Active Learning for Deep Detection Neural Networks
arXiv:1911.09168
Abstract
The cost of drawing object bounding boxes (i.e. labeling) for millions of images is prohibitively high. For instance, labeling pedestrians in a regular urban image could take 35 seconds on average. Active learning aims to reduce the cost of labeling by selecting only those images that are informative to improve the detection network accuracy. In this paper, we propose a method to perform active learning of object detectors based on convolutional neural networks. We propose a new image-level scoring process to rank unlabeled images for their automatic selection, which clearly outperforms classical scores. The proposed method can be applied to videos and sets of still images. In the former case, temporal selection rules can complement our scoring process. As a relevant use case, we extensively study the performance of our method on the task of pedestrian detection. Overall, the experiments show that the proposed method performs better than random selection. Our codes are publicly available at www.gitlab.com/haghdam/deep_active_learning.
Accepted at ICCV 2019
References in corpus (8)
- Rethinking Atrous Convolution for Semantic Image Segmentation
- Deep Visual Domain Adaptation: A Survey
- ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
- Active Learning for Convolutional Neural Networks: A Core-Set Approach
- Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
- Bayesian Active Learning for Classification and Preference Learning
- Dropout Inference in Bayesian Neural Networks with Alpha-divergences
- Deep Active Learning over the Long Tail
Cited by in corpus (7)
- Localizing Objects with Self-Supervised Transformers and no Labels
- Parting with Illusions about Deep Active Learning
- Weakly-Supervised Object Detection Learning through Human-Robot Interaction
- YMIR: A Rapid Data-centric Development Platform for Vision Applications
- Cost-Based Budget Active Learning for Deep Learning
- Learning to Rank for Active Learning: A Listwise Approach
- Distance in Latent Space as Novelty Measure