paluri, Yixuan Li, Ashwin Bharambe, Laurens van der Maaten
ImageNet classification is the de facto pretraining task for these models.
Ranked #222 on Image Classification on ImageNet (using extra training data)
no code implementations • 1 Feb 2018 • Chien-Chih Wang, Kent Loong Tan, Chun-Ting Chen, Yu-Hsiang Lin, S. Sathiya Keerthi, Dhruv Mahajan, S. Sundararajan, Chih-Jen Lin
First, to reduce the communication cost, we propose a diagonalization method such that an approximate Newton direction can be obtained without communication between machines.
no code implementations • 15 Nov 2017 • Dhruv Mahajan, Vivek Gupta, S. Sathiya Keerthi, Sellamanickam Sundararajan, Shravan Narayanamurthy, Rahul Kidambi
We also demonstrate their usefulness in making design choices such as the number of classifiers in the ensemble and the size of a subset of data used for training that is needed to achieve a certain value of generalization error.
no code implementations • ICML 2017 • Si Si, huan zhang, S. Sathiya Keerthi, Dhruv Mahajan, Inderjit S. Dhillon, Cho-Jui Hsieh
In this paper, we study the gradient boosted decision trees (GBDT) when the output space is high dimensional and sparse.
no code implementations • 22 Apr 2017 • Michał Dereziński, Dhruv Mahajan, S. Sathiya Keerthi, S. V. N. Vishwanathan, Markus Weimer
We propose Batch-Expansion Training (BET), a framework for running a batch optimizer on a gradually expanding dataset.
no code implementations • 30 Mar 2016 • Ignacio Cano, Markus Weimer, Dhruv Mahajan, Carlo Curino, Giovanni Matteo Fumarola
Current solutions to learning from geo-distributed data sources revolve around the idea of first centralizing the data in one data center, and then training locally.
no code implementations • 18 May 2014 • Dhruv Mahajan, S. Sathiya Keerthi, S. Sundararajan
This paper concerns the distributed training of nonlinear kernel machines on Map-Reduce.
no code implementations • 18 May 2014 • Dhruv Mahajan, S. Sathiya Keerthi, S. Sundararajan
In this paper we design a distributed algorithm for $l_1$ regularization that is much better suited for such systems than existing algorithms.
no code implementations • 4 Nov 2013 • Dhruv Mahajan, S. Sathiya Keerthi, S. Sundararajan, Leon Bottou
The method has strong convergence properties.
no code implementations • 31 Oct 2013 • Dhruv Mahajan, Nikunj Agrawal, S. Sathiya Keerthi, S. Sundararajan, Leon Bottou
In this paper we give a novel approach to the distributed training of linear classifiers (involving smooth losses and L2 regularization) that is designed to reduce the total communication costs.