activity
20182022
most citedDeep Deterministic Uncertainty for Semantic Segmentation

13 citations · 19 across the 5 of their papers we have counts for

collaborators

8 papers

cs.CV2022

Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning

Jishnu Mukhoti, Tsung-Yu Lin, Omid Poursaeed +4

We introduce Patch Aligned Contrastive Learning (PACL), a modified compatibility function for CLIP's contrastive loss, intending to train an alignment between the patch tokens of t…

cs.CV20221 cited

Raising the Bar on the Evaluation of Out-of-Distribution Detection

Jishnu Mukhoti, Tsung-Yu Lin, Bor-Chun Chen +4

In image classification, a lot of development has happened in detecting out-of-distribution (OoD) data. However, most OoD detection methods are evaluated on a standard set of datas…

cs.CV202113 cited

Deep Deterministic Uncertainty for Semantic Segmentation

Jishnu Mukhoti, Joost van Amersfoort, Philip H. S. Torr +1

We extend Deep Deterministic Uncertainty (DDU), a method for uncertainty estimation using feature space densities, to semantic segmentation. DDU enables quantifying and disentangli…

cs.LG20204 cited

On Batch Normalisation for Approximate Bayesian Inference

Jishnu Mukhoti, Puneet K. Dokania, Philip H. S. Torr +1

We study batch normalisation in the context of variational inference methods in Bayesian neural networks, such as mean-field or MC Dropout. We show that batch-normalisation does no…

cs.LG2020

Calibrating Deep Neural Networks using Focal Loss

Jishnu Mukhoti, Viveka Kulharia, Amartya Sanyal +3

Miscalibration - a mismatch between a model's confidence and its correctness - of Deep Neural Networks (DNNs) makes their predictions hard to rely on. Ideally, we want networks to…

cs.CV20191 cited

Let's Take This Online: Adapting Scene Coordinate Regression Network Predictions for Online RGB-D Camera Relocalisation

Tommaso Cavallari, Luca Bertinetto, Jishnu Mukhoti +2

Many applications require a camera to be relocalised online, without expensive offline training on the target scene. Whilst both keyframe and sparse keypoint matching methods can b…