阅读计划（寒假）

阅读计划

• 经典网络阅读

  • 显著性目标检测

    • U2Nethttps://arxiv.org/abs/2005.09007

  • 实例分割

    • Mask-RCNNhttps://arxiv.org/abs/1703.06870

  • transform

    • Attention is all your need https://arxiv.org/abs/1706.03762
    • An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale https://arxiv.org/abs/2010.11929

  • ShuffleNet (v1)(https://arxiv.org/abs/1707.01083) (v2)(https://arxiv.org/abs/1807.11164)

  • GAN(Generative Adversarial Networks) https://arxiv.org/abs/1406.2661

• 神经网络的量化（了解一下）

  • Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference https://arxiv.org/abs/1712.05877

• 可解释性分析

  • Learning Deep Features for Discriminative Localization, CVPR2016（https://arxiv.org/abs/1512.04150）
  • Grad-CAM: Visual Explanations From Deep Networks via Gradient-Based Localization ICCV 2017（https://arxiv.org/abs/1610.02391?source=post_page---------------------------）

• 无人机目标检测 近年论文

  • TPH-YOLOv5https://arxiv.org/pdf/2108.11539.pdf

  • YOLOX(Exceeding YOLO Series in 2021) https://arxiv.org/abs/2107.08430

  • YOLOv7https://arxiv.org/abs/2207.02696

  • 旋转目标检测

    • Simultaneously Localize, Segment and Rank the Camouflaged Objects（同时定位，分割和排序伪装的对象）https://arxiv.org/abs/2103.04011
    • ReDet: A Rotation-equivariant Detector for Aerial Object Detection（ReDet：用于航空物体检测的等速旋转检测器）https://arxiv.org/abs/2103.07733
    • Dense Label Encoding for Boundary Discontinuity Free Rotation Detection（解读-DCL：旋转目标检测新方法）https://arxiv.org/abs/2011.09670

• 伪装目标检测

  • Camouflaged Object Segmentation with Distraction Mining（带有干扰挖掘的伪装对象分割）https://arxiv.org/pdf/2104.10475.pdf
  • Mutual Graph Learning for Camouflaged Object Detection（用于伪装目标检测的互图学习）https://arxiv.org/abs/2104.02613
  • Uncertainty-aware Joint Salient Object and Camouflaged Object Detection（不确定度联合显着物体和伪装物体检测）https://arxiv.org/abs/2104.02628

• 无人机目标检测应用到ROS（明年开学配合吊舱学习）

  • https://blog.csdn.net/qq_42722197/article/details/122076763?ops_request_misc=&request_id=&biz_id=102&utm_term=%E6%97%A0%E4%BA%BA%E6%9C%BA%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B&utm_medium=distribute.pc_search_result.none-task-blog-2_allsobaiduweb~default-6-122076763.nonecase&spm=1018.2226.3001.4187

  • https://blog.csdn.net/Hugh_LAJ/article/details/124902738?ops_request_misc=&request_id=&biz_id=102&utm_term=%E6%97%A0%E4%BA%BA%E6%9C%BA%E7%9B%AE%E6%A0%87%E6%A3%80%E6%B5%8B&utm_medium=distribute.pc_search_result.none-task-blog-2_allsobaiduweb~default-4-124902738.nonecase&spm=1018.2226.3001.4187

阅读顺序

1、transform（2篇）

2、U2Net、Mask-RCNN（2篇）

3、GAN（1篇）

4、旋转目标检测（3篇）

5、TPH-YOLOv5

6、YOLOx、YOLOv6、7（了解其创新点）

7、Shuffle Net（2篇）

8、伪装目标检测（3篇）

9、可解释性分析、量化（了解，3篇）