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

Abstract

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 recertification. 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 selfpaced 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 "instructorstudent-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-theart 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, which include hundreds of persons under diverse conditions, and demonstrate very promising results. Please find the code of this project at: http://hcp.sysu.edu.cn/projects/aspl/

Learning Loss for Active Learning

“…Do these methods, advanced with small models and data, well scale to large deep networks [23,17] and data? Fortunately, the uncertainty approach [28,55] for classification tasks still performs well despite its simplicity. However, a task-specific design is necessary for other tasks since it utilizes network outputs.…”

Few-Example Object Detection with Model Communication

“…Kumar et al [50] propose to determine the training sample order by how easy they are. Many other researchers [51], [52], [53], [54], [55] propose more theoretically analysis on this progressive paradigm. Some researches also apply the similar idea of the progressive paradigm [56], [57], [58].…”

Cost-Effective Object Detection: Active Sample Mining With Switchable Selection Criteria

“…Self-learning: In the literature, a few works [18], [19], [29], [33], [37]- [39] have attempted to leverage samples with high prediction confidence in the context of self-training. Chen et al [37] proposed the slow addition of both target features and instances, among which the current model is the most confident, to the training set for domain adaption.…”

“…By sequentially optimizing the model while gradually controlling the learning pace via the SPL regularizer, labeled samples can be incrementally added into the training process in a self-paced manner. Inspired by these techniques, several approaches [18], [19] have been developed to improve AL for image classification by introducing a so-called pseudo-labeling strategy, which is intended to automatically select unlabeled samples with high prediction confidence and iteratively assign pseudo-labels to them in a self-paced manner.…”