Zobrazeno 1 - 10
of 357
pro vyhledávání: '"Bennett, Adam P."'
Iterative algorithms solve problems by taking steps until a solution is reached. Models in the form of Deep Thinking (DT) networks have been demonstrated to learn iterative algorithms in a way that can scale to different sized problems at inference t
Externí odkaz:
http://arxiv.org/abs/2410.23451
Deep learning models such as convolutional neural networks and transformers have been widely applied to solve 3D object detection problems in the domain of autonomous driving. While existing models have achieved outstanding performance on most open b
Externí odkaz:
http://arxiv.org/abs/2408.12708
The diffusion of deepfake technologies has sparked serious concerns about its potential misuse across various domains, prompting the urgent need for robust detection methods. Despite advancement, many current approaches prioritize short-term gains at
Externí odkaz:
http://arxiv.org/abs/2408.08412
The performance of domain adaptation technologies has not yet reached an ideal level in the current 3D object detection field for autonomous driving, which is mainly due to significant differences in the size of vehicles, as well as the environments
Externí odkaz:
http://arxiv.org/abs/2407.04061
Semantic segmentation is a critical task in computer vision aiming to identify and classify individual pixels in an image, with numerous applications in for example autonomous driving and medical image analysis. However, semantic segmentation can be
Externí odkaz:
http://arxiv.org/abs/2305.15608
In this paper we show that the expected generalisation performance of a learning machine is determined by the distribution of risks or equivalently its logarithm -- a quantity we term the risk entropy -- and the fluctuations in a quantity we call the
Externí odkaz:
http://arxiv.org/abs/2202.07350
The optimisation of neural networks can be sped up by orthogonalising the gradients before the optimisation step, ensuring the diversification of the learned representations. We orthogonalise the gradients of the layer's components/filters with respe
Externí odkaz:
http://arxiv.org/abs/2202.07052
Autor:
Marcu, Antonia, Prügel-Bennett, Adam
The community lacks theory-informed guidelines for building good data sets. We analyse theoretical directions relating to what aspects of the data matter and conclude that the intuitions derived from the existing literature are incorrect and misleadi
Externí odkaz:
http://arxiv.org/abs/2111.11514
Autor:
Marcu, Antonia, Prügel-Bennett, Adam
Data distortion is commonly applied in vision models during both training (e.g methods like MixUp and CutMix) and evaluation (e.g. shape-texture bias and robustness). This data modification can introduce artificial information. It is often assumed th
Externí odkaz:
http://arxiv.org/abs/2110.13968
Publikováno v:
Field Robotics 2 (2022) 1134-1155
This paper describes Georeference Contrastive Learning of visual Representation (GeoCLR) for efficient training of deep-learning Convolutional Neural Networks (CNNs). The method leverages georeference information by generating a similar image pair us
Externí odkaz:
http://arxiv.org/abs/2108.06421