Search Results for author: Murari Mandal

Found 27 papers, 6 papers with code

UnStar: Unlearning with Self-Taught Anti-Sample Reasoning for LLMs

no code implementations22 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.

Privacy Preserving

ConDa: Fast Federated Unlearning with Contribution Dampening

no code implementations5 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.

Federated Learning

Unlearning or Concealment? A Critical Analysis and Evaluation Metrics for Unlearning in Diffusion Models

no code implementations9 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.

Adversarial Attack Retrieval

A Unified Framework for Continual Learning and Machine Unlearning

no code implementations21 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.

Continual Learning Knowledge Distillation +1

Multi-Modal Recommendation Unlearning

no code implementations24 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.

Recommendation Systems

EcoVal: An Efficient Data Valuation Framework for Machine Learning

no code implementations14 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.

Data Valuation

Distill to Delete: Unlearning in Graph Networks with Knowledge Distillation

no code implementations28 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).

Graph Neural Network Knowledge Distillation

Efficient Neural Architecture Search for Emotion Recognition

no code implementations23 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.

Emotion Recognition Facial Expression Recognition +3

Deep Regression Unlearning

1 code implementation15 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.

Inference Attack Machine Unlearning +2

TabSynDex: A Universal Metric for Robust Evaluation of Synthetic Tabular Data

1 code implementation12 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.

Tabular Data Generation

Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher

1 code implementation17 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.

Machine Unlearning

Zero-Shot Machine Unlearning

1 code implementation14 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.

Machine Unlearning Transfer Learning

Fast Yet Effective Machine Unlearning

1 code implementation17 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.

Machine Unlearning

An Empirical Review of Deep Learning Frameworks for Change Detection: Model Design, Experimental Frameworks, Challenges and Research Needs

no code implementations4 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.

Action Recognition Anomaly Detection +4

Learning to Enhance Visual Quality via Hyperspectral Domain Mapping

no code implementations10 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.

Image Restoration

MotionRec: A Unified Deep Framework for Moving Object Recognition

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.

Moving Object Detection object-detection +1

3DFR: A Swift 3D Feature Reductionist Framework for Scene Independent Change Detection

no code implementations26 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.

Change Detection Decoder

3D CNN with Localized Residual Connections for Hyperspectral Image Classification

1 code implementation6 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.

Classification General Classification +1

AVDNet: A Small-Sized Vehicle Detection Network for Aerial Visual Data

no code implementations17 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.

Challenges in Time-Stamp Aware Anomaly Detection in Traffic Videos

no code implementations11 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.

Anomaly Detection

CANDID: Robust Change Dynamics and Deterministic Update Policy for Dynamic Background Subtraction

no code implementations19 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.

Change Detection

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