Deep Active Learning for Computer Vision: Past and Future

Abstract

As an important data selection schema, active learning emerges as the essential component when iterating an Artificial Intelligence (AI) model. It becomes even more critical given the dominance of deep neural network based models, which are composed of a large number of parameters and data hungry, in application. Despite its indispensable role for developing AI models, research on active learning is not as intensive as other research directions. In this paper, we present a review of active learning through deep active learning approaches from the following perspectives: 1) technical advancements in active learning, 2) applications of active learning in computer vision, 3) industrial systems leveraging or with potential to leverage active learning for data iteration, 4) current limitations and future research directions. We expect this paper to clarify the significance of active learning in a modern AI model manufacturing process and to bring additional research attention to active learning. By addressing data automation challenges and coping with automated machine learning systems, active learning will facilitate democratization of AI technologies by boosting model production at scale.

arXiv commentAccepted by APSIPA Transactions on Signal and Information Processing

References in corpus (30)

• A Simple Framework for Contrastive Learning of Visual Representations
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Bootstrap your own latent: A new approach to self-supervised Learning
• Understanding Black-box Predictions via Influence Functions
• Domain-adversarial neural networks to address the appearance variability of histopathology images
• BEiT: BERT Pre-Training of Image Transformers
• Active Learning for Convolutional Neural Networks: A Core-Set Approach
• Cost-Effective Active Learning for Deep Image Classification
• Deep Bayesian Active Learning with Image Data
• Bayesian Active Learning for Classification and Preference Learning
• Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds
• Adversarial Active Learning for Deep Networks: a Margin Based Approach
• Active Transfer Learning Network: A Unified Deep Joint Spectral-Spatial Feature Learning Model For Hyperspectral Image Classification
• Generative Adversarial Active Learning
• Discriminative Active Learning
• Diverse mini-batch Active Learning
• Deep Active Learning over the Long Tail
• Cost-Effective Active Learning for Melanoma Segmentation
• A Comparative Survey of Deep Active Learning
• Batch Active Learning at Scale
• Batch Active Learning Using Determinantal Point Processes
• SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios
• Ranking CGANs: Subjective Control over Semantic Image Attributes
• Localization-Aware Active Learning for Object Detection
• Consistency-based Active Learning for Object Detection
• Deep Active Learning for Video-based Person Re-identification
• ALBench: A Framework for Evaluating Active Learning in Object Detection
• YMIR: A Rapid Data-centric Development Platform for Vision Applications
• Towards Fewer Labels: Support Pair Active Learning for Person Re-identification
• Unsupervised Clustering Active Learning for Person Re-identification

Cited by in corpus (1)

• Improving Interpretability of Deep Active Learning for Flood Inundation Mapping Through Class Ambiguity Indices Using Multi-spectral Satellite Imagery