Noisy recognition of perceptual mid-level features in music
Self-training with noisy student is a consistency-based semi-supervised self- training method that achieved state-of-the-art accuracy on ImageNet image classification upon its release. It makes use of data noise and model noise when fitting a model to both labelled data and a large amount of artific...
Main Author: | Mossmyr, Simon |
---|---|
Format: | Others |
Language: | English |
Published: |
KTH, Skolan för elektroteknik och datavetenskap (EECS)
2021
|
Subjects: | |
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-294229 |
Similar Items
-
How Musical Instrumentation Affects Perceptual Identification of Musical Genres
by: Brene, Sofia, et al.
Published: (2014) -
Using unsupervised classification with multiple LDA derived models for text generation based on noisy and sensitive data
by: Ljungberg, Lucas
Published: (2019) -
Narrative music: towards an understanding of musical narrative functions in multimedia
by: Wingstedt, Johnny
Published: (2005) -
Constraint-Based Activity Recognition with Uncertainty
by: Mansouri, Masoumeh
Published: (2011) -
Dissection of a Generative Network for Music Composition
by: Brink, Pontus
Published: (2019)