377 citations · 860 across the 18 of their papers we have counts for
25 papers
Parcel2Progression: An Anatomy-aware Longitudinal Framework for Alzheimer's Disease Diagnosis
Madhumitha Venkatesh, Shanawaj S Madarkar, Konda Reddy Mopuri
Alzheimer's disease (AD) progression is a longitudinal process with subtle pathological cues in the early stages. Yet, computational constraints have limited most neuroimaging mode…
TILDE: TILt-based Distributional Erasure for Concept Unlearning
Naveen George, Naoki Murata, Yuhta Takida +2
Concept unlearning in text-to-image diffusion models is critical for safe and practical deployment: with rising privacy concerns, copyright disputes, trademark constraints, and saf…
Rethinking Dataset Distillation: Hard Truths about Soft Labels
Priyam Dey, Aditya Sahdev, Sunny Bhati +2
Despite the perceived success of large-scale dataset distillation (DD) methods, recent evidence finds that simple random image baselines perform on-par with state-of-theart DD meth…
Exploring Compositionality in Vision Transformers using Wavelet Representations
Akshad Shyam Purushottamdas, Pranav K Nayak, Divya Mehul Rajparia +4
While insights into the workings of the transformer model have largely emerged by analysing their behaviour on language tasks, this work investigates the representations learnt by…
DiRe: Diversity-promoting Regularization for Dataset Condensation
Saumyaranjan Mohanty, Aravind Reddy, Konda Reddy Mopuri
In Dataset Condensation, the goal is to synthesize a small dataset that replicates the training utility of a large original dataset. Existing condensation methods synthesize datase…
Locality-Aware Continual Unlearning for Diffusion Models
Naveen George, Naoki Murata, Yuhta Takida +2
Real-world deployment of text-to-image diffusion models requires continual concept removal as new privacy, copyright, or safety obligations arise over time. Existing unlearning met…
DermaCon-IN: A Multi-concept Annotated Dermatological Image Dataset of Indian Skin Disorders for Clinical AI Research
Shanawaj S Madarkar, Mahajabeen Madarkar, Madhumitha Venkatesh +9
Artificial intelligence is poised to augment dermatological care by enabling scalable image-based diagnostics. Yet, the development of robust and equitable models remains hindered…
Lost in Context: The Influence of Context on Feature Attribution Methods for Object Recognition
Sayanta Adhikari, Rishav Kumar, Konda Reddy Mopuri +1
Contextual information plays a critical role in object recognition models within computer vision, where changes in context can significantly affect accuracy, underscoring models' d…
Learning to Retain while Acquiring: Combating Distribution-Shift in Adversarial Data-Free Knowledge Distillation
Gaurav Patel, Konda Reddy Mopuri, Qiang Qiu
Data-free Knowledge Distillation (DFKD) has gained popularity recently, with the fundamental idea of carrying out knowledge transfer from a Teacher neural network to a Student neur…
Class Balancing GAN with a Classifier in the Loop
Harsh Rangwani, Konda Reddy Mopuri, R. Venkatesh Babu
Generative Adversarial Networks (GANs) have swiftly evolved to imitate increasingly complex image distributions. However, majority of the developments focus on performance of GANs…
Mining Data Impressions from Deep Models as Substitute for the Unavailable Training Data
Gaurav Kumar Nayak, Konda Reddy Mopuri, Saksham Jain +1
Pretrained deep models hold their learnt knowledge in the form of model parameters. These parameters act as "memory" for the trained models and help them generalize well on unseen…
Effectiveness of Arbitrary Transfer Sets for Data-free Knowledge Distillation
Gaurav Kumar Nayak, Konda Reddy Mopuri, Anirban Chakraborty
Knowledge Distillation is an effective method to transfer the learning across deep neural networks. Typically, the dataset originally used for training the Teacher model is chosen…
Dataset Condensation with Gradient Matching
Bo Zhao, Konda Reddy Mopuri, Hakan Bilen
As the state-of-the-art machine learning methods in many fields rely on larger datasets, storing datasets and training models on them become significantly more expensive. This pape…
Adversarial Fooling Beyond "Flipping the Label"
Konda Reddy Mopuri, Vaisakh Shaj, R. Venkatesh Babu
Recent advancements in CNNs have shown remarkable achievements in various CV/AI applications. Though CNNs show near human or better than human performance in many critical tasks, t…
iDLG: Improved Deep Leakage from Gradients
Bo Zhao, Konda Reddy Mopuri, Hakan Bilen
It is widely believed that sharing gradients will not leak private training data in distributed learning systems such as Collaborative Learning and Federated Learning, etc. Recentl…
Zero-Shot Knowledge Distillation in Deep Networks
Gaurav Kumar Nayak, Konda Reddy Mopuri, Vaisakh Shaj +2
Knowledge distillation deals with the problem of training a smaller model (Student) from a high capacity source model (Teacher) so as to retain most of its performance. Existing ap…
Gray-box Adversarial Training
Vivek B. S., Konda Reddy Mopuri, R. Venkatesh Babu
Adversarial samples are perturbed inputs crafted to mislead the machine learning systems. A training mechanism, called adversarial training, which presents adversarial samples alon…
Ask, Acquire, and Attack: Data-free UAP Generation using Class Impressions
Konda Reddy Mopuri, Phani Krishna Uppala, R. Venkatesh Babu
Deep learning models are susceptible to input specific noise, called adversarial perturbations. Moreover, there exist input-agnostic noise, called Universal Adversarial Perturbatio…
Generalizable Data-free Objective for Crafting Universal Adversarial Perturbations
Konda Reddy Mopuri, Aditya Ganeshan, R. Venkatesh Babu
Machine learning models are susceptible to adversarial perturbations: small changes to input that can cause large changes in output. It is also demonstrated that there exist input-…
NAG: Network for Adversary Generation
Konda Reddy Mopuri, Utkarsh Ojha, Utsav Garg +1
Adversarial perturbations can pose a serious threat for deploying machine learning systems. Recent works have shown existence of image-agnostic perturbations that can fool classifi…
CNN Fixations: An unraveling approach to visualize the discriminative image regions
Konda Reddy Mopuri, Utsav Garg, R. Venkatesh Babu
Deep convolutional neural networks (CNN) have revolutionized various fields of vision research and have seen unprecedented adoption for multiple tasks such as classification, detec…
Fast Feature Fool: A data independent approach to universal adversarial perturbations
Konda Reddy Mopuri, Utsav Garg, R. Venkatesh Babu
State-of-the-art object recognition Convolutional Neural Networks (CNNs) are shown to be fooled by image agnostic perturbations, called universal adversarial perturbations. It is a…
Deep image representations using caption generators
Konda Reddy Mopuri, Vishal B. Athreya, R. Venkatesh Babu
Deep learning exploits large volumes of labeled data to learn powerful models. When the target dataset is small, it is a common practice to perform transfer learning using pre-trai…
A Taxonomy of Deep Convolutional Neural Nets for Computer Vision
Suraj Srinivas, Ravi Kiran Sarvadevabhatla, Konda Reddy Mopuri +3
Traditional architectures for solving computer vision problems and the degree of success they enjoyed have been heavily reliant on hand-crafted features. However, of late, deep lea…