# Active Self-Paced Learning for Cost-Effective and Progressive Face Identification

arXiv: https://arxiv.org/abs/1701.03555 · HTML: https://mlsanity.com/paper/1701.03555/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jan 2017.

## Built on by (most cited first, 19 of 19)

- [Curriculum Learning: A Survey](https://mlsanity.com/paper/2101.10382/) (2021)
- [Multiple instance active learning for object detection](https://mlsanity.com/paper/2104.02324/) (2021)
- [A Survey on Deep Active Learning: Recent Advances and New Frontiers](https://mlsanity.com/paper/2405.00334/) (2024)
- [Pervasive AI for IoT applications: A Survey on Resource-efficient Distributed Artificial Intelligence](https://mlsanity.com/paper/2105.01798/) (2021)
- [Exploring Diversity-based Active Learning for 3D Object Detection in Autonomous Driving](https://mlsanity.com/paper/2205.07708/) (2022)
- [Introspective Robot Perception using Smoothed Predictions from Bayesian Neural Networks](https://mlsanity.com/paper/2109.12869/) (2021)
- [Toddler-Guidance Learning: Impacts of Critical Period on Multimodal AI Agents](https://mlsanity.com/paper/2201.04990/) (2022)
- [Active Learning to Classify Macromolecular Structures in situ for Less Supervision in Cryo-Electron Tomography](https://mlsanity.com/paper/2102.12040/) (2021)
- [Self-Paced Learning for Open-Set Domain Adaptation](https://mlsanity.com/paper/2303.05933/) (2023)
- [Improving Network Interpretability via Explanation Consistency Evaluation](https://mlsanity.com/paper/2408.04600/) (2024)
- [Exploring the Open World Using Incremental Extreme Value Machines](https://mlsanity.com/paper/2205.14892/) (2022)
- [Parameter-Efficient Active Learning for Foundational models](https://mlsanity.com/paper/2406.09296/) (2024)
- [Confidence-Aware Active Feedback for Interactive Instance Search](https://mlsanity.com/paper/2110.12255/) (2021)
- [Differentiated Relevances Embedding for Group-based Referring Expression Comprehension](https://mlsanity.com/paper/2203.06382/) (2022)
- [GAGA: Deciphering Age-path of Generalized Self-paced Regularizer](https://mlsanity.com/paper/2209.07063/) (2022)
- [Responsible Active Learning via Human-in-the-loop Peer Study](https://mlsanity.com/paper/2211.13587/) (2022)
- [Mixed-order self-paced curriculum learning for universal lesion detection](https://mlsanity.com/paper/2302.04677/) (2023)
- [ADs: Active Data-sharing for Data Quality Assurance in Advanced Manufacturing Systems](https://mlsanity.com/paper/2404.00572/) (2024)
- [MoMBS: Mixed-order minibatch sampling enhances model training from diverse-quality images](https://mlsanity.com/paper/2505.18741/) (2025)

## Abstract (arXiv)

This paper aims to develop a novel cost-effective framework for face identification, which progressively maintains a batch of classifiers with the increasing face images of different individuals. By naturally combining two recently rising techniques: active learning (AL) and self-paced learning (SPL), our framework is capable of automatically annotating new instances and incorporating them into training under weak expert re-certification. We first initialize the classifier using a few annotated samples for each individual, and extract image features using the convolutional neural nets. Then, a number of candidates are selected from the unannotated samples for classifier updating, in which we apply the current classifiers ranking the samples by the prediction confidence. In particular, our approach utilizes the high-confidence and low-confidence samples in the self-paced and the active user-query way, respectively. The neural nets are later fine-tuned based on the updated classifiers. Such heuristic implementation is formulated as solving a concise active SPL optimization problem, which also advances the SPL development by supplementing a rational dynamic curriculum constraint. The new model finely accords with the "instructor-student-collaborative" learning mode in human education. The advantages of this proposed framework are two-folds: i) The required number of annotated samples is significantly decreased while the comparable performance is guaranteed. A dramatic reduction of user effort is also achieved over other state-of-the-art active learning techniques. ii) The mixture of SPL and AL effectively improves not only the classifier accuracy compared to existing AL/SPL methods but also the robustness against noisy data. We evaluate our framework on two challenging datasets, and demonstrate very promising results. (http://hcp.sysu.edu.cn/projects/aspl/)