no code implementations • 22 Oct 2024 • Yash Sinha, Murari Mandal, Mohan Kankanhalli
The key components of machine learning are data samples for training, model for learning patterns, and loss function for optimizing accuracy.
no code implementations • 5 Oct 2024 • Vikram S Chundawat, Pushkar Niroula, Prasanna Dhungana, Stefan Schoepf, Murari Mandal, Alexandra Brintrup
Our technique does not require clients data or any kind of retraining and it does not put any computational overhead on either the client or server side.
no code implementations • 9 Sep 2024 • Aakash Sen Sharma, Niladri Sarkar, Vikram Chundawat, Ankur A Mali, Murari Mandal
We show that the objective functions used for unlearning in the existing methods lead to decoupling of the targeted concepts (meant to be forgotten) for the corresponding prompts.
no code implementations • 21 Aug 2024 • Romit Chatterjee, Vikram Chundawat, Ayush Tarun, Ankur Mali, Murari Mandal
Continual learning and machine unlearning are crucial challenges in machine learning, typically addressed separately.
no code implementations • 24 May 2024 • Yash Sinha, Murari Mandal, Mohan Kankanhalli
This is particularly true in case of multi-modal recommender systems (MMRS), which aim to accommodate the growing influence of multi-modal information on user preferences.
no code implementations • 14 Feb 2024 • Ayush K Tarun, Vikram S Chundawat, Murari Mandal, Hong Ming Tan, Bowei Chen, Mohan Kankanhalli
In this paper, we introduce an efficient data valuation framework EcoVal, to estimate the value of data for machine learning models in a fast and practical manner.
no code implementations • 28 Sep 2023 • Yash Sinha, Murari Mandal, Mohan Kankanhalli
Our work takes a novel approach to address these challenges in graph unlearning through knowledge distillation, as it distills to delete in GNN (D2DGN).
no code implementations • 23 Mar 2023 • Monu Verma, Murari Mandal, Satish Kumar Reddy, Yashwanth Reddy Meedimale, Santosh Kumar Vipparthi
In this paper, we proposed to search for a highly efficient and robust neural architecture for both macro and micro-level facial expression recognition.
1 code implementation • 15 Oct 2022 • Ayush K Tarun, Vikram S Chundawat, Murari Mandal, Mohan Kankanhalli
In the last few years, there have been notable developments in machine unlearning to remove the information of certain training data efficiently and effectively from ML models.
1 code implementation • 12 Jul 2022 • Vikram S Chundawat, Ayush K Tarun, Murari Mandal, Mukund Lahoti, Pratik Narang
We present several baseline models for comparative analysis of the proposed evaluation metric with existing generative models.
1 code implementation • 17 May 2022 • Vikram S Chundawat, Ayush K Tarun, Murari Mandal, Mohan Kankanhalli
It facilitates the provision for removal of certain set or class of data from an already trained ML model without requiring retraining from scratch.
1 code implementation • 14 Jan 2022 • Vikram S Chundawat, Ayush K Tarun, Murari Mandal, Mohan Kankanhalli
In case of machine learning (ML) applications, this necessitates deletion of data not only from storage archives but also from ML models.
1 code implementation • 17 Nov 2021 • Ayush K Tarun, Vikram S Chundawat, Murari Mandal, Mohan Kankanhalli
In the impair step, the noise matrix along with a very high learning rate is used to induce sharp unlearning in the model.
no code implementations • 4 May 2021 • Murari Mandal, Santosh Kumar Vipparthi
To the best of our knowledge, this is a first attempt to comparatively analyze the different evaluation frameworks used in the existing deep change detection methods.
no code implementations • 10 Feb 2021 • Prateek Garg, Murari Mandal, Pratik Narang
Low light conditions in aerial images adversely affect the performance of several vision based applications.
no code implementations • 10 Feb 2021 • Harsh Sinha, Aditya Mehta, Murari Mandal, Pratik Narang
We incorporate a self-supervision and a spectral profile regularization network to infer a plausible HSI from an RGB image.
no code implementations • 7 Nov 2020 • Aditya Mehta, Harsh Sinha, Murari Mandal, Pratik Narang
The performance of SkyGAN is evaluated on the recent SateHaze1k dataset as well as the HAI dataset.
no code implementations • 4 Aug 2020 • Murari Mandal, Lav Kush Kumar, Santosh Kumar Vipparthi
Therefore, in this paper, we introduce MOR-UAV, a large-scale video dataset for MOR in aerial videos.
no code implementations • 7 May 2020 • Codruta O. Ancuti, Cosmin Ancuti, Florin-Alexandru Vasluianu, Radu Timofte, Jing Liu, Haiyan Wu, Yuan Xie, Yanyun Qu, Lizhuang Ma, Ziling Huang, Qili Deng, Ju-Chin Chao, Tsung-Shan Yang, Peng-Wen Chen, Po-Min Hsu, Tzu-Yi Liao, Chung-En Sun, Pei-Yuan Wu, Jeonghyeok Do, Jongmin Park, Munchurl Kim, Kareem Metwaly, Xuelu Li, Tiantong Guo, Vishal Monga, Mingzhao Yu, Venkateswararao Cherukuri, Shiue-Yuan Chuang, Tsung-Nan Lin, David Lee, Jerome Chang, Zhan-Han Wang, Yu-Bang Chang, Chang-Hong Lin, Yu Dong, Hong-Yu Zhou, Xiangzhen Kong, Sourya Dipta Das, Saikat Dutta, Xuan Zhao, Bing Ouyang, Dennis Estrada, Meiqi Wang, Tianqi Su, Siyi Chen, Bangyong Sun, Vincent Whannou de Dravo, Zhe Yu, Pratik Narang, Aryan Mehra, Navaneeth Raghunath, Murari Mandal
We focus on the proposed solutions and their results evaluated on NH-Haze, a novel dataset consisting of 55 pairs of real haze free and nonhomogeneous hazy images recorded outdoor.
no code implementations • WACV 2020 • Murari Mandal, Lav Kush Kumar, Mahipal Singh Saran, Santosh Kumar Vipparthi
To the best of our knowledge, this is a first attempt for simultaneous localization and classification of moving objects in a video, i. e. MOR in a single-stage deep learning framework.
no code implementations • 26 Dec 2019 • Murari Mandal, Vansh Dhar, Abhishek Mishra, Santosh Kumar Vipparthi
In this paper we propose an end-to-end swift 3D feature reductionist framework (3DFR) for scene independent change detection.
1 code implementation • 6 Dec 2019 • Shivangi Dwivedi, Murari Mandal, Shekhar Yadav, Santosh Kumar Vipparthi
Our work chalks a comparative study with the existing methods employed for abstracting deeper features and propose a model which incorporates residual features from multiple stages in the network.
no code implementations • 31 Aug 2019 • Murari Mandal, Manal Shah, Prashant Meena, Santosh Kumar Vipparthi
Detection of small-sized targets is of paramount importance in many aerial vision-based applications.
no code implementations • 17 Jul 2019 • Murari Mandal, Manal Shah, Prashant Meena, Sanhita Devi, Santosh Kumar Vipparthi
Detection of small-sized targets in aerial views is a challenging task due to the smallness of vehicle size, complex background, and monotonic object appearances.
no code implementations • 11 Jun 2019 • Kuldeep Marotirao Biradar, Ayushi Gupta, Murari Mandal, Santosh Kumar Vipparthi
In this paper, we present a three-stage pipeline to learn the motion patterns in videos to detect a visual anomaly.
no code implementations • 7 May 2018 • Sonakshi Mathur, Mallika Chaudhary, Hemant Verma, Murari Mandal, S. K. Vipparthi, Subrahmanyam Murala
A novel color feature descriptor, Multichannel Distributed Local Pattern (MDLP) is proposed in this manuscript.
no code implementations • 19 Apr 2018 • Murari Mandal, Prafulla Saxena, Santosh Kumar Vipparthi, Subrahmanyam Murala
Background subtraction in video provides the preliminary information which is essential for many computer vision applications.