no code implementations • 10 Jan 2024 • Mandar Kulkarni, Praveen Tangarajan, Kyung Kim, Anusua Trivedi
As a policy model, we experimented with a public gpt-2 model and an in-house BERT model.
no code implementations • 7 Aug 2022 • Mandar Kulkarni, Soumya Chennabasavaraj, Nikesh Garera
We propose a transformer-based approach for code-mix query translation to enable users to search with these queries.
no code implementations • 7 Aug 2022 • Mandar Kulkarni, Nikesh Garera
For demonstration, we show results for Hindi to English query translation and use mBART-large-50 model as the baseline to improve upon.
no code implementations • 2 Nov 2020 • Mandar Kulkarni, Aria Abubakar
In this work, we propose a Soft-Attention Convolutional Neural Network (CNN) based approach for rare event detection in sequences.
1 code implementation • 13 Nov 2018 • Mandar Kulkarni
In this paper, we propose a Reinforcement Learning (RL) based approach to generate adversarial examples for the pre-trained (target) models.
no code implementations • 3 May 2018 • Mandar Kulkarni, Aria Abubakar
We assume that the adversary do not possess any knowledge of the target data distribution, and we use an unlabeled mismatched dataset to query the target, e. g., for the ResNet-50 target, we use the Food-101 dataset as the query.
no code implementations • 21 Mar 2017 • Mandar Kulkarni, Kalpesh Patil, Shirish Karande
Current approaches for Knowledge Distillation (KD) either directly use training data or sample from the training data distribution.
no code implementations • 21 Mar 2017 • Mandar Kulkarni, Shirish Karande
The hierarchical feature representation built by deep networks enable compact and precise encoding of the data.
no code implementations • 16 Sep 2016 • Yash Bhalgat, Mandar Kulkarni, Shirish Karande, Sachin Lodha
Document digitization is becoming increasingly crucial.
no code implementations • 8 Sep 2016 • Anand Sriraman, Mandar Kulkarni, Rahul Kumar, Kanika Kalra, Purushotam Radadia, Shirish Karande
We present an end-to-end machine-human image annotation system where each component can be attached in a plug-and-play fashion.