22 citations · 31 across the 3 of their papers we have counts for
4 papers
Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning
Jishnu Jaykumar P, Kamalesh Palanisamy, Yu-Wei Chao +2
We propose a novel framework for few-shot learning by leveraging large-scale vision-language models such as CLIP. Motivated by unimodal prototypical networks for few-shot learning,…
Self-Supervised Unseen Object Instance Segmentation via Long-Term Robot Interaction
Yangxiao Lu, Ninad Khargonkar, Zesheng Xu +6
We introduce a novel robotic system for improving unseen object instance segmentation in the real world by leveraging long-term robot interaction with objects. Previous approaches…
SplitEasy: A Practical Approach for Training ML models on Mobile Devices
Kamalesh Palanisamy, Vivek Khimani, Moin Hussain Moti +1
Modern mobile devices, although resourceful, cannot train state-of-the-art machine learning models without the assistance of servers, which require access to, potentially, privacy-…
Rethinking CNN Models for Audio Classification
Kamalesh Palanisamy, Dipika Singhania, Angela Yao
In this paper, we show that ImageNet-Pretrained standard deep CNN models can be used as strong baseline networks for audio classification. Even though there is a significant differ…