147 citations · 297 across the 10 of their papers we have counts for
10 papers
Fine-tuning can cripple your foundation model; preserving features may be the solution
Jishnu Mukhoti, Yarin Gal, Philip H. S. Torr +1
Pre-trained foundation models, due to their enormous capacity and exposure to vast amounts of data during pre-training, are known to have learned plenty of real-world concepts. An…
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…
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…
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…
Deep Deterministic Uncertainty: A Simple Baseline
Jishnu Mukhoti, Andreas Kirsch, Joost van Amersfoort +2
Reliable uncertainty from deterministic single-forward pass models is sought after because conventional methods of uncertainty quantification are computationally expensive. We take…
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…
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…
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…
On the Importance of Strong Baselines in Bayesian Deep Learning
Jishnu Mukhoti, Pontus Stenetorp, Yarin Gal
Like all sub-fields of machine learning Bayesian Deep Learning is driven by empirical validation of its theoretical proposals. Given the many aspects of an experiment it is always…
Evaluating Bayesian Deep Learning Methods for Semantic Segmentation
Jishnu Mukhoti, Yarin Gal
Deep learning has been revolutionary for computer vision and semantic segmentation in particular, with Bayesian Deep Learning (BDL) used to obtain uncertainty maps from deep models…