Curriculum Learning of Visual Attribute Clusters for Multi-Task Classification

TL;DR

This paper presents a novel curriculum learning approach for multi-task visual attribute classification, grouping correlated attributes into clusters to improve learning efficiency and accuracy in human-related image analysis.

Contribution

It introduces a hierarchical clustering-based method to organize attributes and applies curriculum learning to enhance multi-task classification performance.

Findings

Boosts classification accuracy by 4% to 10%.

Speeds up learning process through knowledge transfer.

Effective across various human attribute datasets.

Abstract

Visual attributes, from simple objects (e.g., backpacks, hats) to soft-biometrics (e.g., gender, height, clothing) have proven to be a powerful representational approach for many applications such as image description and human identification. In this paper, we introduce a novel method to combine the advantages of both multi-task and curriculum learning in a visual attribute classification framework. Individual tasks are grouped after performing hierarchical clustering based on their correlation. The clusters of tasks are learned in a curriculum learning setup by transferring knowledge between clusters. The learning process within each cluster is performed in a multi-task classification setup. By leveraging the acquired knowledge, we speed-up the process and improve performance. We demonstrate the effectiveness of our method via ablation studies and a detailed analysis of the covariates, on a variety of publicly available datasets of humans standing with their full-body visible. Extensive experimentation has proven that the proposed approach boosts the performance by 4% to 10%.