Deep regression models typically learn in an end-to-end fashion and do not explicitly try to learn a regression-aware representation. Their representations tend to be fragmented and …
Deep learning revolutionized data science, and recently its popularity has grown exponentially, as did the amount of papers employing deep networks. Vision tasks, such as …
W Dai, Y Du, H Bai, KT Cheng… - Advances in Neural …, 2023 - proceedings.neurips.cc
Contrastive learning methods can be applied to deep regression by enforcing label distance relationships in feature space. However, these methods are limited to labeled data only …
S Zhang, L Yang, MB Mi, X Zheng, A Yao - arXiv preprint arXiv …, 2023 - arxiv.org
In computer vision, it is often observed that formulating regression problems as a classification task often yields better performance. We investigate this curious phenomenon …
It is common within the deep learning community to first pre-train a deep neural network from a large-scale dataset and then fine-tune the pre-trained model to a specific downstream …
J Ma, S Fattahi - Advances in Neural Information Processing …, 2022 - proceedings.neurips.cc
This work characterizes the effect of depth on the optimization landscape of linear regression, showing that, despite their nonconvexity, deeper models have more desirable …
Representation learning that leverages large-scale labelled datasets, is central to recent progress in machine learning. Access to task relevant labels at scale is often scarce or …
Despite being able to capture a range of features of the data, high accuracy models trained with supervision tend to make similar predictions. This seemingly implies that high …
Many machine learning algorithms are trained and evaluated by splitting data from a single source into training and test sets. While such focus on in-distribution learning scenarios has …