Successive Subspace Learning: An Overview

Rouhsedaghat, Mozhdeh; Monajatipoor, Masoud; Azizi, Zohreh; Kuo, C.‐C. Jay

doi:10.48550/arxiv.2103.00121

Cited by 5 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Successive subspace learning (SSL) was recently introduced in [19,20,21,22]. The technique has been applied to many applications such as point cloud classification, segmentation and registration [23,24,25,26,27], face recognition [28,29], deepfake detection [30], anomaly detection [31], etc. SSL-based object classification work can be found in [32,33,34].…”

Section: Design Of Learning Systems With Ssl Featuresmentioning

confidence: 99%

Design of Supervision-Scalable Learning Systems: Methodology and Performance Benchmarking

Yang¹,

Huang²,

Kuo³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

The design of robust learning systems that offer stable performance under a wide range of supervision degrees is investigated in this work. We choose the image classification problem as an illustrative example and focus on the design of modularized systems that consist of three learning modules: representation learning, feature learning and decision learning. We discuss ways to adjust each module so that the design is robust with respect to different training sample numbers. Based on these ideas, we propose two families of learning systems. One adopts the classical histogram of oriented gradients (HOG) features while the other uses successive-subspace-learning (SSL) features. We test their performance against LeNet-5, which is an end-to-end optimized neural network, for MNIST and Fashion-MNIST datasets. The number of training samples per image class goes from the extremely weak supervision condition (i.e., 1 labeled sample per class) to the strong supervision condition (i.e., 4096 labeled sample per class) with gradual transition in between (i.e., 2 n , n = 0, 1, • • • , 12). Experimental results show that the two families of modularized learning systems have more robust performance than LeNet-5. They both outperform LeNet-5 by a large margin for small n and have performance comparable with that of LeNet-5 for large n.

show abstract

Section: Design Of Learning Systems With Ssl Featuresmentioning

confidence: 99%

Design of Supervision-Scalable Learning Systems: Methodology and Performance Benchmarking

Yang¹,

Huang²,

Kuo³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…SSL and Its Applications. SSL is an emerging machine learning technique developed by Kuo et al in recent years [17], [18], [19], [20], [21]. It has been applied to quite a few applications with impressive performance.…”

Section: Related Workmentioning

confidence: 99%

AnomalyHop: An SSL-based Image Anomaly Localization Method

Zhang

Wang²,

Wang³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

An image anomaly localization method based on the successive subspace learning (SSL) framework, called Anomaly-Hop, is proposed in this work. AnomalyHop consists of three modules: 1) feature extraction via successive subspace learning (SSL), 2) normality feature distributions modeling via Gaussian models, and 3) anomaly map generation and fusion. Comparing with state-of-the-art image anomaly localization methods based on deep neural networks (DNNs), AnomalyHop is mathematically transparent, easy to train, and fast in its inference speed. Besides, its area under the ROC curve (ROC-AUC) performance on the MVTec AD dataset is 95.9%, which is among the best of several benchmarking methods. 1

show abstract

“…One emerging alternative is successive subspace learning [18,[68][69][70][71]113]. Simply speaking, SSL is a lightweight unsupervised data embedding (or feature learning) method and it can be applied to different data types (e.g.…”

Section: A) Interpretable and Modularized Learningmentioning

confidence: 99%

Bridging Gap between Image Pixels and Semantics via Supervision: A Survey

Duan¹,

Kuo²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

The fact that there exists a gap between low-level features and semantic meanings of images, called the semantic gap, is known for decades. Resolution of the semantic gap is a long standing problem. The semantic gap problem is reviewed and a survey on recent efforts in bridging the gap is made in this work. Most importantly, we claim that the semantic gap is primarily bridged through supervised learning today. Experiences are drawn from two application domains to illustrate this point: 1) object detection and 2) metric learning for content-based image retrieval (CBIR). To begin with, this paper offers a historical retrospective on supervision, makes a gradual transition to the modern data-driven methodology and introduces commonly used datasets. Then, it summarizes various supervision methods to bridge the semantic gap in the context of object detection and metric learning.

show abstract

Successive Subspace Learning: An Overview

Cited by 5 publications

References 0 publications

Design of Supervision-Scalable Learning Systems: Methodology and Performance Benchmarking

Design of Supervision-Scalable Learning Systems: Methodology and Performance Benchmarking

AnomalyHop: An SSL-based Image Anomaly Localization Method

Bridging Gap between Image Pixels and Semantics via Supervision: A Survey

Contact Info

Product

Resources

About