5 citations · 9 across the 7 of their papers we have counts for
7 papers
Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models
Peter Robicheaux, Matvei Popov, Anish Madan +4
Vision-language models (VLMs) trained on internet-scale data achieve remarkable zero-shot detection performance on common objects like car, truck, and pedestrian. However, state-of…
SMORE: Simultaneous Map and Object REconstruction
Nathaniel Chodosh, Anish Madan, Simon Lucey +1
We present a method for dynamic surface reconstruction of large-scale urban scenes from LiDAR. Depth-based reconstructions tend to focus on small-scale objects or large-scale SLAM…
NurtureNet: A Multi-task Video-based Approach for Newborn Anthropometry
Yash Khandelwal, Mayur Arvind, Sriram Kumar +17
Malnutrition among newborns is a top public health concern in developing countries. Identification and subsequent growth monitoring are key to successful interventions. However, th…
Revisiting Few-Shot Object Detection with Vision-Language Models
Anish Madan, Neehar Peri, Shu Kong +1
The era of vision-language models (VLMs) trained on web-scale datasets challenges conventional formulations of "open-world" perception. In this work, we revisit the task of few-sho…
B-SMALL: A Bayesian Neural Network approach to Sparse Model-Agnostic Meta-Learning
Anish Madan, Ranjitha Prasad
There is a growing interest in the learning-to-learn paradigm, also known as meta-learning, where models infer on new tasks using a few training examples. Recently, meta-learning b…
REGroup: Rank-aggregating Ensemble of Generative Classifiers for Robust Predictions
Lokender Tiwari, Anish Madan, Saket Anand +1
Deep Neural Networks (DNNs) are often criticized for being susceptible to adversarial attacks. Most successful defense strategies adopt adversarial training or random input transfo…
C3VQG: Category Consistent Cyclic Visual Question Generation
Shagun Uppal, Anish Madan, Sarthak Bhagat +2
Visual Question Generation (VQG) is the task of generating natural questions based on an image. Popular methods in the past have explored image-to-sequence architectures trained wi…