Search Results for author:
Found 17 papers, 5 papers with code
On The Specialization of Neural Modules
Our results shed light on the difficulty of module specialization, what is required for modules to successfully specialize, and the necessity of modular architectures to achieve systematicity.
A Large-scale Evaluation of Pretraining Paradigms for the Detection of Defects in Electroluminescence Solar Cell Images
Additionally, we provide a large-scale unlabelled EL image dataset of $22000$ images, and a $642$-image labelled semantic segmentation EL dataset, for further research in developing self- and semi-supervised training techniques in this domain.
DeepSet SimCLR: Self-supervised deep sets for improved pathology representation learning
Often, applications of self-supervised learning to 3D medical data opt to use 3D variants of successful 2D network architectures.
Affine transformation estimation improves visual self-supervised learning
The standard approach to modern self-supervised learning is to generate random views through data augmentations and minimise a loss computed from the representations of these views.
Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies
To this end, we introduce a neural network architecture, the Decision Adapter, which generates the weights of an adapter module and conditions the behaviour of an agent on the context information.
On the robustness of self-supervised representations for multi-view object classification
It is known that representations from self-supervised pre-training can perform on par, and often better, on various downstream tasks than representations from fully-supervised pre-training.
Accounting for the Sequential Nature of States to Learn Features for Reinforcement Learning
In this work, we investigate the properties of data that cause popular representation learning approaches to fail.
Overlooked Implications of the Reconstruction Loss for VAE Disentanglement
Our findings demonstrate the subjective nature of disentanglement and the importance of considering the interaction between the ground-truth factors, data and notably, the reconstruction loss, which is under-recognised in the literature.
Improving Pose Estimation through Contextual Activity Fusion
This research presents the idea of activity fusion into existing Pose Estimation architectures to enhance their predictive ability.
Generative Adversarial Networks for Non-Raytraced Global Illumination on Older GPU Hardware
We give an overview of the different rendering methods and we demonstrate that the use of a Generative Adversarial Networks (GAN) for Global Illumination (GI) gives a superior quality rendered image to that of a rasterisations image.
The Role of Learning Regime, Architecture and Dataset Structure on Systematic Generalization in Simple Neural Networks
We introduce a minimal space of datasets with systematic and non-systematic features in both the input and output.
Automated Parking Space Detection Using Convolutional Neural Networks
Those bounding box coordinates are saved from a frame of the video of the parking lot in a JSON format, to be later used by the system for sequential prediction on each parking spot.
Confident in the Crowd: Bayesian Inference to Improve Data Labelling in Crowdsourcing
The naive approach to assigning labels is to adopt a majority vote method, however, in the context of data labelling, this is not always ideal as data labellers are not equally reliable.
The Wits Intelligent Teaching System: Detecting Student Engagement During Lectures Using Convolutional Neural Networks
To perform contingent teaching and be responsive to students' needs during class, lecturers must be able to quickly assess the state of their audience.
Explicit homography estimation improves contrastive self-supervised learning
We show how the inclusion of this module to regress the parameters of an affine transformation or homography, in addition to the original contrastive objective, improves both performance and learning speed.
Quantisation and Pruning for Neural Network Compression and Regularisation
Deep neural networks are typically too computationally expensive to run in real-time on consumer-grade hardware and low-powered devices.
Ranked #1 on
Neural Network Compression
on CIFAR-10
Using Objective Bayesian Methods to Determine the Optimal Degree of Curvature within the Loss Landscape
The efficacy of the width of the basin of attraction surrounding a minimum in parameter space as an indicator for the generalizability of a model parametrization is a point of contention surrounding the training of artificial neural networks, with the dominant view being that wider areas in the landscape reflect better generalizability by the trained model.
