Search Results for author: Chandrajit Bajaj

Found 18 papers, 7 papers with code

A distribution-dependent Mumford-Shah model for unsupervised hyperspectral image segmentation

no code implementations28 Mar 2022 Jan-Christopher Cohrs, Chandrajit Bajaj, Benjamin Berkels

We equipped the MS functional with a novel robust distribution-dependent indicator function designed to handle the characteristic challenges of hyperspectral data.

Denoising Dimensionality Reduction +3

E-CIR: Event-Enhanced Continuous Intensity Recovery

1 code implementation3 Mar 2022 Chen Song, QiXing Huang, Chandrajit Bajaj

A camera begins to sense light the moment we press the shutter button.

Deblurring

Learning Optimal Control with Stochastic Models of Hamiltonian Dynamics

no code implementations15 Nov 2021 Chandrajit Bajaj, Minh Nguyen

Optimal control problems can be solved by first applying the Pontryagin maximum principle, followed by computing a solution of the corresponding unconstrained Hamiltonian dynamical system.

Recursive Self-Improvement for Camera Image and Signal Processing Pipeline

no code implementations15 Nov 2021 Chandrajit Bajaj, Yi Wang, Yunhao Yang, Yuhan Zheng

Current camera image and signal processing pipelines (ISPs), including deep trained versions, tend to apply a single filter that is uniformly applied to the entire image.

Data Augmentation Image Enhancement +1

Robust Learning of Physics Informed Neural Networks

1 code implementation26 Oct 2021 Chandrajit Bajaj, Luke McLennan, Timothy Andeen, Avik Roy

Physics-informed Neural Networks (PINNs) have been shown to be effective in solving partial differential equations by capturing the physics induced constraints as a part of the training loss function.

Scene Synthesis via Uncertainty-Driven Attribute Synchronization

1 code implementation ICCV 2021 Haitao Yang, Zaiwei Zhang, Siming Yan, Haibin Huang, Chongyang Ma, Yi Zheng, Chandrajit Bajaj, QiXing Huang

This task is challenging because 3D scenes exhibit diverse patterns, ranging from continuous ones, such as object sizes and the relative poses between pairs of shapes, to discrete patterns, such as occurrence and co-occurrence of objects with symmetrical relationships.

Deep Predictive Learning of Carotid Stenosis Severity

no code implementations31 Jul 2021 Yiqun Diao, Oliver Zhao, Priya Kothapalli, Peter Monteleone, Chandrajit Bajaj

Carotid artery stenosis is the narrowing of carotid arteries, which supplies blood to the neck and head.

Invariance-based Multi-Clustering of Latent Space Embeddings for Equivariant Learning

no code implementations25 Jul 2021 Chandrajit Bajaj, Avik Roy, Haoran Zhang

Variational Autoencoders (VAEs) have been shown to be remarkably effective in recovering model latent spaces for several computer vision tasks.

Learning Transferable 3D Adversarial Cloaks for Deep Trained Detectors

1 code implementation22 Apr 2021 Arman Maesumi, Mingkang Zhu, Yi Wang, Tianlong Chen, Zhangyang Wang, Chandrajit Bajaj

This paper presents a novel patch-based adversarial attack pipeline that trains adversarial patches on 3D human meshes.

Adversarial Attack

Learning Deep Latent Subspaces for Image Denoising

no code implementations1 Apr 2021 Yunhao Yang, Yuhan Zheng, Yi Wang, Chandrajit Bajaj

We compare our results to a conventional one-encoder-one-decoder architecture.

Image Denoising

Can 3D Adversarial Logos Cloak Humans?

1 code implementation25 Jun 2020 Yi Wang, Jingyang Zhou, Tianlong Chen, Sijia Liu, Shiyu Chang, Chandrajit Bajaj, Zhangyang Wang

Contrary to the traditional adversarial patch, this new form of attack is mapped into the 3D object world and back-propagates to the 2D image domain through differentiable rendering.

Stein Variational Gradient Descent With Matrix-Valued Kernels

1 code implementation NeurIPS 2019 Dilin Wang, Ziyang Tang, Chandrajit Bajaj, Qiang Liu

Stein variational gradient descent (SVGD) is a particle-based inference algorithm that leverages gradient information for efficient approximate inference.

Bayesian Inference

Blind Hyperspectral-Multispectral Image Fusion via Graph Laplacian Regularization

no code implementations21 Feb 2019 Chandrajit Bajaj, Tianming Wang

Fusing a low-resolution hyperspectral image (HSI) and a high-resolution multispectral image (MSI) of the same scene leads to a super-resolution image (SRI), which is information rich spatially and spectrally.

Super-Resolution

SMAC: Simultaneous Mapping and Clustering Using Spectral Decompositions

no code implementations ICML 2018 Chandrajit Bajaj, Tingran Gao, Zihang He, Qi-Xing Huang, Zhenxiao Liang

We introduce a principled approach for simultaneous mapping and clustering (SMAC) for establishing consistent maps across heterogeneous object collections (e. g., 2D images or 3D shapes).

SMAC

Dynamic Filtering with Large Sampling Field for ConvNets

no code implementations ECCV 2018 Jialin Wu, Dai Li, Yu Yang, Chandrajit Bajaj, Xiangyang Ji

We propose a dynamic filtering strategy with large sampling field for ConvNets (LS-DFN), where the position-specific kernels learn from not only the identical position but also multiple sampled neighbor regions.

Object Detection Semantic Segmentation +1

Translation Synchronization via Truncated Least Squares

no code implementations NeurIPS 2017 Xiangru Huang, Zhenxiao Liang, Chandrajit Bajaj, Qi-Xing Huang

In this paper, we introduce a robust algorithm, \textsl{TranSync}, for the 1D translation synchronization problem, in which the aim is to recover the global coordinates of a set of nodes from noisy measurements of relative coordinates along an observation graph.

Translation

Higher Order Mutual Information Approximation for Feature Selection

no code implementations2 Dec 2016 Jilin Wu, Soumyajit Gupta, Chandrajit Bajaj

Feature selection is a process of choosing a subset of relevant features so that the quality of prediction models can be improved.

feature selection

Cannot find the paper you are looking for? You can Submit a new open access paper.