Active and Incremental Learning with Weak Supervision

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%.

Accepted for publication in KI - Künstliche Intelligenz

References in corpus (13)

• SSD: Single Shot MultiBox Detector
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Overcoming catastrophic forgetting in neural networks
• YOLOv3: An Incremental Improvement
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Focal Loss for Dense Object Detection
• Cost-Effective Active Learning for Deep Image Classification
• Deep Bayesian Active Learning with Image Data
• LSDA: Large Scale Detection Through Adaptation
• Her2 Challenge Contest: A Detailed Assessment of Automated Her2 Scoring Algorithms in Whole Slide Images of Breast Cancer Tissues
• Active and Continuous Exploration with Deep Neural Networks and Expected Model Output Changes
• Camera-trap images segmentation using multi-layer robust principal component analysis
• Active learning with version spaces for object detection

Cited by in corpus (3)

• A Weakly Supervised Region-Based Active Learning Method for COVID-19 Segmentation in CT Images
• Learning Structured Representations of Entity Names using Active Learning and Weak Supervision
• Active WeaSuL: Improving Weak Supervision with Active Learning