Search Results for author: M. Salman Asif

Found 41 papers, 14 papers with code

Overcoming Distribution Shifts in Plug-and-Play Methods with Test-Time Training

no code implementations15 Mar 2024 Edward P. Chandler, Shirin Shoushtari, Jiaming Liu, M. Salman Asif, Ulugbek S. Kamilov

A common issue with the learned models is that of a performance drop when there is a distribution shift between the training and testing data.

Image Reconstruction

STRIDE: Single-video based Temporally Continuous Occlusion Robust 3D Pose Estimation

no code implementations24 Dec 2023 Rohit Lal, Saketh Bachu, Yash Garg, Arindam Dutta, Calvin-Khang Ta, Dripta S. Raychaudhuri, Hannah Dela Cruz, M. Salman Asif, Amit K. Roy-Chowdhury

This challenge arises because these models struggle to generalize beyond their training datasets, and the variety of occlusions is hard to capture in the training data.

3D Human Pose Estimation 3D Pose Estimation +3

Domain Expansion via Network Adaptation for Solving Inverse Problems

no code implementations10 Oct 2023 Nebiyou Yismaw, Ulugbek S. Kamilov, M. Salman Asif

Deep learning-based methods deliver state-of-the-art performance for solving inverse problems that arise in computational imaging.

Domain Adaptation

Factorized Tensor Networks for Multi-Task and Multi-Domain Learning

no code implementations9 Oct 2023 Yash Garg, Nebiyou Yismaw, Rakib Hyder, Ashley Prater-Bennette, M. Salman Asif

In this paper, we propose a factorized tensor network (FTN) that can achieve accuracy comparable to independent single-task/domain networks with a small number of additional parameters.

Tensor Networks

Robust Multimodal Learning with Missing Modalities via Parameter-Efficient Adaptation

no code implementations6 Oct 2023 Md Kaykobad Reza, Ashley Prater-Bennette, M. Salman Asif

We conduct a series of experiments to highlight the missing modality robustness of our proposed method on 5 different datasets for multimodal semantic segmentation, multimodal material segmentation, and multimodal sentiment analysis tasks.

Multimodal Sentiment Analysis Semantic Segmentation

Prior Mismatch and Adaptation in PnP-ADMM with a Nonconvex Convergence Analysis

no code implementations29 Sep 2023 Shirin Shoushtari, Jiaming Liu, Edward P. Chandler, M. Salman Asif, Ulugbek S. Kamilov

Our second set of numerical results considers a simple and effective domain adaption strategy that closes the performance gap due to the use of mismatched denoisers.

Domain Adaptation Image Super-Resolution

MMSFormer: Multimodal Transformer for Material and Semantic Segmentation

1 code implementation7 Sep 2023 Md Kaykobad Reza, Ashley Prater-Bennette, M. Salman Asif

Furthermore, our ablation studies also highlight the capacity of different input modalities to improve performance in the identification of different types of materials.

Segmentation Semantic Segmentation +1

DNeRV: Modeling Inherent Dynamics via Difference Neural Representation for Videos

no code implementations CVPR 2023 Qi Zhao, M. Salman Asif, Zhan Ma

DNeRV achieves competitive results against the state-of-the-art neural compression approaches and outperforms existing implicit methods on downstream inpainting and interpolation for $960 \times 1920$ videos.

Video Compression

Ensemble-based Blackbox Attacks on Dense Prediction

1 code implementation CVPR 2023 Zikui Cai, Yaoteng Tan, M. Salman Asif

We performed a number of experiments for object detectors and segmentation to highlight the significance of the our proposed methods.

Object object-detection +2

Disguise without Disruption: Utility-Preserving Face De-Identification

no code implementations23 Mar 2023 Zikui Cai, Zhongpai Gao, Benjamin Planche, Meng Zheng, Terrence Chen, M. Salman Asif, Ziyan Wu

We extensively evaluate our method using multiple datasets, demonstrating a higher de-identification rate and superior consistency compared to prior approaches in various downstream tasks.

De-identification Ensemble Learning

Compressive Sensing with Tensorized Autoencoder

no code implementations10 Mar 2023 Rakib Hyder, M. Salman Asif

Furthermore, in many cases, parts of images can be corrupted by noise or missing entries.

Compressive Sensing Denoising

Coded Illumination for 3D Lensless Imaging

no code implementations22 Dec 2022 Yucheng Zheng, M. Salman Asif

With such baseline distance between the lensless camera and illumination source, the camera observes a slice of the 3D volume, and the PSF of each depth plane becomes more resolvable from each other.

3D Reconstruction Image Reconstruction

Efficient Visual Computing with Camera RAW Snapshots

1 code implementation15 Dec 2022 Zhihao LI, Ming Lu, Xu Zhang, Xin Feng, M. Salman Asif, Zhan Ma

Conventional cameras capture image irradiance on a sensor and convert it to RGB images using an image signal processor (ISP).

Autonomous Driving Image Compression +2

GAMA: Generative Adversarial Multi-Object Scene Attacks

no code implementations20 Sep 2022 Abhishek Aich, Calvin-Khang Ta, Akash Gupta, Chengyu Song, Srikanth V. Krishnamurthy, M. Salman Asif, Amit K. Roy-Chowdhury

Using the joint image-text features to train the generator, we show that GAMA can craft potent transferable perturbations in order to fool victim classifiers in various attack settings.

Language Modelling Object

Leveraging Local Patch Differences in Multi-Object Scenes for Generative Adversarial Attacks

no code implementations20 Sep 2022 Abhishek Aich, Shasha Li, Chengyu Song, M. Salman Asif, Srikanth V. Krishnamurthy, Amit K. Roy-Chowdhury

Our goal is to design an attack strategy that can learn from such natural scenes by leveraging the local patch differences that occur inherently in such images (e. g. difference between the local patch on the object `person' and the object `bike' in a traffic scene).

Object

Blackbox Attacks via Surrogate Ensemble Search

1 code implementation7 Aug 2022 Zikui Cai, Chengyu Song, Srikanth Krishnamurthy, Amit Roy-Chowdhury, M. Salman Asif

We also show that the perturbations generated by our proposed method are highly transferable and can be adopted for hard-label blackbox attacks.

H2-Stereo: High-Speed, High-Resolution Stereoscopic Video System

no code implementations4 Aug 2022 Ming Cheng, Yiling Xu, Wang Shen, M. Salman Asif, Chao Ma, Jun Sun, Zhan Ma

We utilize a disparity network to transfer spatiotemporal information across views even in large disparity scenes, based on which, we propose disparity-guided flow-based warping for LSR-HFR view and complementary warping for HSR-LFR view.

Super-Resolution Vocal Bursts Intensity Prediction

Incremental Task Learning with Incremental Rank Updates

1 code implementation19 Jul 2022 Rakib Hyder, Ken Shao, Boyu Hou, Panos Markopoulos, Ashley Prater-Bennette, M. Salman Asif

Our method also offers better memory efficiency compared to episodic memory- and mask-based approaches.

Continual Learning

Event Transformer

no code implementations11 Apr 2022 Zhihao LI, M. Salman Asif, Zhan Ma

The event camera is a bio-vision inspired camera with high dynamic range, high response speed, and low power consumption, recently attracting extensive attention for its use in vast vision tasks.

Event-based vision

Provable and Efficient Continual Representation Learning

1 code implementation3 Mar 2022 Yingcong Li, Mingchen Li, M. Salman Asif, Samet Oymak

In continual learning (CL), the goal is to design models that can learn a sequence of tasks without catastrophic forgetting.

Continual Learning Representation Learning

Coded Illumination for Improved Lensless Imaging

1 code implementation25 Nov 2021 Yucheng Zheng, M. Salman Asif

In this paper, we propose to use coded illumination to improve the quality of images reconstructed with lensless cameras.

ADC: Adversarial attacks against object Detection that evade Context consistency checks

no code implementations24 Oct 2021 Mingjun Yin, Shasha Li, Chengyu Song, M. Salman Asif, Amit K. Roy-Chowdhury, Srikanth V. Krishnamurthy

A very recent defense strategy for detecting adversarial examples, that has been shown to be robust to current attacks, is to check for intrinsic context consistencies in the input data, where context refers to various relationships (e. g., object-to-object co-occurrence relationships) in images.

Object object-detection +1

A Simple Framework for 3D Lensless Imaging with Programmable Masks

1 code implementation ICCV 2021 Yucheng Zheng, Yi Hua, Aswin C. Sankaranarayanan, M. Salman Asif

Existing methods for lensless imaging can recover the depth and intensity of the scene, but they require solving computationally-expensive inverse problems.

Depth Estimation

Recovery Analysis for Plug-and-Play Priors using the Restricted Eigenvalue Condition

1 code implementation NeurIPS 2021 Jiaming Liu, M. Salman Asif, Brendt Wohlberg, Ulugbek S. Kamilov

The plug-and-play priors (PnP) and regularization by denoising (RED) methods have become widely used for solving inverse problems by leveraging pre-trained deep denoisers as image priors.

Compressive Sensing Denoising

Provably Convergent Algorithms for Solving Inverse Problems Using Generative Models

no code implementations13 May 2021 Viraj Shah, Rakib Hyder, M. Salman Asif, Chinmay Hegde

The traditional approach of hand-crafting priors (such as sparsity) for solving inverse problems is slowly being replaced by the use of richer learned priors (such as those modeled by deep generative networks).

Solving Phase Retrieval with a Learned Reference

1 code implementation ECCV 2020 Rakib Hyder, Zikui Cai, M. Salman Asif

We performed a number of simulations on a variety of datasets under different conditions and found that our proposed method for phase retrieval via unrolled network and learned reference provides near-perfect recovery at fixed (small) computational cost.

Retrieval

Non-Adversarial Video Synthesis with Learned Priors

1 code implementation CVPR 2020 Abhishek Aich, Akash Gupta, Rameswar Panda, Rakib Hyder, M. Salman Asif, Amit K. Roy-Chowdhury

Different from these methods, we focus on the problem of generating videos from latent noise vectors, without any reference input frames.

Joint Image and Depth Estimation with Mask-Based Lensless Cameras

no code implementations6 Oct 2019 Yucheng Zheng, M. Salman Asif

We built a prototype lensless camera and present experimental results for reconstruction of intensity and depth maps of different real objects.

Depth Estimation

A Dual Camera System for High Spatiotemporal Resolution Video Acquisition

no code implementations28 Sep 2019 Ming Cheng, Zhan Ma, M. Salman Asif, Yiling Xu, Haojie Liu, Wenbo Bao, Jun Sun

This paper presents a dual camera system for high spatiotemporal resolution (HSTR) video acquisition, where one camera shoots a video with high spatial resolution and low frame rate (HSR-LFR) and another one captures a low spatial resolution and high frame rate (LSR-HFR) video.

Vocal Bursts Intensity Prediction

Generative Models for Low-Dimensional Video Representation and Compressive Sensing

no code implementations NeurIPS Workshop Deep_Invers 2019 Rakib Hyder, M. Salman Asif

In the context of compressive sensing, if the unknown image belongs to the range of a pretrained generative network, then we can recover the image by estimating the underlying compact latent code from the available measurements.

Compressive Sensing Denoising +1

Alternating Phase Projected Gradient Descent with Generative Priors for Solving Compressive Phase Retrieval

no code implementations7 Mar 2019 Rakib Hyder, Viraj Shah, Chinmay Hegde, M. Salman Asif

We empirically show that the performance of our method with projected gradient descent is superior to the existing approach for solving phase retrieval under generative priors.

Retrieval

Generative Models for Low-Rank Video Representation and Reconstruction

1 code implementation25 Feb 2019 Rakib Hyder, M. Salman Asif

Finding compact representation of videos is an essential component in almost every problem related to video processing or understanding.

Toward Depth Estimation Using Mask-Based Lensless Cameras

no code implementations9 Nov 2017 M. Salman Asif

Recently, coded masks have been used to demonstrate a thin form-factor lensless camera, FlatCam, in which a mask is placed immediately on top of a bare image sensor.

Depth Estimation

Toward Long Distance, Sub-diffraction Imaging Using Coherent Camera Arrays

no code implementations28 Oct 2015 Jason Holloway, M. Salman Asif, Manoj Kumar Sharma, Nathan Matsuda, Roarke Horstmeyer, Oliver Cossairt, Ashok Veeraraghavan

Recent advances in ptychography have demonstrated that one can image beyond the diffraction limit of the objective lens in a microscope.

Retrieval Translation

FlatCam: Thin, Bare-Sensor Cameras using Coded Aperture and Computation

2 code implementations1 Sep 2015 M. Salman Asif, Ali Ayremlou, Aswin Sankaranarayanan, Ashok Veeraraghavan, Richard Baraniuk

FlatCam is a thin form-factor lensless camera that consists of a coded mask placed on top of a bare, conventional sensor array.

Image Reconstruction

Sparse Recovery of Streaming Signals Using L1-Homotopy

no code implementations14 Jun 2013 M. Salman Asif, Justin Romberg

In this paper, we discuss two such streaming systems and a homotopy-based algorithm for quickly solving the associated L1-norm minimization programs: 1) Recovery of a smooth, time-varying signal for which, instead of using block transforms, we use lapped orthogonal transforms for sparse representation.

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