paper-with-me

홈 › Papers

Unsupervised Progressive Learning and the STAM Architecture

2019-04-03 · James Smith, Cameron Taylor, Seth Baer, Constantine Dovrolis

We first pose the Unsupervised Progressive Learning (UPL) problem: an online representation learning problem in which the learner observes a non-stationary and unlabeled data stream, learning a growing number of features that persist over time even though the data is not stored or replayed. To solve the UPL problem we propose the Self-Taught Associative Memory (STAM) architecture. Layered hierarchies of STAM modules learn based on a combination of online clustering, novelty detection, forgetting outliers, and storing only prototypical features rather than specific examples. We evaluate STAM representations using clustering and classification tasks. While there are no existing learning scenarios that are directly comparable to UPL, we compare the STAM architecture with two recent continual learning models, Memory Aware Synapses (MAS) and Gradient Episodic Memories (GEM), after adapting them in the UPL setting.

📄 PDF Abstract BibTeX arXiv:1904.02021

Code (1)

CameronTaylorFL/stam 공식 구현 pytorch

Tasks

ClusteringContinual LearningNovelty DetectionOnline ClusteringRepresentation Learning

Similar Papers 제목 키워드 기반

A neuro-inspired architecture for unsupervised continual learning based on online clustering and hierarchical predictive coding

2018-10-22 · Constantine Dovrolis

We propose that the Continual Learning desiderata can be achieved through a neuro-inspired architecture, grounded on Mountcastle's cortical column hypothesis. The proposed architecture involves a single module, called Se…

ClusteringContinual LearningOnline Clustering

Unsupervised Continual Learning and Self-Taught Associative Memory Hierarchies

2019-03-24 · ICLR Workshop LLD 2019 · James Smith, Seth Baer, Zsolt Kira, Constantine Dovrolis

We first pose the Unsupervised Continual Learning (UCL) problem: learning salient representations from a non-stationary stream of unlabeled data in which the number of object classes varies with time. Given limited label…

Continual LearningOnline Clustering

StampNet: unsupervised multi-class object discovery

2019-02-07 · Joost Visser, Alessandro Corbetta, Vlado Menkovski, Federico Toschi

Unsupervised object discovery in images involves uncovering recurring patterns that define objects and discriminates them against the background. This is more challenging than image clustering as the size and the locatio…

ClusteringImage ClusteringObjectObject Discovery

Stamp processing with examplar features

2016-09-16 · Yash Bhalgat, Mandar Kulkarni, Shirish Karande, Sachin Lodha

Document digitization is becoming increasingly crucial. In this work, we propose a shape based approach for automatic stamp verification/detection in document images using an unsupervised feature learning. Given a small …

Clustering

Reducing the Label Bias for Timestamp Supervised Temporal Action Segmentation

2023-01-01 · CVPR 2023 1 · Kaiyuan Liu, Yunheng Li, Shenglan Liu, Chenwei Tan 외

Timestamp supervised temporal action segmentation (TSTAS) is more cost-effective than fully supervised counterparts. However, previous approaches suffer from severe label bias due to over-reliance on sparse timestamp…

Action SegmentationTemporal Action Segmentation