Unsupervised sound localization via iterative contrastive learning
نویسندگان
چکیده
منابع مشابه
Iterative Spectral Clustering for Unsupervised Object Localization
This paper addresses the problem of unsupervised object localization in an image. Unlike previous supervised and weakly supervised algorithms that require bounding box or image level annotations for training classifiers in order to learn features representing the object, we propose a simple yet effective technique for localization using iterative spectral clustering. This iterative spectral clu...
متن کاملIterative Spatial Probability Based Sound Localization
A two-dimensional sound localization system using an iterative spatial probability (ISP) algorithm is proposed. With the ISP algorithm, sound signals from two microphones are iteratively crosscorrelated and the time index of the strongest correlation is recorded in a histogram. This information is then used to create a spatial probability map, which makes it possible to accommodate any number o...
متن کاملUnsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA
Nonlinear independent component analysis (ICA) provides an appealing framework for unsupervised feature learning, but the models proposed so far are not identifiable. Here, we first propose a new intuitive principle of unsupervised deep learning from time series which uses the nonstationary structure of the data. Our learning principle, time-contrastive learning (TCL), finds a representation wh...
متن کاملGuiding Unsupervised Grammar Induction Using Contrastive Estimation∗
We describe a novel training criterion for probabilistic grammar induction models, contrastive estimation [Smith and Eisner, 2005], which can be interpreted as exploiting implicit negative evidence and includes a wide class of likelihood-based objective functions. This criterion is a generalization of the function maximized by the ExpectationMaximization algorithm [Dempster et al., 1977]. CE is...
متن کاملDeep Unsupervised Domain Adaptation for Image Classification via Low Rank Representation Learning
Domain adaptation is a powerful technique given a wide amount of labeled data from similar attributes in different domains. In real-world applications, there is a huge number of data but almost more of them are unlabeled. It is effective in image classification where it is expensive and time-consuming to obtain adequate label data. We propose a novel method named DALRRL, which consists of deep ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Computer Vision and Image Understanding
سال: 2023
ISSN: ['1090-235X', '1077-3142']
DOI: https://doi.org/10.1016/j.cviu.2022.103602