Coincidence, Categorization, and Consolidation: Learning to Recognize Sounds with Minimal Supervision
원문 초록
Humans do not acquire perceptual abilities in the way we train machines. While machine learning algorithms typically operate on large collections of randomly-chosen, explicitly-labeled examples, human acquisition relies more heavily on multimodal unsupervised learning (as infants) and active learning (as children). With this motivation, we present a learning framework for sound representation and recognition that combines (i) a self-supervised objective based on a general notion of unimodal and cross-modal coincidence, (ii) a clustering objective that reflects our need to impose categorical structure on our experiences, and (iii) a cluster-based active learning procedure that solicits targeted weak supervision to consolidate categories into relevant semantic classes. By training a combined sound embedding/clustering/classification network according to these criteria, we achieve a new state-of-the-art unsupervised audio representation and demonstrate up to a 20-fold reduction in the number of labels required to reach a desired classification performance.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Wide Contextual Residual Network with Active Learning for Remote Sensing Image Classification
CNTK: Microsoft's Open-Source Deep-Learning Toolkit
GraRep: Learning Graph Representations with Global Structural Information
Chainer: a Next-Generation Open Source Framework for Deep Learning
Tri-Learn Graph Fusion Network for Attributed Graph Clustering
Car Object Counting and Position Estimation via Extension of the CLIP-EBC Framework
토론
이 논문과 연결된 포럼 글이 아직 없습니다.