activity
20202024
most citedSubmodlib: A Submodular Optimization Library

6 citations · 30 across the 20 of their papers we have counts for

collaborators
Showing cs.CVShow all

8 papers · 1 filter

cs.CV2022

DIAGNOSE: Avoiding Out-of-distribution Data using Submodular Information Measures

Suraj Kothawade, Akshit Srivastava, Venkat Iyer +2

Avoiding out-of-distribution (OOD) data is critical for training supervised machine learning models in the medical imaging domain. Furthermore, obtaining labeled medical data is di…

cs.CV2022

CLINICAL: Targeted Active Learning for Imbalanced Medical Image Classification

Suraj Kothawade, Atharv Savarkar, Venkat Iyer +3

Training deep learning models on medical datasets that perform well for all classes is a challenging task. It is often the case that a suboptimal performance is obtained on some cl…

cs.CV2022

Counting in the 2020s: Binned Representations and Inclusive Performance Measures for Deep Crowd Counting Approaches

Sravya Vardhani Shivapuja, Ashwin Gopinath, Ayush Gupta +2

The data distribution in popular crowd counting datasets is typically heavy tailed and discontinuous. This skew affects all stages within the pipelines of deep crowd counting appro…

cs.CV2021

Wisdom of (Binned) Crowds: A Bayesian Stratification Paradigm for Crowd Counting

Sravya Vardhani Shivapuja, Mansi Pradeep Khamkar, Divij Bajaj +2

Datasets for training crowd counting deep networks are typically heavy-tailed in count distribution and exhibit discontinuities across the count range. As a result, the de facto st…

cs.CV20213 cited

Effective Evaluation of Deep Active Learning on Image Classification Tasks

Nathan Beck, Durga Sivasubramanian, Apurva Dani +2

With the goal of making deep learning more label-efficient, a growing number of papers have been studying active learning (AL) for deep models. However, there are a number of issue…

cs.CV2021

Select, Substitute, Search: A New Benchmark for Knowledge-Augmented Visual Question Answering

Aman Jain, Mayank Kothyari, Vishwajeet Kumar +3

Multimodal IR, spanning text corpus, knowledge graph and images, called outside knowledge visual question answering (OKVQA), is of much recent interest. However, the popular data s…