1st Place Solutions for UG2+ Challenge 2021 -- (Semi-)supervised Face detection in the low light condition

• URL: http://arxiv.org/abs/2107.00818v1
• Date: Fri, 2 Jul 2021 04:12:23 GMT
• Title: 1st Place Solutions for UG2+ Challenge 2021 -- (Semi-)supervised Face detection in the low light condition
• Authors: Pengcheng Wang, Lingqiao Ji, Zhilong Ji, Yuan Gao, Xiao Liu
• Abstract summary: "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. We ensemble several models which achieved mAP 74.89 on the testing set, ranking 1st on the final leaderboard.
• Score: 13.241328369629453
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• First Place Solution to the ECCV 2024 ROAD++ Challenge @ ROAD++ Spatiotemporal Agent Detection 2024 [12.952512012601874]
  The task of Track 1 is agent detection, which aims to construct an "agent tube" for agents in consecutive video frames. Our solutions focus on the challenges in this task including extreme-size objects, low-light, imbalance and fine-grained classification. We rank first in the test set of Track 1 for the ROAD++ Challenge 2024, and achieve 30.82% average video-mAP.
  arXiv  Detail & Related papers  (2024-10-30T14:52:43Z)
• Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection [106.39544368711427]
  We study the problem of generalizable synthetic image detection, aiming to detect forgery images from diverse generative methods. We present a novel forgery-aware adaptive transformer approach, namely FatFormer. Our approach tuned on 4-class ProGAN data attains an average of 98% accuracy to unseen GANs, and surprisingly generalizes to unseen diffusion models with 95% accuracy.
  arXiv  Detail & Related papers  (2023-12-27T17:36:32Z)
• Gen2Det: Generate to Detect [42.13657805295144]
  We motivate and present Gen2Det, a simple modular pipeline to create synthetic training data for object detection for free. In addition to the synthetic data, Gen2Det proposes a suite of techniques to best utilize the generated data, including image-level filtering, instance-level filtering, and better training recipe.
  arXiv  Detail & Related papers  (2023-12-07T18:59:58Z)
• 1st Place Solution for ECCV 2022 OOD-CV Challenge Object Detection Track [71.12470906323298]
  Generalize-then-Adapt (G&A) framework is composed of a two-stage domain generalization part and a one-stage domain adaptation part. The proposed G&A framework help us achieve the first place on the object detection leaderboard of the OOD-CV challenge.
  arXiv  Detail & Related papers  (2023-01-12T03:50:46Z)
• Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method [51.30748775681917]
  We consider the task of low-light image enhancement (LLIE) and introduce a large-scale database consisting of images at 4K and 8K resolution. We conduct systematic benchmarking studies and provide a comparison of current LLIE algorithms. As a second contribution, we introduce LLFormer, a transformer-based low-light enhancement method.
  arXiv  Detail & Related papers  (2022-12-22T09:05:07Z)
• 2nd Place Solutions for UG2+ Challenge 2022 -- D$^{3}$Net for Mitigating Atmospheric Turbulence from Images [5.092028049119383]
  D$3$Net was proposed by our team "TUK-IK" for Atmospheric Turbulence Mitigation in $UG2+$ Challenge at CVPR 2022. The proposed method ranked 2nd on the final leader-board of the aforementioned challenge in the testing phase, respectively.
  arXiv  Detail & Related papers  (2022-08-25T20:20:09Z)
• D^2LV: A Data-Driven and Local-Verification Approach for Image Copy Detection [36.473577708618976]
  A data-driven and local-verification approach is proposed to compete for Image Similarity Challenge: Matching Track at NeurIPS'21. In D2LV, unsupervised pre-training substitutes the commonly-used supervised one. The proposed approach ranks first out of 1,103 participants on the Facebook AI Image Similarity Challenge: Matching Track.
  arXiv  Detail & Related papers  (2021-11-13T10:56:58Z)
• Dual-Camera Super-Resolution with Aligned Attention Modules [56.54073689003269]
  We present a novel approach to reference-based super-resolution (RefSR) with the focus on dual-camera super-resolution (DCSR) Our proposed method generalizes the standard patch-based feature matching with spatial alignment operations. To bridge the domain gaps between real-world images and the training images, we propose a self-supervised domain adaptation strategy.
  arXiv  Detail & Related papers  (2021-09-03T07:17:31Z)
• Anchor-free Small-scale Multispectral Pedestrian Detection [88.7497134369344]
  We propose a method for effective and efficient multispectral fusion of the two modalities in an adapted single-stage anchor-free base architecture. We aim at learning pedestrian representations based on object center and scale rather than direct bounding box predictions. Results show our method's effectiveness in detecting small-scaled pedestrians.
  arXiv  Detail & Related papers  (2020-08-19T13:13:01Z)
• NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results [148.54397669654958]
  This paper reviews the NTIRE 2020 challenge on real world super-resolution. The challenge addresses the real world setting, where paired true high and low-resolution images are unavailable. In total 22 teams competed in the final testing phase, demonstrating new and innovative solutions to the problem.
  arXiv  Detail & Related papers  (2020-05-05T08:17:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.