Dhruv Mahajan

papers

1,815

total citations

papers (16)

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

NEURIPS 2020arXiv

462

citations

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

CVPR 2020arXiv

394

citations

Weakly Supervised Instance Segmentation for Videos With Temporal Mask Consistency

CVPR 2021arXiv

citations

Context Diffusion: In-Context Aware Image Generation

ECCV 2024arXiv

citations

Law of the Weakest Link: Cross Capabilities of Large Language Models

ICLR 2025arXiv

citations

DLWL: Improving Detection for Lowshot Classes With Weakly Labelled Data

CVPR 2020

citations

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

ICCV 2021

citations

Dhruv Mahajan

papers (16)

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

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

PACO: Parts and Attributes of Common Objects

Revisiting Weakly Supervised Pre-Training of Visual Perception Models

ClusterFit: Improving Generalization of Visual Representations

Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias

Adaptive Methods for Real-World Domain Generalization

Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training

Neural Basis Models for Interpretability

Scalable Interpretability via Polynomials

Making Heads or Tails: Towards Semantically Consistent Visual Counterfactuals

Weakly Supervised Instance Segmentation for Videos With Temporal Mask Consistency

Context Diffusion: In-Context Aware Image Generation

Law of the Weakest Link: Cross Capabilities of Large Language Models

DLWL: Improving Detection for Lowshot Classes With Weakly Labelled Data

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

papers (16)

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

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

PACO: Parts and Attributes of Common Objects

Revisiting Weakly Supervised Pre-Training of Visual Perception Models

ClusterFit: Improving Generalization of Visual Representations

Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias

Adaptive Methods for Real-World Domain Generalization

Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training

Neural Basis Models for Interpretability

Scalable Interpretability via Polynomials

Making Heads or Tails: Towards Semantically Consistent Visual Counterfactuals

Weakly Supervised Instance Segmentation for Videos With Temporal Mask Consistency

Context Diffusion: In-Context Aware Image Generation

Law of the Weakest Link: Cross Capabilities of Large Language Models

DLWL: Improving Detection for Lowshot Classes With Weakly Labelled Data

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