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

Abstract

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/)

arXiv commentTo appear in IEEE Transactions on Pattern Analysis and Machine Intelligence 2017

References in corpus (3)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Learning Face Representation from Scratch
• Cost-Effective Active Learning for Deep Image Classification

Cited by in corpus (15)

• Few-Example Object Detection with Model Communication
• Pervasive AI for IoT applications: A Survey on Resource-efficient Distributed Artificial Intelligence
• Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation
• Weakly Supervised Vessel Segmentation in X-ray Angiograms by Self-Paced Learning from Noisy Labels with Suggestive Annotation
• Active Learning to Classify Macromolecular Structures in situ for Less Supervision in Cryo-Electron Tomography
• Deep Co-Space: Sample Mining Across Feature Transformation for Semi-Supervised Learning
• A Survey on Curriculum Learning
• Diffusion-based Deep Active Learning
• Multiple instance active learning for object detection
• Toddler-Guidance Learning: Impacts of Critical Period on Multimodal AI Agents
• Self-Paced Multi-Label Learning with Diversity
• Person Re-Identification via Active Hard Sample Mining
• Confidence-Aware Active Feedback for Interactive Instance Search
• Self-Paced Deep Regression Forests for Facial Age Estimation
• Towards Time-Aware Distant Supervision for Relation Extraction