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
174 publications
Ming-Hsuan Yang
115 publications
Jan Kautz
101 publications
Andrea Vedaldi
96 publications
Stefano Soatto
78 publications
Zhe Lin
70 publications
Juho Kannala
58 publications
Hang Su
47 publications
Manmohan Chandraker
45 publications
Tommi Jaakkola
43 publications
Pietro Perona
39 publications

Revisiting Contrastive Learning for Few-Shot Classification

Instance discrimination based contrastive learning has emerged as a lead...
01/26/2021 ∙ by Orchid Majumder, et al. ∙ 16 ∙ share

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

We present a plug-in replacement for batch normalization (BN) called exp...
01/21/2021 ∙ by Zhaowei Cai, et al. ∙ 9 ∙ share

read it
StarcNet: Machine Learning for Star Cluster Identification

We present a machine learning (ML) pipeline to identify star clusters in...
12/16/2020 ∙ by Gustavo Perez, et al. ∙ 13 ∙ share

read it
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...
10/06/2020 ∙ by Zitian Chen, et al. ∙ 18 ∙ share

read it
PhraseCut: Language-based Image Segmentation in the Wild

We consider the problem of segmenting image regions given a natural lang...
08/03/2020 ∙ by Chenyun Wu, et al. ∙ 5 ∙ share

read it
Describing Textures using Natural Language

Textures in natural images can be characterized by color, shape, periodi...
08/03/2020 ∙ by Chenyun Wu, et al. ∙ 12 ∙ share

read it
Unsupervised Discovery of Object Landmarks via Contrastive Learning

Given a collection of images, humans are able to discover landmarks of t...
06/26/2020 ∙ by Zezhou Cheng, et al. ∙ 5 ∙ share

read it
Exploring and Predicting Transferability across NLP Tasks

Recent advances in NLP demonstrate the effectiveness of training large-s...
05/02/2020 ∙ by Tu Vu, et al. ∙ 0 ∙ share

read it
Detecting and Tracking Communal Bird Roosts in Weather Radar Data

The US weather radar archive holds detailed information about biological...
04/24/2020 ∙ by Zezhou Cheng, et al. ∙ 14 ∙ share

read it
Deep Manifold Prior

We present a prior for manifold structured data, such as surfaces of 3D ...
04/08/2020 ∙ by Matheus Gadelha, et al. ∙ 15 ∙ share

read it
Learning Generative Models of Shape Handles

We present a generative model to synthesize 3D shapes as sets of handles...
04/06/2020 ∙ by Matheus Gadelha, et al. ∙ 7 ∙ share

read it
Label-Efficient Learning on Point Clouds using Approximate Convex Decompositions

The problems of shape classification and part segmentation from 3D point...
03/30/2020 ∙ by Matheus Gadelha, et al. ∙ 2 ∙ share

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

We propose a novel, end-to-end trainable, deep network called ParSeNet t...
03/26/2020 ∙ by Gopal Sharma, et al. ∙ 0 ∙ share

read it
Neural Shape Parsers for Constructive Solid Geometry

Constructive Solid Geometry (CSG) is a geometric modeling technique that...
12/22/2019 ∙ by Gopal Sharma, et al. ∙ 26 ∙ share

read it
The Spectral Bias of the Deep Image Prior

The "deep image prior" proposed by Ulyanov et al. is an intriguing prope...
12/18/2019 ∙ by Prithvijit Chakrabarty, et al. ∙ 21 ∙ share

read it
When Does Self-supervision Improve Few-shot Learning?

We present a technique to improve the generalization of deep representat...
10/08/2019 ∙ by Jong-Chyi Su, et al. ∙ 19 ∙ share

read it
Learning Point Embeddings from Shape Repositories for Few-Shot Segmentation

User generated 3D shapes in online repositories contain rich information...
10/03/2019 ∙ by Gopal Sharma, et al. ∙ 7 ∙ share

read it
Visualizing and Describing Fine-grained Categories as Textures

We analyze how categories from recent FGVC challenges can be described b...
07/02/2019 ∙ by Tsung-Yu Lin, et al. ∙ 0 ∙ share

read it
Boosting Supervision with Self-Supervision for Few-shot Learning

We present a technique to improve the transferability of deep representa...
06/17/2019 ∙ by Jong-Chyi Su, et al. ∙ 6 ∙ share

read it
Inferring 3D Shapes from Image Collections using Adversarial Networks

We investigate the problem of learning a probabilistic distribution over...
06/11/2019 ∙ by Matheus Gadelha, et al. ∙ 7 ∙ share

read it
Active Adversarial Domain Adaptation

We propose an active learning approach for transferring representations ...
04/16/2019 ∙ by Jong-Chyi Su, et al. ∙ 16 ∙ share

read it
A Bayesian Perspective on the Deep Image Prior

The deep image prior was recently introduced as a prior for natural imag...
04/16/2019 ∙ by Zezhou Cheng, et al. ∙ 22 ∙ share

read it
Meta-Learning with Differentiable Convex Optimization

Many meta-learning approaches for few-shot learning rely on simple base ...
04/07/2019 ∙ by Kwonjoon Lee, et al. ∙ 4 ∙ share

read it
Task2Vec: Task Embedding for Meta-Learning

We introduce a method to provide vectorial representations of visual cla...
02/10/2019 ∙ by Alessandro Achille, et al. ∙ 10 ∙ share

read it
A Deeper Look at 3D Shape Classifiers

We investigate the role of representations and architectures for classif...
09/07/2018 ∙ by Jong-Chyi Su, et al. ∙ 0 ∙ share

read it
Second-order Democratic Aggregation

Aggregated second-order features extracted from deep convolutional netwo...
08/22/2018 ∙ by Tsung-Yu Lin, et al. ∙ 0 ∙ share

read it
Multiresolution Tree Networks for 3D Point Cloud Processing

We present multiresolution tree-structured networks to process point clo...
07/10/2018 ∙ by Matheus Gadelha, et al. ∙ 2 ∙ share

read it
VisemeNet: Audio-Driven Animator-Centric Speech Animation

We present a novel deep-learning based approach to producing animator-ce...
05/24/2018 ∙ by Yang Zhou, et al. ∙ 0 ∙ share

read it
SPLATNet: Sparse Lattice Networks for Point Cloud Processing

We present a network architecture for processing point clouds that direc...
02/22/2018 ∙ by Hang Su, et al. ∙ 0 ∙ share

read it
CSGNet: Neural Shape Parser for Constructive Solid Geometry

We present a neural architecture that takes as input a 2D or 3D shape an...
12/22/2017 ∙ by Gopal Sharma, et al. ∙ 0 ∙ share

read it
Improved Bilinear Pooling with CNNs

Bilinear pooling of Convolutional Neural Network (CNN) features [22, 23]...
07/21/2017 ∙ by Tsung-Yu Lin, et al. ∙ 0 ∙ share

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

We propose a method for reconstructing 3D shapes from 2D sketches in the...
07/20/2017 ∙ by Zhaoliang Lun, et al. ∙ 0 ∙ share

read it
Shape Generation using Spatially Partitioned Point Clouds

We propose a method to generate 3D shapes using point clouds. Given a po...
07/19/2017 ∙ by Matheus Gadelha, et al. ∙ 0 ∙ share

read it
3D Shape Induction from 2D Views of Multiple Objects

In this paper we investigate the problem of inducing a distribution over...
12/18/2016 ∙ by Matheus Gadelha, et al. ∙ 0 ∙ share

read it
3D Shape Segmentation with Projective Convolutional Networks

This paper introduces a deep architecture for segmenting 3D objects into...
12/08/2016 ∙ by Evangelos Kalogerakis, et al. ∙ 0 ∙ share

read it
Adapting Models to Signal Degradation using Distillation

Model compression and knowledge distillation have been successfully appl...
04/01/2016 ∙ by Jong-Chyi Su, et al. ∙ 0 ∙ share

read it
High Dimensional Inference with Random Maximum A-Posteriori Perturbations

This paper presents a new approach, called perturb-max, for high-dimensi...
02/10/2016 ∙ by Tamir Hazan, et al. ∙ 0 ∙ share

read it
Deep filter banks for texture recognition, description, and segmentation

Visual textures have played a key role in image understanding because th...
07/09/2015 ∙ by Mircea Cimpoi, et al. ∙ 0 ∙ share

read it
One-to-many face recognition with bilinear CNNs

The recent explosive growth in convolutional neural network (CNN) resear...
06/03/2015 ∙ by Aruni RoyChowdhury, et al. ∙ 0 ∙ share

read it
Multi-view Convolutional Neural Networks for 3D Shape Recognition

A longstanding question in computer vision concerns the representation o...
05/05/2015 ∙ by Hang Su, et al. ∙ 0 ∙ share

read it
Bilinear CNNs for Fine-grained Visual Recognition

We present a simple and effective architecture for fine-grained visual r...
04/29/2015 ∙ by Tsung-Yu Lin, et al. ∙ 0 ∙ share

read it
Jointly Learning Multiple Measures of Similarities from Triplet Comparisons

Similarity between objects is multi-faceted and it can be easier for hum...
03/05/2015 ∙ by Liwen Zhang, et al. ∙ 0 ∙ share

read it
Deep convolutional filter banks for texture recognition and segmentation

Research in texture recognition often concentrates on the problem of mat...
11/25/2014 ∙ by Mircea Cimpoi, et al. ∙ 0 ∙ share

read it
Describing Textures in the Wild

Patterns and textures are defining characteristics of many natural objec...
11/14/2013 ∙ by Mircea Cimpoi, et al. ∙ 0 ∙ share

read it
Fine-Grained Visual Classification of Aircraft

This paper introduces FGVC-Aircraft, a new dataset containing 10,000 ima...
06/21/2013 ∙ by Subhransu Maji, et al. ∙ 0 ∙ share

read it
Linearized Additive Classifiers

We revisit the additive model learning literature and adapt a penalized ...
10/05/2011 ∙ by Subhransu Maji, et al. ∙ 0 ∙ share

read it