Search Results for author: Dhruv Mahajan

Found 36 papers, 16 papers with code

Large-scale weakly-supervised pre-training for video action recognition

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)

Action Classification Action Recognition +3

ClusterFit: Improving Generalization of Visual Representations

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.

Action Classification Clustering +2

Self-Supervised Learning by Cross-Modal Audio-Video Clustering

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.

Audio Classification Clustering +5

From Patches to Pictures (PaQ-2-PiQ): Mapping the Perceptual Space of Picture Quality

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.

Blind Image Quality Assessment Video Quality Assessment

Neural Basis Models for Interpretability

1 code implementation27 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.

Additive models Interpretable Machine Learning

Scalable Interpretability via Polynomials

1 code implementation27 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.

Additive models BIG-bench Machine Learning +1

Making Heads or Tails: Towards Semantically Consistent Visual Counterfactuals

1 code implementation24 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.

counterfactual Counterfactual Explanation +1

Adaptive Methods for Aggregated Domain Generalization

1 code implementation9 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.

Domain Generalization

Measuring Dataset Granularity

1 code implementation21 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.

Clustering Few-Shot Learning

Batch-Expansion Training: An Efficient Optimization Framework

no code implementations22 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.

Distributed Newton Methods for Deep Neural Networks

no code implementations1 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.

Efficient Estimation of Generalization Error and Bias-Variance Components of Ensembles

no code implementations15 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.

Towards Geo-Distributed Machine Learning

no code implementations30 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.

BIG-bench Machine Learning

A distributed block coordinate descent method for training $l_1$ regularized linear classifiers

no code implementations18 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.

An efficient distributed learning algorithm based on effective local functional approximations

no code implementations31 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.

L2 Regularization

A Distributed Algorithm for Training Nonlinear Kernel Machines

no code implementations18 May 2014 Dhruv Mahajan, S. Sathiya Keerthi, S. Sundararajan

This paper concerns the distributed training of nonlinear kernel machines on Map-Reduce.

Defense Against Adversarial Images using Web-Scale Nearest-Neighbor Search

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.

What leads to generalization of object proposals?

no code implementations13 Aug 2020 Rui Wang, Dhruv Mahajan, Vignesh Ramanathan

It is lucrative to train a good proposal model, that generalizes to unseen classes.

Object Object Proposal Generation

Weakly Supervised Instance Segmentation for Videos with Temporal Mask Consistency

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.

Instance Segmentation Relation Network +3

Adaptive Methods for Real-World Domain Generalization

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.

Domain Generalization

Large-Scale Attribute-Object Compositions

no code implementations24 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.

Attribute Object

PreDet: Large-Scale Weakly Supervised Pre-Training for Detection

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.

Classification Contrastive Learning +3

Text-to-Sticker: Style Tailoring Latent Diffusion Models for Human Expression

no code implementations17 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.

Image Generation Prompt Engineering

Context Diffusion: In-Context Aware Image Generation

no code implementations6 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.

Image Generation In-Context Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.