activity
20192022
most citedAttribute-Guided Adversarial Training for Robustness to Natural Perturbations

4 citations · 8 across the 6 of their papers we have counts for

collaborators

10 papers

cs.CV2022

To Find Waldo You Need Contextual Cues: Debiasing Who's Waldo

Yiran Luo, Pratyay Banerjee, Tejas Gokhale +2

We present a debiased dataset for the Person-centric Visual Grounding (PCVG) task first proposed by Cui et al. (2021) in the Who's Waldo dataset. Given an image and a caption, PCVG…

cs.CL20222 cited

Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness

Tejas Gokhale, Swaroop Mishra, Man Luo +2

Data modification, either via additional training datasets, data augmentation, debiasing, and dataset filtering, has been proposed as an effective solution for generalizing to out-…

cs.IR2022

Improving Biomedical Information Retrieval with Neural Retrievers

Man Luo, Arindam Mitra, Tejas Gokhale +1

Information retrieval (IR) is essential in search engines and dialogue systems as well as natural language processing tasks such as open-domain question answering. IR serve an impo…

cs.CV20211 cited

Weakly Supervised Relative Spatial Reasoning for Visual Question Answering

Pratyay Banerjee, Tejas Gokhale, Yezhou Yang +1

Vision-and-language (V\&L) reasoning necessitates perception of visual concepts such as objects and actions, understanding semantics and language grounding, and reasoning about the…

cs.CL2021

Self-Supervised Test-Time Learning for Reading Comprehension

Pratyay Banerjee, Tejas Gokhale, Chitta Baral

Recent work on unsupervised question answering has shown that models can be trained with procedurally generated question-answer pairs and can achieve performance competitive with s…

cs.CV2020

WeaQA: Weak Supervision via Captions for Visual Question Answering

Pratyay Banerjee, Tejas Gokhale, Yezhou Yang +1

Methodologies for training visual question answering (VQA) models assume the availability of datasets with human-annotated \textit{Image-Question-Answer} (I-Q-A) triplets. This has…