DeepAI AI Chat
Log In Sign Up

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

by   Liang Lin, et al.
Xi'an Jiaotong University
The Hong Kong Polytechnic University

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. (


page 2

page 5

page 15

page 16


Cost-Effective Active Learning for Deep Image Classification

Recent successes in learning-based image classification, however, heavil...

Cost-effective Object Detection: Active Sample Mining with Switchable Selection Criteria

Though quite challenging, the training of object detectors using large-s...

Cluster-Based Active Learning

In this work, we introduce Cluster-Based Active Learning, a novel framew...

AL-iGAN: An Active Learning Framework for Tunnel Geological Reconstruction Based on TBM Operational Data

In tunnel boring machine (TBM) underground projects, an accurate descrip...

Does Informativeness Matter? Active Learning for Educational Dialogue Act Classification

Dialogue Acts (DAs) can be used to explain what expert tutors do and wha...

Fair Robust Active Learning by Joint Inconsistency

Fair Active Learning (FAL) utilized active learning techniques to achiev...

Confidence-Aware Active Feedback for Efficient Instance Search

Relevance feedback is widely used in instance search (INS) tasks to furt...