Reinforced active learning for image segmentation

Abstract

Learning-based approaches for semantic segmentation have two inherent challenges. First, acquiring pixel-wise labels is expensive and time-consuming. Second, realistic segmentation datasets are highly unbalanced: some categories are much more abundant than others, biasing the performance to the most represented ones. In this paper, we are interested in focusing human labelling effort on a small subset of a larger pool of data, minimizing this effort while maximizing performance of a segmentation model on a hold-out set. We present a new active learning strategy for semantic segmentation based on deep reinforcement learning (RL). An agent learns a policy to select a subset of small informative image regions -- opposed to entire images -- to be labeled, from a pool of unlabeled data. The region selection decision is made based on predictions and uncertainties of the segmentation model being trained. Our method proposes a new modification of the deep Q-network (DQN) formulation for active learning, adapting it to the large-scale nature of semantic segmentation problems. We test the proof of concept in CamVid and provide results in the large-scale dataset Cityscapes. On Cityscapes, our deep RL region-based DQN approach requires roughly 30% less additional labeled data than our most competitive baseline to reach the same performance. Moreover, we find that our method asks for more labels of under-represented categories compared to the baselines, improving their performance and helping to mitigate class imbalance.

Accepted to ICLR2020

References in corpus (16)

• Playing Atari with Deep Reinforcement Learning
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• Cost-Effective Active Learning for Deep Image Classification
• Deep Bayesian Active Learning with Image Data
• Bayesian Active Learning for Classification and Preference Learning
• RGB-D Object Detection and Semantic Segmentation for Autonomous Manipulation in Clutter
• Learning Active Learning from Data
• Active One-shot Learning
• Panoptic Feature Pyramid Networks
• Meta-Learning Transferable Active Learning Policies by Deep Reinforcement Learning
• Learning Algorithms for Active Learning
• Application of Decision Rules for Handling Class Imbalance in Semantic Segmentation
• CEREALS - Cost-Effective REgion-based Active Learning for Semantic Segmentation
• Discovering General-Purpose Active Learning Strategies
• DSNet for Real-Time Driving Scene Semantic Segmentation
• Multi-Target Embodied Question Answering

Cited by in corpus (9)

• A Weakly Supervised Region-Based Active Learning Method for COVID-19 Segmentation in CT Images
• Minimax Active Learning
• Exploring Spatial Diversity for Region-based Active Learning
• On uncertainty estimation in active learning for image segmentation
• Unsupervised Video Decomposition using Spatio-temporal Iterative Inference
• MEAL: Manifold Embedding-based Active Learning
• All you need are a few pixels: semantic segmentation with PixelPick
• DEAL: Difficulty-aware Active Learning for Semantic Segmentation
• Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation