Feature dimensionality reduction: a review
W Jia, M Sun, J Lian, S Hou - Complex & Intelligent Systems, 2022 - Springer
As basic research, it has also received increasing attention from people that the “curse of
dimensionality” will lead to increase the cost of data storage and computing; it also …
dimensionality” will lead to increase the cost of data storage and computing; it also …
Towards the next generation of machine learning models in additive manufacturing: A review of process dependent material evolution
Additive manufacturing facilitates producing of complex parts due to its design freedom in a
wide range of applications. Despite considerable advancements in additive manufacturing …
wide range of applications. Despite considerable advancements in additive manufacturing …
Content-aware local gan for photo-realistic super-resolution
Recently, GAN has successfully contributed to making single-image super-resolution (SISR)
methods produce more realistic images. However, natural images have complex distribution …
methods produce more realistic images. However, natural images have complex distribution …
Contrastive and non-contrastive self-supervised learning recover global and local spectral embedding methods
R Balestriero, Y LeCun - Advances in Neural Information …, 2022 - proceedings.neurips.cc
Abstract Self-Supervised Learning (SSL) surmises that inputs and pairwise positive
relationships are enough to learn meaningful representations. Although SSL has recently …
relationships are enough to learn meaningful representations. Although SSL has recently …
Declutr: Deep contrastive learning for unsupervised textual representations
Sentence embeddings are an important component of many natural language processing
(NLP) systems. Like word embeddings, sentence embeddings are typically learned on large …
(NLP) systems. Like word embeddings, sentence embeddings are typically learned on large …
Learning causally invariant representations for out-of-distribution generalization on graphs
Despite recent success in using the invariance principle for out-of-distribution (OOD)
generalization on Euclidean data (eg, images), studies on graph data are still limited …
generalization on Euclidean data (eg, images), studies on graph data are still limited …
Multi-similarity loss with general pair weighting for deep metric learning
A family of loss functions built on pair-based computation have been proposed in the
literature which provide a myriad of solutions for deep metric learning. In this pa-per, we …
literature which provide a myriad of solutions for deep metric learning. In this pa-per, we …
Negative margin matters: Understanding margin in few-shot classification
This paper introduces a negative margin loss to metric learning based few-shot learning
methods. The negative margin loss significantly outperforms regular softmax loss, and …
methods. The negative margin loss significantly outperforms regular softmax loss, and …
Deep domain generalization via conditional invariant adversarial networks
Abstract Domain generalization aims to learn a classification model from multiple source
domains and generalize it to unseen target domains. A critical problem in domain …
domains and generalize it to unseen target domains. A critical problem in domain …
Fakecatcher: Detection of synthetic portrait videos using biological signals
The recent proliferation of fake portrait videos poses direct threats on society, law, and
privacy [1]. Believing the fake video of a politician, distributing fake pornographic content of …
privacy [1]. Believing the fake video of a politician, distributing fake pornographic content of …