Subhransu Maji

is this you? claim profile

∙

0 followers

∙

University of Massachusetts Amherst

∙

Amazon

∙

berkeley college

∙

Toyota Technological Institute at Chicago

Assistant Professor of Computer Science at University of Massachusetts Amherst since 2014, Research Assistant Professor at Toyota Technological Institute at Chicago (TTIC) from 2012-2014, Visiting Researcher at University of Oxford 2013, Visiting Researcher at Johns Hopkins University 2012, PHD Student at UC Berkeley from 2006-2011, Visiting Researcher at Microsoft Research India 2010, Intern at Google 2008, Intern at INRIA 2005.

Featured Co-authors

Rui Wang
176 publications
Andrea Vedaldi
121 publications
Jan Kautz
120 publications
Ming-Hsuan Yang
115 publications
Stefano Soatto
108 publications
Zhe Lin
87 publications
Hang Su
70 publications
Cees G. M. Snoek
67 publications
Juho Kannala
66 publications
Manmohan Chandraker
56 publications
Esa Rahtu
55 publications

∙ 04/11/2022

Improving Few-Shot Part Segmentation using Coarse Supervision

A significant bottleneck in training deep networks for part segmentation...

Oindrila Saha, et al. ∙

∙ 03/22/2022

Leveraging Textures in Zero-shot Understanding of Fine-Grained Domains

Textures can be used to describe the appearance of objects in a wide ran...

Chenyun Wu, et al. ∙

∙ 12/01/2021

GANORCON: Are Generative Models Useful for Few-shot Segmentation?

Advances in generative modeling based on GANs has motivated the communit...

Oindrila Saha, et al. ∙

∙ 11/23/2021

Semi-Supervised Learning with Taxonomic Labels

We propose techniques to incorporate coarse taxonomic labels to train im...

Jong-Chyi Su, et al. ∙

∙ 08/03/2021

Domain Adaptor Networks for Hyperspectral Image Recognition

We consider the problem of adapting a network trained on three-channel c...

Gustavo Perez, et al. ∙

∙ 07/02/2021

On Measuring and Controlling the Spectral Bias of the Deep Image Prior

The deep image prior has demonstrated the remarkable ability that untrai...

Zenglin Shi, et al. ∙

∙ 06/02/2021

The Semi-Supervised iNaturalist Challenge at the FGVC8 Workshop

Semi-iNat is a challenging dataset for semi-supervised classification wi...

Jong-Chyi Su, et al. ∙

∙ 04/01/2021

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

We evaluate the effectiveness of semi-supervised learning (SSL) on a rea...

Jong-Chyi Su, et al. ∙

∙ 03/11/2021

The Semi-Supervised iNaturalist-Aves Challenge at FGVC7 Workshop

This document describes the details and the motivation behind a new data...

Jong-Chyi Su, et al. ∙

∙ 01/26/2021

Revisiting Contrastive Learning for Few-Shot Classification

Instance discrimination based contrastive learning has emerged as a lead...

Orchid Majumder, et al. ∙

∙ 01/21/2021

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

We present a plug-in replacement for batch normalization (BN) called exp...

Zhaowei Cai, et al. ∙

∙ 12/16/2020

StarcNet: Machine Learning for Star Cluster Identification

We present a machine learning (ML) pipeline to identify star clusters in...

Gustavo Perez, et al. ∙

∙ 10/06/2020

Shot in the Dark: Few-Shot Learning with No Base-Class Labels

Few-shot learning aims to learn classifiers for new objects from a small...

Zitian Chen, et al. ∙

∙ 08/03/2020

PhraseCut: Language-based Image Segmentation in the Wild

We consider the problem of segmenting image regions given a natural lang...

Chenyun Wu, et al. ∙

∙ 08/03/2020

Describing Textures using Natural Language

Textures in natural images can be characterized by color, shape, periodi...

Chenyun Wu, et al. ∙

∙ 06/26/2020

Unsupervised Discovery of Object Landmarks via Contrastive Learning

Given a collection of images, humans are able to discover landmarks of t...

Zezhou Cheng, et al. ∙

∙ 05/02/2020

Exploring and Predicting Transferability across NLP Tasks

Recent advances in NLP demonstrate the effectiveness of training large-s...

Tu Vu, et al. ∙

∙ 04/24/2020

Detecting and Tracking Communal Bird Roosts in Weather Radar Data

The US weather radar archive holds detailed information about biological...

Zezhou Cheng, et al. ∙

∙ 04/08/2020

Deep Manifold Prior

We present a prior for manifold structured data, such as surfaces of 3D ...

Matheus Gadelha, et al. ∙

∙ 04/06/2020

Learning Generative Models of Shape Handles

We present a generative model to synthesize 3D shapes as sets of handles...

Matheus Gadelha, et al. ∙

∙ 03/30/2020

Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions

The problems of shape classification and part segmentation from 3D point...

Matheus Gadelha, et al. ∙

∙ 03/26/2020

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

We propose a novel, end-to-end trainable, deep network called ParSeNet t...

Gopal Sharma, et al. ∙

∙ 12/22/2019

Neural Shape Parsers for Constructive Solid Geometry

Constructive Solid Geometry (CSG) is a geometric modeling technique that...

Gopal Sharma, et al. ∙

∙ 12/18/2019

The Spectral Bias of the Deep Image Prior

The "deep image prior" proposed by Ulyanov et al. is an intriguing prope...

Prithvijit Chakrabarty, et al. ∙

∙ 10/08/2019

When Does Self-supervision Improve Few-shot Learning?

We present a technique to improve the generalization of deep representat...

Jong-Chyi Su, et al. ∙

∙ 10/03/2019

Learning Point Embeddings from Shape Repositories for Few-Shot Segmentation

User generated 3D shapes in online repositories contain rich information...

Gopal Sharma, et al. ∙

∙ 07/02/2019

Visualizing and Describing Fine-grained Categories as Textures

We analyze how categories from recent FGVC challenges can be described b...

Tsung-Yu Lin, et al. ∙

∙ 06/17/2019

Boosting Supervision with Self-Supervision for Few-shot Learning

We present a technique to improve the transferability of deep representa...

Jong-Chyi Su, et al. ∙

∙ 06/11/2019

Inferring 3D Shapes from Image Collections using Adversarial Networks

We investigate the problem of learning a probabilistic distribution over...

Matheus Gadelha, et al. ∙

∙ 04/16/2019

Active Adversarial Domain Adaptation

We propose an active learning approach for transferring representations ...

Jong-Chyi Su, et al. ∙

∙ 04/16/2019

A Bayesian Perspective on the Deep Image Prior

The deep image prior was recently introduced as a prior for natural imag...

Zezhou Cheng, et al. ∙

∙ 04/07/2019

Meta-Learning with Differentiable Convex Optimization

Many meta-learning approaches for few-shot learning rely on simple base ...

Kwonjoon Lee, et al. ∙

∙ 02/10/2019

Task2Vec: Task Embedding for Meta-Learning

We introduce a method to provide vectorial representations of visual cla...

Alessandro Achille, et al. ∙

∙ 09/07/2018

A Deeper Look at 3D Shape Classifiers

We investigate the role of representations and architectures for classif...

Jong-Chyi Su, et al. ∙

∙ 08/22/2018

Second-order Democratic Aggregation

Aggregated second-order features extracted from deep convolutional netwo...

Tsung-Yu Lin, et al. ∙

∙ 07/10/2018

Multiresolution Tree Networks for 3D Point Cloud Processing

We present multiresolution tree-structured networks to process point clo...

Matheus Gadelha, et al. ∙

∙ 05/24/2018

VisemeNet: Audio-Driven Animator-Centric Speech Animation

We present a novel deep-learning based approach to producing animator-ce...

Yang Zhou, et al. ∙

∙ 02/22/2018

SPLATNet: Sparse Lattice Networks for Point Cloud Processing

We present a network architecture for processing point clouds that direc...

Hang Su, et al. ∙

∙ 12/22/2017

CSGNet: Neural Shape Parser for Constructive Solid Geometry

We present a neural architecture that takes as input a 2D or 3D shape an...

Gopal Sharma, et al. ∙

∙ 07/21/2017

Improved Bilinear Pooling with CNNs

Bilinear pooling of Convolutional Neural Network (CNN) features [22, 23]...

Tsung-Yu Lin, et al. ∙

∙ 07/20/2017

3D Shape Reconstruction from Sketches via Multi-view Convolutional Networks

We propose a method for reconstructing 3D shapes from 2D sketches in the...

Zhaoliang Lun, et al. ∙

∙ 07/19/2017

Shape Generation using Spatially Partitioned Point Clouds

We propose a method to generate 3D shapes using point clouds. Given a po...

Matheus Gadelha, et al. ∙

∙ 12/18/2016

3D Shape Induction from 2D Views of Multiple Objects

In this paper we investigate the problem of inducing a distribution over...

Matheus Gadelha, et al. ∙

∙ 12/08/2016

3D Shape Segmentation with Projective Convolutional Networks

This paper introduces a deep architecture for segmenting 3D objects into...

Evangelos Kalogerakis, et al. ∙

∙ 04/01/2016

Adapting Models to Signal Degradation using Distillation

Model compression and knowledge distillation have been successfully appl...

Jong-Chyi Su, et al. ∙

∙ 02/10/2016

High Dimensional Inference with Random Maximum A-Posteriori Perturbations

This paper presents a new approach, called perturb-max, for high-dimensi...

Tamir Hazan, et al. ∙

∙ 07/09/2015

Deep filter banks for texture recognition, description, and segmentation

Visual textures have played a key role in image understanding because th...

Mircea Cimpoi, et al. ∙

∙ 06/03/2015

One-to-many face recognition with bilinear CNNs

The recent explosive growth in convolutional neural network (CNN) resear...

Aruni RoyChowdhury, et al. ∙

∙ 05/05/2015

Multi-view Convolutional Neural Networks for 3D Shape Recognition

A longstanding question in computer vision concerns the representation o...

Hang Su, et al. ∙

∙ 04/29/2015

Bilinear CNNs for Fine-grained Visual Recognition

We present a simple and effective architecture for fine-grained visual r...

Tsung-Yu Lin, et al. ∙