中科院和京東AI研究院提出：改進SRN人臉檢測演算法，目前業界最強！
- 2019 年 12 月 31 日
- 筆記
前戲
最近出了很多論文，各種SOTA。比如（點擊可訪問）：
今天po的改進SRN人臉檢測演算法（Improved Selective Refinement Network for Face Detection），其剛剛擊敗半個月前中星微提出的的VIM-FD演算法，所以為目前人臉檢測方向的SOTA論文。
正文
《Improved Selective Refinement Network for Face Detection》
arXiv: https://arxiv.org/abs/1901.06651
作者團隊：中科院自動化所和京東 AI研究院
註：2019年01月23日剛出爐的paper
Abstract：As a long-standing problem in computer vision, face detection has attracted much attention in recent decades for its practical applications. With the availability of face detection benchmark WIDER FACE dataset, much of the progresses have been made by various algorithms in recent years. Among them, the Selective Refinement Network (SRN) face detector introduces the two-step classification and regression operations selectively into an anchor-based face detector to reduce false positives and improve location accuracy simultaneously. Moreover, it designs a receptive field enhancement block to provide more diverse receptive field. In this report, to further improve the performance of SRN, we exploit some existing techniques via extensive experiments, including new data augmentation strategy, improved backbone network, MS COCO pretraining, decoupled classification module, segmentation branch and Squeeze-and-Excitation block. Some of these techniques bring performance improvements, while few of them do not well adapt to our baseline. As a consequence, we present an improved SRN face detector by combining these useful techniques together and obtain the best performance on widely used face detection benchmark WIDER FACE dataset.
摘要：近年來，人臉檢測作為電腦視覺中長期存在的問題，因其實際應用而備受關注。隨著人臉檢測基準WIDER FACE數據集的推出，近年來各種演算法已經取得了很多進展。其中，選擇性細化網路（SRN）人臉檢測器選擇性地將兩步分類和回歸操作引入到基於 anchor的人臉檢測器中，以同時減少誤報並提高定位精度。此外，它設計了一個感受野增強模組，以提供更多樣化的感受野。在本文中，為了進一步提高SRN的性能，我們通過廣泛的實驗開發了一些現有技術，包括新的數據增強策略，改進的骨幹網路，MS COCO預訓練，解耦分類模組，分段分支和Squeeze-Excitation塊。其中一些技術可以帶來性能改進，而其中很少一些技術不能很好地適應我們的基準線。因此，我們通過將這些有用的技術結合在一起，提出了一種改進的SRN人臉檢測器，並在廣泛使用的人臉檢測基準WIDER FACE數據集上獲得了最佳性能。
Selective Refinement Network
Network structure illustration
The brief overview of Selective Refinement Network with segmentation branch
創新點
- Selective Two-step Classification
- Selective Two-step Regression
- Receptive Field Enhancement
註：論文中還分享了一些改進的tricks，如data augmentation、feature extractor、training strategy
實驗結果
