NEWSLETTER
Towards the automatic evaluation of self-supervised speech models using rank
This study explores the use of the ranking rank as a non-supervised evaluation metric for general-use speech-use coders trained through ...
Tag: Selfsupervised
PyG-SSL – An open source library for self-supervised learning of graphs and supports various scientific computing and deep learning backends
Complex domains such as social networks, molecular biology, and recommender systems have data structured in graphs consisting of nodes, edges, ...
No train, all gain: Improving frozen representations with self-supervised gradients.
A central challenge in advancing deep learning-based classification and retrieval tasks is achieving robust representations without the need for extensive ...
Is it possible to eliminate the top-down model for speaker recognition with self-supervised speech features?
Self-supervised features are typically used instead of filterbank features in speech verification models. However, these models were originally designed to ...
From MOCO v1 to v3: Towards building a dynamic dictionary for self-supervised learning — Part 1 | by Mengliu Zhao | Jul, 2024
A brief overview of the boost contrast learning frameworkHave we reached the era of self-supervised learning?Data flows every day. People ...
AI research from UC Berkeley and NYU explores gap between visual clip embedding space and vision-only self-supervised learning
MLLMs, or multimodal large language models, have been making strides lately. By incorporating images into large language models (LLMs) and ...
SeMAnD: Self-supervised anomaly detection in multimodal geospatial datasets
*= Equal taxpayers We propose a self-supervised anomaly detection technique, called SeMAnD, to detect geometric anomalies in multimodal geospatial datasets. ...
Recommended.
