Active and Incremental Learning with Weak Supervision

Clemens-Alexander Brust,Joachim Denzler,Christoph Käding

doi:10.1007/s13218-020-00631-4

Clemens-Alexander Brust, Joachim Denzler + Show 1 more

Open Access

https://doi.org/10.1007/s13218-020-00631-4

Copy DOI

Abstract

Large amounts of labeled training data are one of the main contributors to the great success that deep models have achieved in the past. Label acquisition for tasks other than benchmarks can pose a challenge due to requirements of both funding and expertise. By selecting unlabeled examples that are promising in terms of model improvement and only asking for respective labels, active learning can increase the efficiency of the labeling process in terms of time and cost. In this work, we describe combinations of an incremental learning scheme and methods of active learning. These allow for continuous exploration of newly observed unlabeled data. We describe selection criteria based on model uncertainty as well as expected model output change (EMOC). An object detection task is evaluated in a continuous exploration context on the PASCAL VOC dataset. We also validate a weakly supervised system based on active and incremental learning in a real-world biodiversity application where images from camera traps are analyzed. Labeling only 32 images by accepting or rejecting proposals generated by our method yields an increase in accuracy from 25.4 to 42.6%.

Highlights

Deep convolutional networks (CNNs) show impressive performance in a variety of applications
By mapping the classes of the PASCAL VOC dataset [7] to the observed species, the initial model achieves an accuracy of 66.5%
There are basically two main scenarios in which a rejection can possibly happen. Both cases need to be considered during active learning and we present solutions and adaptations of the expected model output change (EMOC) principle for each of them in the following

Summary

Introduction

Deep convolutional networks (CNNs) show impressive performance in a variety of applications. Even in the challenging task of object detection, they serve as excellent models [18, 44, 45, 52, 53]. In many application scenarios, new data becomes available over time or the distribution underlying the problem changes. When this happens, models are usually retrained from scratch or have to be refined via either fine-tuning [21, 45] or incremental learning [40, 51]. Classification is a machine learning task in which an example x, e.g. an image or text, from a data space is assigned a class c from a set C of many possible classes, e.g. cat or dog.

Objectives

Methods

Results

Discussion

Conclusion