NVlabs / AL-MDN

Official pytorch implementation of Active Learning for deep object detection via probabilistic modeling (ICCV 2021)
https://openaccess.thecvf.com/content/ICCV2021/html/Choi_Active_Learning_for_Deep_Object_Detection_via_Probabilistic_Modeling_ICCV_2021_paper.html
Other
168 stars 23 forks source link
active-learning deep-learning object-detection

Active Learning for Deep Object Detection via Probabilistic Modeling

This repository is the official PyTorch implementation of Active Learning for Deep Object Detection via Probabilistic Modeling, ICCV 2021.

The proposed method is implemented based on the SSD pytorch.

Our approach relies on mixture density networks to estimate, in a single forward pass of a single model, both localization and classification uncertainties, and leverages them in the scoring function for active learning.

Our method performs on par with multiple model-based methods (e.g., ensembles and MC-Dropout). Therefore, our method provides the best trade-off between accuracy and computational cost. License -------- To view a NVIDIA Source Code License for this work, visit https://github.com/NVlabs/AL-MDN/blob/main/LICENSE Requirements ---------------------- For setup and data preparation, please refer to the README in [SSD pytorch](https://github.com/amdegroot/ssd.pytorch). Code was tested in virtual environment with `Python 3+` and `Pytorch 1.1`. Training -------- - Make directory `mkdir weights` and `cd weights`. - Download the [FC-reduced VGG-16 backbone weight](https://s3.amazonaws.com/amdegroot-models/vgg16_reducedfc.pth) in the `weights` directory, and `cd ..`. - If necessary, change the `VOC_ROOT` in `data/voc0712.py` or `COCO_ROOT` in `data/coco.py`. - Please refer to `data/config.py` for configuration. - Run the training code: ``` # Supervised learning CUDA_VISIBLE_DEVICES= python train_ssd_gmm_supervised_learning.py # Active learning CUDA_VISIBLE_DEVICES= python train_ssd_gmm_active_learining.py ``` Evaluation -------- - To evaluate on MS-COCO, change the `COCO_ROOT_EVAL` in `data/coco_eval.py`. - Run the evaluation code: ``` # Evaluation on PASCAL VOC python eval_voc.py --trained_model # Evaluation on MS-COCO python eval_coco.py --trained_model ``` Visualization --------- - Run the visualization code: ``` python demo.py --trained_model ``` Citation -------- ``` @InProceedings{Choi_2021_ICCV, author = {Choi, Jiwoong and Elezi, Ismail and Lee, Hyuk-Jae and Farabet, Clement and Alvarez, Jose M.}, title = {Active Learning for Deep Object Detection via Probabilistic Modeling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {10264-10273} } ```