# Active Learning for Deep Detection Neural Networks

arXiv: https://arxiv.org/abs/1911.09168 · HTML: https://mlsanity.com/paper/1911.09168/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2019.

## Built on by (most cited first, 30 of 62)

- [Localizing Objects with Self-Supervised Transformers and no Labels](https://mlsanity.com/paper/2109.14279/) (2021)
- [Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut](https://mlsanity.com/paper/2202.11539/) (2022)
- [TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cut](https://mlsanity.com/paper/2209.00383/) (2022)
- [Active Learning for Deep Object Detection via Probabilistic Modeling](https://mlsanity.com/paper/2103.16130/) (2021)
- [Multiple instance active learning for object detection](https://mlsanity.com/paper/2104.02324/) (2021)
- [Learning 3D Semantic Segmentation with only 2D Image Supervision](https://mlsanity.com/paper/2110.11325/) (2021)
- [Technical Report on the Pangram AI-Generated Text Classifier](https://mlsanity.com/paper/2402.14873/) (2024)
- [Discovering and forecasting extreme events via active learning in neural operators](https://mlsanity.com/paper/2204.02488/) (2022)
- [Not All Labels Are Equal: Rationalizing The Labeling Costs for Training Object Detection](https://mlsanity.com/paper/2106.11921/) (2021)
- [Exploring Active 3D Object Detection from a Generalization Perspective](https://mlsanity.com/paper/2301.09249/) (2023)
- [Active Learning for Deep Visual Tracking](https://mlsanity.com/paper/2110.13259/) (2021)
- [MCDAL: Maximum Classifier Discrepancy for Active Learning](https://mlsanity.com/paper/2107.11049/) (2021)
- [Semantic Segmentation with Active Semi-Supervised Learning](https://mlsanity.com/paper/2203.10730/) (2022)
- [Exploring Diversity-based Active Learning for 3D Object Detection in Autonomous Driving](https://mlsanity.com/paper/2205.07708/) (2022)
- [Active Pointly-Supervised Instance Segmentation](https://mlsanity.com/paper/2207.11493/) (2022)
- [Neural Interactive Keypoint Detection](https://mlsanity.com/paper/2308.10174/) (2023)
- [Monocular 3D Object Detection with LiDAR Guided Semi Supervised Active Learning](https://mlsanity.com/paper/2307.08415/) (2023)
- [Multi-Task Consistency for Active Learning](https://mlsanity.com/paper/2306.12398/) (2023)
- [Bayesian Active Learning for Sim-to-Real Robotic Perception](https://mlsanity.com/paper/2109.11547/) (2021)
- [Active learning with MaskAL reduces annotation effort for training Mask R-CNN](https://mlsanity.com/paper/2112.06586/) (2021)
- [ALBench: A Framework for Evaluating Active Learning in Object Detection](https://mlsanity.com/paper/2207.13339/) (2022)
- [Deep Active Learning for Computer Vision: Past and Future](https://mlsanity.com/paper/2211.14819/) (2022)
- [When Deep Learners Change Their Mind: Learning Dynamics for Active Learning](https://mlsanity.com/paper/2107.14707/) (2021)
- [CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentation](https://mlsanity.com/paper/2112.05975/) (2021)
- [Active Learning of Neural Collision Handler for Complex 3D Mesh Deformations](https://mlsanity.com/paper/2110.07727/) (2021)
- [YMIR: A Rapid Data-centric Development Platform for Vision Applications](https://mlsanity.com/paper/2111.10046/) (2021)
- [Deep Unsupervised Active Learning on Learnable Graphs](https://mlsanity.com/paper/2111.04286/) (2021)
- [Active Learning for Object Detection with Non-Redundant Informative Sampling](https://mlsanity.com/paper/2307.08414/) (2023)
- [Dataset Definition Standard (DDS)](https://mlsanity.com/paper/2101.03020/) (2021)
- [MUS-CDB: Mixed Uncertainty Sampling with Class Distribution Balancing for Active Annotation in Aerial Object Detection](https://mlsanity.com/paper/2212.02804/) (2022)

## Abstract (arXiv)

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.