Subhransu Maji

32

Papers

258

Total Citations

Papers (32)

When Does Self-supervision Improve Few-shot Learning?

Improved Zero-Shot Classification by Adapting VLMs with Text Descriptions

Human-in-the-Loop Visual Re-ID for Population Size Estimation

Consensus-Driven Active Model Selection

Generate, Transduct, Adapt: Iterative Transduction with VLMs

3D Shape Segmentation With Projective Convolutional Networks

SPLATNet: Sparse Lattice Networks for Point Cloud Processing

CSGNet: Neural Shape Parser for Constructive Solid Geometry

A Bayesian Perspective on the Deep Image Prior

Meta-Learning With Differentiable Convex Optimization

Learning Generative Models of Shape Handles

PhraseCut: Language-Based Image Segmentation in the Wild

Exponential Moving Average Normalization for Self-Supervised and Semi-Supervised Learning

A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classification

GanOrCon: Are Generative Models Useful for Few-Shot Segmentation?

Multi-View Convolutional Neural Networks for 3D Shape Recognition

Bilinear CNN Models for Fine-Grained Visual Recognition

Reasoning About Fine-Grained Attribute Phrases Using Reference Games

Shape Reconstruction Using Differentiable Projections and Deep Priors

Task2Vec: Task Embedding for Meta-Learning

On Equivariant and Invariant Learning of Object Landmark Representations

LU-NeRF: Scene and Pose Estimation by Synchronizing Local Unposed NeRFs

Describing Textures using Natural Language

ParSeNet: A Parametric Surface Fitting Network for 3D Point Clouds

Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions

MvDeCor: Multi-View Dense Correspondence Learning for Fine-Grained 3D Segmentation

Cross-Modal 3D Shape Generation and Manipulation

Improving Few-Shot Part Segmentation Using Coarse Supervision

WildSAT: Learning Satellite Image Representations from Wildlife Observations

Task2Box: Box Embeddings for Modeling Asymmetric Task Relationships

Deep Filter Banks for Texture Recognition and Segmentation

Visualizing and Understanding Deep Texture Representations