1.2k citations · 2k across the 56 of their papers we have counts for
65 papers
PARTICLE: Part Discovery and Contrastive Learning for Fine-grained Recognition
Oindrila Saha, Subhransu Maji
We develop techniques for refining representations for fine-grained classification and segmentation tasks in a self-supervised manner. We find that fine-tuning methods based on ins…
COSE: A Consistency-Sensitivity Metric for Saliency on Image Classification
Rangel Daroya, Aaron Sun, Subhransu Maji
We present a set of metrics that utilize vision priors to effectively assess the performance of saliency methods on image classification tasks. To understand behavior in deep learn…
LU-NeRF: Scene and Pose Estimation by Synchronizing Local Unposed NeRFs
Zezhou Cheng, Carlos Esteves, Varun Jampani +3
A critical obstacle preventing NeRF models from being deployed broadly in the wild is their reliance on accurate camera poses. Consequently, there is growing interest in extending…
DISCount: Counting in Large Image Collections with Detector-Based Importance Sampling
Gustavo Perez, Subhransu Maji, Daniel Sheldon
Many modern applications use computer vision to detect and count objects in massive image collections. However, when the detection task is very difficult or in the presence of doma…
Accidental Turntables: Learning 3D Pose by Watching Objects Turn
Zezhou Cheng, Matheus Gadelha, Subhransu Maji
We propose a technique for learning single-view 3D object pose estimation models by utilizing a new source of data -- in-the-wild videos where objects turn. Such videos are prevale…
MvDeCor: Multi-view Dense Correspondence Learning for Fine-grained 3D Segmentation
Gopal Sharma, Kangxue Yin, Subhransu Maji +3
We propose to utilize self-supervised techniques in the 2D domain for fine-grained 3D shape segmentation tasks. This is inspired by the observation that view-based surface represen…
Cross-Modal 3D Shape Generation and Manipulation
Zezhou Cheng, Menglei Chai, Jian Ren +5
Creating and editing the shape and color of 3D objects require tremendous human effort and expertise. Compared to direct manipulation in 3D interfaces, 2D interactions such as sket…
Improving Few-Shot Part Segmentation using Coarse Supervision
Oindrila Saha, Zezhou Cheng, Subhransu Maji
A significant bottleneck in training deep networks for part segmentation is the cost of obtaining detailed annotations. We propose a framework to exploit coarse labels such as figu…
How well does CLIP understand texture?
Chenyun Wu, Subhransu Maji
We investigate how well CLIP understands texture in natural images described by natural language. To this end, we analyze CLIP's ability to: (1) perform zero-shot learning on vario…
PriFit: Learning to Fit Primitives Improves Few Shot Point Cloud Segmentation
Gopal Sharma, Bidya Dash, Aruni RoyChowdhury +7
We present PriFit, a semi-supervised approach for label-efficient learning of 3D point cloud segmentation networks. PriFit combines geometric primitive fitting with point-based rep…
GANORCON: Are Generative Models Useful for Few-shot Segmentation?
Oindrila Saha, Zezhou Cheng, Subhransu Maji
Advances in generative modeling based on GANs has motivated the community to find their use beyond image generation and editing tasks. In particular, several recent works have show…
Semi-Supervised Learning with Taxonomic Labels
Jong-Chyi Su, Subhransu Maji
We propose techniques to incorporate coarse taxonomic labels to train image classifiers in fine-grained domains. Such labels can often be obtained with a smaller effort for fine-gr…
Domain Adaptor Networks for Hyperspectral Image Recognition
Gustavo Perez, Subhransu Maji
We consider the problem of adapting a network trained on three-channel color images to a hyperspectral domain with a large number of channels. To this end, we propose domain adapto…
On Measuring and Controlling the Spectral Bias of the Deep Image Prior
Zenglin Shi, Pascal Mettes, Subhransu Maji +1
The deep image prior showed that a randomly initialized network with a suitable architecture can be trained to solve inverse imaging problems by simply optimizing it's parameters t…
The Semi-Supervised iNaturalist Challenge at the FGVC8 Workshop
Jong-Chyi Su, Subhransu Maji
Semi-iNat is a challenging dataset for semi-supervised classification with a long-tailed distribution of classes, fine-grained categories, and domain shifts between labeled and unl…
A Realistic Evaluation of Semi-Supervised Learning for Fine-Grained Classification
Jong-Chyi Su, Zezhou Cheng, Subhransu Maji
We evaluate the effectiveness of semi-supervised learning (SSL) on a realistic benchmark where data exhibits considerable class imbalance and contains images from novel classes. Ou…
The Semi-Supervised iNaturalist-Aves Challenge at FGVC7 Workshop
Jong-Chyi Su, Subhransu Maji
This document describes the details and the motivation behind a new dataset we collected for the semi-supervised recognition challenge~\cite{semi-aves} at the FGVC7 workshop at CVP…
Supervised Momentum Contrastive Learning for Few-Shot Classification
Orchid Majumder, Avinash Ravichandran, Subhransu Maji +3
Few-shot learning aims to transfer information from one task to enable generalization on novel tasks given a few examples. This information is present both in the domain and the cl…
Exponential Moving Average Normalization for Self-supervised and Semi-supervised Learning
Zhaowei Cai, Avinash Ravichandran, Subhransu Maji +3
We present a plug-in replacement for batch normalization (BN) called exponential moving average normalization (EMAN), which improves the performance of existing student-teacher bas…
StarcNet: Machine Learning for Star Cluster Identification
Gustavo Perez, Matteo Messa, Daniela Calzetti +4
We present a machine learning (ML) pipeline to identify star clusters in the multi{color images of nearby galaxies, from observations obtained with the Hubble Space Telescope as pa…
Shot in the Dark: Few-Shot Learning with No Base-Class Labels
Zitian Chen, Subhransu Maji, Erik Learned-Miller
Few-shot learning aims to build classifiers for new classes from a small number of labeled examples and is commonly facilitated by access to examples from a distinct set of 'base c…
PhraseCut: Language-based Image Segmentation in the Wild
Chenyun Wu, Zhe Lin, Scott Cohen +2
We consider the problem of segmenting image regions given a natural language phrase, and study it on a novel dataset of 77,262 images and 345,486 phrase-region pairs. Our dataset i…
Describing Textures using Natural Language
Chenyun Wu, Mikayla Timm, Subhransu Maji
Textures in natural images can be characterized by color, shape, periodicity of elements within them, and other attributes that can be described using natural language. In this pap…
On Equivariant and Invariant Learning of Object Landmark Representations
Zezhou Cheng, Jong-Chyi Su, Subhransu Maji
Given a collection of images, humans are able to discover landmarks by modeling the shared geometric structure across instances. This idea of geometric equivariance has been widely…