no code implementations • 29 Mar 2024 • Anurag Roy, Riddhiman Moulick, Vinay K. Verma, Saptarshi Ghosh, Abir Das
Continual Learning (CL) enables machine learning models to learn from continuously shifting new training data in absence of data from old tasks.
no code implementations • ICCV 2023 • Anurag Roy, Vinay Kumar Verma, Sravan Voonna, Kripabandhu Ghosh, Saptarshi Ghosh, Abir Das
Although there have been some recent CL approaches for vision transformers, they either store training instances of previous tasks or require a task identifier during test time, which can be limiting.
no code implementations • 13 Oct 2022 • Anurag Roy, David Johnson Ekka, Saptarshi Ghosh, Abir Das
In this paper, we propose a new and challenging Few-Shot Visual Question Generation (FS-VQG) task and provide a comprehensive benchmark to it.
1 code implementation • 9 Jan 2021 • Anurag Roy, Shalmoli Ghosh, Kripabandhu Ghosh, Saptarshi Ghosh
To enable tasks such as search/retrieval and classification over all the available data, we need robust algorithms for text normalization, i. e., for cleaning different kinds of noise in the text.
Information Retrieval Optical Character Recognition (OCR) +2
1 code implementation • 23 Jul 2020 • Anurag Roy, Vinay Kumar Verma, Kripabandhu Ghosh, Saptarshi Ghosh
Most existing algorithms for cross-modal Information Retrieval are based on a supervised train-test setup, where a model learns to align the mode of the query (e. g., text) to the mode of the documents (e. g., images) from a given training set.