Multipattern Mining Using Pattern-Level Contrastive Learning and Multipattern Activation Map

doi:10.1109/TNNLS.2022.3218073

Multipattern Mining Using Pattern-Level Contrastive Learning and Multipattern Activation Map

2024-07-01

0

PRE

AI

DOI：10.1109/TNNLS.2022.3218073

Original

Original request for help

Save

Abstract

En 中文

Visual patterns are basic elements in images and represent the discernible regularity in the visual world. Thus, mining visual patterns is a fundamental task in computer vision. Most previous studies consider that only one visual pattern exists in a category, and then builds up a one-to-one mapping using category label. In reality, however, many categories include multiple patterns, which are many-to-one mappings. Without knowing the information of patterns, few existing pattern mining methods can discover and distinguish varied patterns in a category. To tackle this problem, we propose a novel framework, PaclMap, which learns medium-grained features to represent patterns. It includes an unsupervised pattern-level contrastive learning and a multipattern activation map. Their joint optimization encourages the network to mine both discriminative and frequent patterns in a category. Extensive experiments conducted on four benchmark datasets (Place-20, imagenet large scale visual recognition challenge (ILSVRC)-20, visual object classes (VOC), and Travel) demonstrate that PaclMap outperforms six state-of-the-art methods with average improvements of 2.9% on accuracy and 12.3% on frequency, respectively.

Keywords:

Visualization

Feature extraction

Task analysis

Semantics

Convolutional neural networks

Optimization

Transforms

Joint optimization

multipattern activation map

multipattern mining

pattern-level contrastive learning

Multipattern Mining Using Pattern-Level Contrastive Learning and Multipattern Activation Map

Abstract

Journal

Organization