# Cost-Effective Active Learning for Deep Image Classification

## TL;DR

This paper introduces CEAL, a cost-effective active learning framework that combines deep CNNs and a novel sample selection strategy to reduce manual labeling while maintaining high classification performance.

## Contribution

The paper presents a new active learning approach integrating deep CNNs with a cost-effective sample selection strategy, including pseudo-labeling of high confidence samples.

## Key findings

- Achieves competitive classification accuracy with fewer labeled samples.
- Effectively utilizes high confidence unlabeled samples for feature learning.
- Demonstrates promising results on face recognition and object categorization datasets.

## Abstract

Recent successes in learning-based image classification, however, heavily rely on the large number of annotated training samples, which may require considerable human efforts. In this paper, we propose a novel active learning framework, which is capable of building a competitive classifier with optimal feature representation via a limited amount of labeled training instances in an incremental learning manner. Our approach advances the existing active learning methods in two aspects. First, we incorporate deep convolutional neural networks into active learning. Through the properly designed framework, the feature representation and the classifier can be simultaneously updated with progressively annotated informative samples. Second, we present a cost-effective sample selection strategy to improve the classification performance with less manual annotations. Unlike traditional methods focusing on only the uncertain samples of low prediction confidence, we especially discover the large amount of high confidence samples from the unlabeled set for feature learning. Specifically, these high confidence samples are automatically selected and iteratively assigned pseudo-labels. We thus call our framework "Cost-Effective Active Learning" (CEAL) standing for the two advantages.Extensive experiments demonstrate that the proposed CEAL framework can achieve promising results on two challenging image classification datasets, i.e., face recognition on CACD database [1] and object categorization on Caltech-256 [2].