Pre-trained foundation models, owing primarily to their enormous capacit...
The current approach for testing the robustness of object detectors suff...
Transformers for graph data are increasingly widely studied and successf...
In image classification, a lot of development has happened in detecting
...
Following the surge of popularity of Transformers in Computer Vision, se...
It is now well known that neural networks can be wrong with high confide...
We show that the effectiveness of the well celebrated Mixup [Zhang et al...
Despite clear computational advantages in building robust neural network...
Recently, Wong et al. showed that adversarial training with single-step ...
Randomized smoothing has recently emerged as an effective tool that enab...
There has been increasing interest in building deep hierarchy-aware
clas...
We study batch normalisation in the context of variational inference met...
In continual learning (CL), a learner is faced with a sequence of tasks,...
Recurrent models are becoming a popular choice for video enhancement tas...
We investigate two causes for adversarial vulnerability in deep neural
n...
Recent studies have shown that skeletonization (pruning parameters) of
n...
Evaluating Visual Dialogue, the task of answering a sequence of question...
Miscalibration – a mismatch between a model's confidence and its correct...
In continual learning, the learner faces a stream of data whose distribu...
Quantizing large Neural Networks (NN) while maintaining the performance ...
Arnab Ghosh 6:32 PM We propose an interactive GAN-based sketch-to-image
...
Exciting new work on the generalization bounds for neural networks (NN) ...
Learning with less supervision is a major challenge in artificial
intell...
We characterise some of the quirks and shortcomings in the exploration o...
Compressing large neural networks by quantizing the parameters, while
ma...
Deformable registration has been one of the pillars of biomedical image
...
We study the incremental learning problem for the classification task, a...
We propose a novel weakly supervised discriminative algorithm for learni...
We propose an approach to discover class-specific pixels for the
weakly-...
This paper describes an intuitive generalization to the Generative
Adver...
In this paper, we propose several improvements on the block-coordinate
F...
We propose a new family of discrete energy minimization problems, which ...