# Curriculum Learning of Visual Attribute Clusters for Multi-Task Classification

arXiv: https://arxiv.org/abs/1709.06664 · HTML: https://mlsanity.com/paper/1709.06664/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Sep 2017.

## Built on by (most cited first, 8 of 8)

- [Uncertainty-Aware Unsupervised Domain Adaptation in Object Detection](https://mlsanity.com/paper/2103.00236/) (2021)
- [Coarse-to-Fine Curriculum Learning](https://mlsanity.com/paper/2106.04072/) (2021)
- [Asynchronous Curriculum Experience Replay: A Deep Reinforcement Learning Approach for UAV Autonomous Motion Control in Unknown Dynamic Environments](https://mlsanity.com/paper/2207.01251/) (2022)
- [Medical Knowledge-Guided Deep Curriculum Learning for Elbow Fracture Diagnosis from X-Ray Images](https://mlsanity.com/paper/2110.10381/) (2021)
- [Less Emphasis on Difficult Layer Regions: Curriculum Learning for Singularly Perturbed Convection-Diffusion-Reaction Problems](https://mlsanity.com/paper/2210.12685/) (2022)
- [Data Distribution-based Curriculum Learning](https://mlsanity.com/paper/2402.07352/) (2024)
- [Human not in the loop: objective sample difficulty measures for Curriculum Learning](https://mlsanity.com/paper/2302.01243/) (2023)
- [Directed Link Prediction using GNN with Local and Global Feature Fusion](https://mlsanity.com/paper/2506.20235/) (2025)

## Abstract (arXiv)

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%.