activity
20162021
most citedFoodX-251: A Dataset for Fine-grained Food Classification

66 citations · 99 across the 8 of their papers we have counts for

collaborators

16 papers

cs.CV2021

Challenges in Procedural Multimodal Machine Comprehension:A Novel Way To Benchmark

Pritish Sahu, Karan Sikka, Ajay Divakaran

We focus on Multimodal Machine Reading Comprehension (M3C) where a model is expected to answer questions based on given passage (or context), and the context and the questions can…

cs.CL20211 cited

Towards Solving Multimodal Comprehension

Pritish Sahu, Karan Sikka, Ajay Divakaran

This paper targets the problem of procedural multimodal machine comprehension (M3C). This task requires an AI to comprehend given steps of multimodal instructions and then answer q…

cs.LG20203 cited

Detecting Trojaned DNNs Using Counterfactual Attributions

Karan Sikka, Indranil Sur, Susmit Jha +2

We target the problem of detecting Trojans or backdoors in DNNs. Such models behave normally with typical inputs but produce specific incorrect predictions for inputs poisoned with…

cs.CV20205 cited

Zero-Shot Learning with Knowledge Enhanced Visual Semantic Embeddings

Karan Sikka, Jihua Huang, Andrew Silberfarb +6

We improve zero-shot learning (ZSL) by incorporating common-sense knowledge in DNNs. We propose Common-Sense based Neuro-Symbolic Loss (CSNL) that formulates prior knowledge as nov…

cs.CV202021 cited

RGB2LIDAR: Towards Solving Large-Scale Cross-Modal Visual Localization

Niluthpol Chowdhury Mithun, Karan Sikka, Han-Pang Chiu +2

We study an important, yet largely unexplored problem of large-scale cross-modal visual localization by matching ground RGB images to a geo-referenced aerial LIDAR 3D point cloud (…

cs.CV2020

Deep Adaptive Semantic Logic (DASL): Compiling Declarative Knowledge into Deep Neural Networks

Karan Sikka, Andrew Silberfarb, John Byrnes +4

We introduce Deep Adaptive Semantic Logic (DASL), a novel framework for automating the generation of deep neural networks that incorporates user-provided formal knowledge to improv…