1st Place Solutions for UG2+ Challenge 2021 -- (Semi-)supervised Face detection in the low light condition
Not on the map. Why?
Abstract (arXiv)
In this technical report, we briefly introduce the solution of our team "TAL-ai" for (Semi-) supervised Face detection in the low light condition in UG2+ Challenge in CVPR 2021. By conducting several experiments with popular image enhancement methods and image transfer methods, we pulled the low light image and the normal image to a more closer domain. And it is observed that using these data to training can achieve better performance. We also adapt several popular object detection frameworks, e.g., DetectoRS, Cascade-RCNN, and large backbone like Swin-transformer. Finally, we ensemble several models which achieved mAP 74.89 on the testing set, ranking 1st on the final leaderboard.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 14 of its 22 references that are in the map. First posted on arXiv 2 Jul 2021.
Builds on
14 of 22 references.
References · 14
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
- 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
- 2017Deformable Convolutional Networkscited by 1,481
- 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
- 2018Albumentations: fast and flexible image augmentationscited by 558
- 2020Zero-Reference Deep Curve Estimation for Low-Light Image Enhancementcited by 541
- 2019Cascade R-CNN: High Quality Object Detection and Instance Segmentationcited by 428
- 2017Soft-NMS -- Improving Object Detection With One Line of Codecited by 380
- 2019GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyondcited by 331
- 2015WIDER FACE: A Face Detection Benchmarkcited by 297
- 2020DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolutioncited by 222
- 2019UG2+ Track 2: A Collective Benchmark Effort for Evaluating and Advancing Image Understanding in Poor Visibility Environmentscited by 84
Built on by
Not cited yet.