Zobrazeno 1 - 10
of 92
pro vyhledávání: '"McDonagh, Steven"'
Autor:
Ericsson, Linus, Espinosa, Miguel, Yang, Chenhongyi, Antoniou, Antreas, Storkey, Amos, Cohen, Shay B., McDonagh, Steven, Crowley, Elliot J.
Neural architecture search (NAS) finds high performing networks for a given task. Yet the results of NAS are fairly prosaic; they did not e.g. create a shift from convolutional structures to transformers. This is not least because the search spaces i
Externí odkaz:
http://arxiv.org/abs/2405.20838
Machine unlearning is a promising paradigm for removing unwanted data samples from a trained model, towards ensuring compliance with privacy regulations and limiting harmful biases. Although unlearning has been shown in, e.g., classification and reco
Externí odkaz:
http://arxiv.org/abs/2405.15517
Autor:
Tudosiu, Petru-Daniel, Yang, Yongxin, Zhang, Shifeng, Chen, Fei, McDonagh, Steven, Lampouras, Gerasimos, Iacobacci, Ignacio, Parisot, Sarah
Text-to-image generation has achieved astonishing results, yet precise spatial controllability and prompt fidelity remain highly challenging. This limitation is typically addressed through cumbersome prompt engineering, scene layout conditioning, or
Externí odkaz:
http://arxiv.org/abs/2404.02790
Deep neural networks have become a standard building block for designing models that can perform multiple dense computer vision tasks such as depth estimation and semantic segmentation thanks to their ability to capture complex correlations in high d
Externí odkaz:
http://arxiv.org/abs/2310.00986
Large scale vision and language models can achieve impressive zero-shot recognition performance by mapping class specific text queries to image content. Two distinct challenges that remain however, are high sensitivity to the choice of handcrafted cl
Externí odkaz:
http://arxiv.org/abs/2304.01830
Behavior of neural networks is irremediably determined by the specific loss and data used during training. However it is often desirable to tune the model at inference time based on external factors such as preferences of the user or dynamic characte
Externí odkaz:
http://arxiv.org/abs/2304.00898
Self-supervised pre-training, based on the pretext task of instance discrimination, has fueled the recent advance in label-efficient object detection. However, existing studies focus on pre-training only a feature extractor network to learn transfera
Externí odkaz:
http://arxiv.org/abs/2211.09022
Image quality assessment (IQA) forms a natural and often straightforward undertaking for humans, yet effective automation of the task remains highly challenging. Recent metrics from the deep learning community commonly compare image pairs during trai
Externí odkaz:
http://arxiv.org/abs/2211.05215
Autor:
Verwimp, Eli, Yang, Kuo, Parisot, Sarah, Lanqing, Hong, McDonagh, Steven, Pérez-Pellitero, Eduardo, De Lange, Matthias, Tuytelaars, Tinne
In this paper we describe the design and the ideas motivating a new Continual Learning benchmark for Autonomous Driving (CLAD), that focuses on the problems of object classification and object detection. The benchmark utilises SODA10M, a recently rel
Externí odkaz:
http://arxiv.org/abs/2210.03482
Density-based Out-of-distribution (OOD) detection has recently been shown unreliable for the task of detecting OOD images. Various density ratio based approaches achieve good empirical performance, however methods typically lack a principled probabil
Externí odkaz:
http://arxiv.org/abs/2206.03955