Large language models (LLMs) have led to a series of breakthroughs in na...
Mixup is a regularization technique that artificially produces new sampl...
Deep Convolutional Neural Networks (CNNs) have long been the architectur...
Standard training techniques for neural networks involve multiple source...
Modern image retrieval systems increasingly rely on the use of deep neur...
The label shift problem refers to the supervised learning setting where ...
Modern retrieval problems are characterised by training sets with potent...
While stochastic gradient descent (SGD) is still the de facto algorithm ...
Semantic segmentation is a challenging vision problem that usually
neces...
Federated learning enables multiple participants to jointly construct a ...
Evaluation metrics for image captioning face two challenges. Firstly,
co...
Do convolutional networks really need a fixed feed-forward structure? Of...
The variety, abundance, and structured nature of hashtags make them an
i...
Deep neural networks trained on large supervised datasets have led to
im...
We present an approach to effectively use millions of images with noisy
...
In this work we propose a novel interpretation of residual networks show...
What makes images similar? To measure the similarity between images, the...
This paper describes the COCO-Text dataset. In recent years large-scale
...