Comparison of SIFT Encoded and Deep Learning Features for the Classification and Detection of Esca D
識別葡萄的一種蟲害，比較了傳統SIFT和深度學習分類，最後還作了目標檢測網絡
分類用的 MobileNet，目標檢測 RetinaNet性能
MobileNet 是將傳統深度可分離卷積分紅了兩步，深度卷積和逐點卷積，性能基本不受影響狀況下，下降計算量和參數量學習
RetinaNet 主要提出 focal loss，用於處理目標檢測時正負樣本不均衡問題，FL的做用以下blog
網絡結構就是 FPN + sub-network + FL深度學習
FPN是圖像金字塔網絡，對不一樣scale的圖像進行融合和預測，主要用於目標檢測，原理感受和unet差很少原理
相關文章
- 1. [解讀] Deep Clustering for Unsupervised Learning of Visual Features
- 2. [CVPR 2020] D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features
- 3. 【譯】The challenge of verification and testing of machine learning
- 4. 【學習】Deep Learning for Deepfakes Creation and Detection
- 5. Deep Clustering for Unspervised Learning of Visual Features
- 6. Summary of defect detection algorithms based on deep learning
- 7. ASLFeat: Learning Local Features of Accurate Shape and Localization &&2020
- 8. 論文：Automated Vehicle Detection and Classification: Models, Methods, and Techniques翻譯（四）
- 9. 【文獻學習】Power of Deep Learning for Channel Estimation and Signal Detection in OFDM
- 10. Some methods of deep learning and dimensionality reduction
- 更多相關文章...
- • XSLT
- • XSLT
- • RxJava操作符（七）Conditional and Boolean
- • 爲了進字節跳動，我精選了29道Java經典算法題，帶詳細講解
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. [解讀] Deep Clustering for Unsupervised Learning of Visual Features
- 2. [CVPR 2020] D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features
- 3. 【譯】The challenge of verification and testing of machine learning
- 4. 【學習】Deep Learning for Deepfakes Creation and Detection
- 5. Deep Clustering for Unspervised Learning of Visual Features
- 6. Summary of defect detection algorithms based on deep learning
- 7. ASLFeat: Learning Local Features of Accurate Shape and Localization &&2020
- 8. 論文：Automated Vehicle Detection and Classification: Models, Methods, and Techniques翻譯（四）
- 9. 【文獻學習】Power of Deep Learning for Channel Estimation and Signal Detection in OFDM
- 10. Some methods of deep learning and dimensionality reduction