Perceptual Visual Interactive Learning

TL;DR

This paper introduces a perceptual visual interactive learning framework that leverages human perception and computer analysis to improve labeling accuracy and efficiency in machine learning, especially with limited labeled data.

Contribution

It proposes a novel PVIL framework combining gestalt principles and MDR for enhanced interactive learning, bridging perception and cognition in visual tasks.

Findings

PVIL outperforms traditional labeling methods in accuracy.

PVIL achieves higher efficiency in labeling dense and sparse datasets.

Experimental results demonstrate the framework's superiority in classification tasks.

Abstract

Supervised learning methods are widely used in machine learning. However, the lack of labels in existing data limits the application of these technologies. Visual interactive learning (VIL) compared with computers can avoid semantic gap, and solve the labeling problem of small label quantity (SLQ) samples in a groundbreaking way. In order to fully understand the importance of VIL to the interaction process, we re-summarize the interactive learning related algorithms (e.g. clustering, classification, retrieval etc.) from the perspective of VIL. Note that, perception and cognition are two main visual processes of VIL. On this basis, we propose a perceptual visual interactive learning (PVIL) framework, which adopts gestalt principle to design interaction strategy and multi-dimensionality reduction (MDR) to optimize the process of visualization. The advantage of PVIL framework is that it combines computer's sensitivity of detailed features and human's overall understanding of global tasks. Experimental results validate that the framework is superior to traditional computer labeling methods (such as label propagation) in both accuracy and efficiency, which achieves significant classification results on dense distribution and sparse classes dataset.