Search Results for author: Badri N. Patro

Found 14 papers, 4 papers with code

Barlow constrained optimization for Visual Question Answering

no code implementations7 Mar 2022 Abhishek Jha, Badri N. Patro, Luc van Gool, Tinne Tuytelaars

In this paper, we propose a novel regularization for VQA models, Constrained Optimization using Barlow's theory (COB), that improves the information content of the joint space by minimizing the redundancy.

Question Answering Visual Question Answering +1

Deep Bayesian Network for Visual Question Generation

no code implementations23 Jan 2020 Badri N. Patro, Vinod K. Kurmi, Sandeep Kumar, Vinay P. Namboodiri

This is a Bayesian framework and the results show a remarkable similarity to natural questions as validated by a human study.

Natural Questions Question Generation

Uncertainty based Class Activation Maps for Visual Question Answering

no code implementations23 Jan 2020 Badri N. Patro, Mayank Lunayach, Vinay P. Namboodiri

These have two-fold benefits: a) improvement in obtaining the certainty estimates that correlate better with misclassified samples and b) improved attention maps that provide state-of-the-art results in terms of correlation with human attention regions.

Probabilistic Deep Learning Question Answering +1

Robust Explanations for Visual Question Answering

1 code implementation23 Jan 2020 Badri N. Patro, Shivansh Pate, Vinay P. Namboodiri

Our model explains the answers obtained through a VQA model by providing visual and textual explanations.

Question Answering Visual Question Answering +1

Revisiting Paraphrase Question Generator using Pairwise Discriminator

1 code implementation31 Dec 2019 Badri N. Patro, Dev Chauhan, Vinod K. Kurmi, Vinay P. Namboodiri

One way to ensure this is by adding constraints for true paraphrase embeddings to be close and unrelated paraphrase candidate sentence embeddings to be far.

Paraphrase Generation Sentence Embedding +2

Deep Exemplar Networks for VQA and VQG

no code implementations19 Dec 2019 Badri N. Patro, Vinay P. Namboodiri

Specifically, we incorporate exemplar based approaches and show that an exemplar based module can be incorporated in almost any of the deep learning architectures proposed in the literature and the addition of such a block results in improved performance for solving these tasks.

Question Answering Question Generation +2

Dynamic Attention Networks for Task Oriented Grounding

no code implementations14 Oct 2019 Soumik Dasgupta, Badri N. Patro, Vinay P. Namboodiri

In this work, we show that Dynamic Attention helps in achieving grounding and also aids in the policy learning objective.

Granular Multimodal Attention Networks for Visual Dialog

no code implementations13 Oct 2019 Badri N. Patro, Shivansh Patel, Vinay P. Namboodiri

Particularly, in this work, we propose a new method Granular Multi-modal Attention, where we aim to particularly address the question of the right granularity at which one needs to attend while solving the Visual Dialog task.

Visual Dialog

U-CAM: Visual Explanation using Uncertainty based Class Activation Maps

no code implementations ICCV 2019 Badri N. Patro, Mayank Lunayach, Shivansh Patel, Vinay P. Namboodiri

These have two-fold benefits: a) improvement in obtaining the certainty estimates that correlate better with misclassified samples and b) improved attention maps that provide state-of-the-art results in terms of correlation with human attention regions.

Probabilistic Deep Learning Question Answering +1

Learning Semantic Sentence Embeddings using Sequential Pair-wise Discriminator

2 code implementations COLING 2018 Badri N. Patro, Vinod K. Kurmi, Sandeep Kumar, Vinay P. Namboodiri

One way to ensure this is by adding constraints for true paraphrase embeddings to be close and unrelated paraphrase candidate sentence embeddings to be far.

Paraphrase Generation Sentence Embedding +2

Cannot find the paper you are looking for? You can Submit a new open access paper.