no code implementations • 24 Apr 2024 • Chandrajit Bajaj, Minh Nguyen
Reinforcement learning (RL) with continuous state and action spaces remains one of the most challenging problems within the field.
1 code implementation • 21 Feb 2024 • Chandrajit Bajaj, Minh Nguyen
Instead of treating time series as a static vector or a data sequence as often seen in previous methods, we introduce a novel framework that considers each time series, not necessarily of fixed length, as a sample realization of a continuous-time stochastic process.
1 code implementation • 20 Apr 2023 • Haitao Yang, Xiangru Huang, Bo Sun, Chandrajit Bajaj, QiXing Huang
GenCorres addresses this issue by learning an implicit generator from the input shapes, which provides intermediate shapes between two arbitrary shapes.
1 code implementation • 15 Mar 2023 • Chen Song, Chandrajit Bajaj, QiXing Huang
We additionally show that our approach easily extends to video super-resolution when combined with recent advances in implicit neural representation.
no code implementations • 6 Dec 2022 • Chandrajit Bajaj, Conrad Li, Minh Nguyen
In this paper, we develop a reinforcement learning (RL) framework in a continuous setting and based on a stochastic parametrized Hamiltonian version of the Pontryagin maximum principle (PMP) to solve the side-chain packing and protein-folding problem.
no code implementations • 26 Nov 2022 • Chandrajit Bajaj, Omatharv Bharat Vaidya, Yi Wang
Task learning in neural networks typically requires finding a globally optimal minimizer to a loss function objective.
no code implementations • 1 Sep 2022 • Taemin Heo, Chandrajit Bajaj
We learn approximate full-rank and compact tensor sketches with decompositive representations providing compact space, time and spectral embeddings of tensor fields.
1 code implementation • 28 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.
1 code implementation • CVPR 2022 • Chen Song, QiXing Huang, Chandrajit Bajaj
A camera begins to sense light the moment we press the shutter button.
1 code implementation • 15 Nov 2021 • Chandrajit Bajaj, Yi Wang, Yunhao Yang
Our \textit{Recursive Self Enhancement Reinforcement Learning}(RSE-RL) model views the identification and correction of artifacts as a recursive self-learning and self-improvement exercise and consists of two major sub-modules: (i) The latent feature sub-space clustering/grouping obtained through variational auto-encoders enabling rapid identification of the correspondence and discrepancy between noisy and clean image patches.
1 code implementation • 15 Nov 2021 • Chandrajit Bajaj, Minh Nguyen
In this paper, we propose novel learning frameworks to tackle optimal control problems by applying the Pontryagin maximum principle and then solving for a Hamiltonian dynamical system.
1 code implementation • 26 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.
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.
1 code implementation • ICCV 2021 • QiXing Huang, Xiangru Huang, Bo Sun, Zaiwei Zhang, Junfeng Jiang, Chandrajit Bajaj
Our approach builds on an approximation of the as-rigid-as possible (or ARAP) deformation energy.
no code implementations • 31 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.
no code implementations • 25 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.
1 code implementation • 22 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.
1 code implementation • 1 Apr 2021 • Yunhao Yang, Yi Wang, Chandrajit Bajaj
Camera Image Signal Processing (ISP) pipelines can get appealing results in different image signal processing tasks.
1 code implementation • 25 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.
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.
no code implementations • 21 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.
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).
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.
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.
no code implementations • 2 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.