10 citations · 29 across the 8 of their papers we have counts for
6 papers · 1 filter
Discovering Failure Modes in Vision-Language Models using RL
Kanishk Jain, Qian Yang, Shravan Nayak +3
Vision-language Models (VLMs), despite achieving strong performance on multimodal benchmarks, often misinterpret straightforward visual concepts that humans identify effortlessly,…
Test-Time Amendment with a Coarse Classifier for Fine-Grained Classification
Kanishk Jain, Shyamgopal Karthik, Vineet Gandhi
We investigate the problem of reducing mistake severity for fine-grained classification. Fine-grained classification can be challenging, mainly due to the requirement of domain exp…
Ground then Navigate: Language-guided Navigation in Dynamic Scenes
Kanishk Jain, Varun Chhangani, Amogh Tiwari +2
We investigate the Vision-and-Language Navigation (VLN) problem in the context of autonomous driving in outdoor settings. We solve the problem by explicitly grounding the navigable…
Grounding Linguistic Commands to Navigable Regions
Nivedita Rufus, Kanishk Jain, Unni Krishnan R Nair +2
Humans have a natural ability to effortlessly comprehend linguistic commands such as "park next to the yellow sedan" and instinctively know which region of the road the vehicle sho…
Bringing Generalization to Deep Multi-View Pedestrian Detection
Jeet Vora, Swetanjal Dutta, Kanishk Jain +2
Multi-view Detection (MVD) is highly effective for occlusion reasoning in a crowded environment. While recent works using deep learning have made significant advances in the field,…
Comprehensive Multi-Modal Interactions for Referring Image Segmentation
Kanishk Jain, Vineet Gandhi
We investigate Referring Image Segmentation (RIS), which outputs a segmentation map corresponding to the natural language description. Addressing RIS efficiently requires consideri…