6 papers
Forget Less by Learning Together through Concept Consolidation
Arjun Ramesh Kaushik, Naresh Kumar Devulapally, Vishnu Suresh Lokhande +2
Custom Diffusion Models (CDMs) have gained significant attention due to their remarkable ability to personalize generative processes. However, existing CDMs suffer from catastrophi…
Learning Action Hierarchies via Hybrid Geometric Diffusion
Arjun Ramesh Kaushik, Nalini K. Ratha, Venu Govindaraju
Temporal action segmentation is a critical task in video understanding, where the goal is to assign action labels to each frame in a video. While recent advances leverage iterative…
Forget Less by Learning from Parents Through Hierarchical Relationships
Arjun Ramesh Kaushik, Naresh Kumar Devulapally, Vishnu Suresh Lokhande +2
Custom Diffusion Models (CDMs) offer impressive capabilities for personalization in generative modeling, yet they remain vulnerable to catastrophic forgetting when learning new con…
Shielding Latent Face Representations From Privacy Attacks
Arjun Ramesh Kaushik, Bharat Chandra Yalavarthi, Arun Ross +2
In today's data-driven analytics landscape, deep learning has become a powerful tool, with latent representations, known as embeddings, playing a central role in several applicatio…
Enhancing Authorship Attribution through Embedding Fusion: A Novel Approach with Masked and Encoder-Decoder Language Models
Arjun Ramesh Kaushik, Sunil Rufus R P, Nalini Ratha
The increasing prevalence of AI-generated content alongside human-written text underscores the need for reliable discrimination methods. To address this challenge, we propose a nov…
Towards Building Secure UAV Navigation with FHE-aware Knowledge Distillation
Arjun Ramesh Kaushik, Charanjit Jutla, Nalini Ratha
In safeguarding mission-critical systems, such as Unmanned Aerial Vehicles (UAVs), preserving the privacy of path trajectories during navigation is paramount. While the combination…