當前位置：首頁 > 人文社科 > 生活经验 >内容正文

生活经验

Paper9：Fast RCNN

發布時間：2023/11/27 生活经验 32 豆豆

生活随笔收集整理的這篇文章主要介紹了 Paper9：Fast RCNN 小編覺得挺不錯的,現在分享給大家,幫大家做個參考.

code：s available under the open-source MIT License at https://github.com/rbgirshick/ fast-rcnn.

摘要：

Fast R-CNN在訓練和測試上的速度都得到提高，而且準確率也提高了。在on PASCAL VOC 2012上，Fast R-CNN trains the very deep VGG16 network 9× faster than R-CNN, is 213× faster at test-time, and achieves a higher mAP on PASCAL VOC 2012。Fast R-CNN與SPPNet相比，Fast R-CNN訓練VGG16更快，準確率也更高；

The Fast R-CNN method has several advantages:

1. Higher detection quality (mAP) than R-CNN, SPPnet

2. Training is single-stage, using a multi-task loss

3. Training can update all network layers

4. No disk storage is required for feature caching

mAP：mean Average Precision,簡單翻譯過來就是平均的平均精確度（沒錯，就是兩個平均），首先是一個類別內，求平均精確度（Average Precision），然后對所有類別的平均精確度再求平均（mean Average Precision）。

mAP: mean Average Precision, 即各類別AP的平均值
AP: PR曲線下面積，后文會詳細講解
PR曲線: Precision-Recall曲線
Precision: TP / (TP + FP)
Recall: TP / (TP + FN)
TP: IoU>0.5的檢測框數量（同一Ground Truth只計算一次）
FP: IoU<=0.5的檢測框，或者是檢測到同一個GT的多余檢測框的數量
FN: 沒有檢測到的GT的數量

Propose：First, numerous candidate object locations (often called “proposals”) must be processed。

1、Introduction

Methods：In this paper, we streamline the training process for state-of-the-art ConvNet-based object detectors [9, 11]. We propose a single-stage training algorithm that jointly learns to classify object proposals and refine their spatial locations.

Result：The resulting method can train a very deep detection network (VGG16 [20]) 9× faster than R-CNN [9] and 3× faster than SPPnet [11]. At runtime, the detection network processes images in 0.3s (excluding object proposal time) while achieving top accuracy on PASCAL VOC 2012 [7] with a mAP of 66% (vs. 62% for R-CNN).1。

首先指出R-CNN的缺點：The Region-based Convolutional Network method (R-CNN) [9] achieves excellent object detection accuracy by using a deep ConvNet to classify object proposals. R-CNN, however, has notable drawbacks：

1. Training is a multi-stage pipeline.（多階段訓練）

R-CNN first fine tunes a ConvNet on object proposals using log loss. Then, it fits SVMs to ConvNet features. These SVMs act as object detectors, replacing the softmax classifier learnt by fine-tuning. In the third training stage, bounding-box regressors are learned.

2. Training is expensive in space and time.（訓練階段對于空間和時間的消耗太高）

For SVM and bounding-box regressor training, features are extracted from each object proposal in each image and written to disk. With very deep networks, such as VGG16, this process takes 2.5 GPU-days for the 5k images of the VOC07 trainval set. These features require hundreds of gigabytes of storage.

3. Object detection is slow.（物體檢測比較慢）

At test-time, features are extracted from each object proposal in each test image. Detection with VGG16 takes 47s / image (on a GPU).

論述R-CNN和SPPNet：（再看一下金字塔池化spatial pyramid pooling15和微調算法11）

R-CNN很慢，因為它對每個對象建議執行一個ConvNet forward pass，而不共享計算。而Spatial pyramid pooling networks (SPPnets) [11] were proposed to speed up R-CNN by sharing computatio。

The SPPnet method computes a convolutional feature map for the entire input image and then classifies each object proposal using a feature vector extracted from the shared feature map. Features are extracted for a proposal by max pooling the portion of the feature map inside the proposal into a fixed-size output (e.g., 6 × 6). Multiple output sizes are pooled and then concatenated as in spatial pyramid pooling [15]. SPPnet accelerates R-CNN by 10 to 100× at test time. Training time is also reduced by 3× due to faster proposal feature extraction.

（SPPnet方法為整個輸入圖像計算卷積特征圖，然后使用從共享特征圖中提取的特征向量對每個對象提議進行分類。通過最大程度地將提案中的要素地圖部分集中到固定大小的輸出（例如6×6）中，提取提案的要素。合并多個輸出大小，然后像在空間金字塔合并中一樣進行串聯[15]。在測試時，SPPnet將R-CNN的速度提高了10到100倍。由于建議特征提取速度更快，培訓時間也減少了3倍。）

SPPnet的缺點：

SPPnet also has notable drawbacks. Like R-CNN, training is a multi-stage pipeline that involves extracting features, fine-tuning a network with log loss, training SVMs, and finally fitting bounding-box regressors. Features are also written to disk. But unlike R-CNN, the fine-tuning algorithm proposed in [11] cannot update the convolutional layers that precede the spatial pyramid pooling. Unsurprisingly, this limitation (fixed convolutional layers) limits the accuracy of very deep networks.

（SPPnet也有明顯的缺點。像R-CNN一樣，訓練是一個多階段的管道，涉及提取特征，對網絡進行log損失微調，訓練SVM，最后擬合邊界框回歸器。特征也會寫入磁盤。但是與R-CNN不同，文獻[11]中提出的微調算法無法更新空間金字塔池之前的卷積層。毫無疑問，此限制（固定的卷積層）限制了非常深的網絡的準確性。）

2、Fast RCNN architecture and training

快速的R-CNN網絡以一幅完整的圖像和一組對象建議(object proposals)作為輸入。First，該網絡首先對整個圖像進行卷積(conv)和最大池化層處理，生成conv特征映射。Then，然后，對每個對象提議object proposal，一個感興趣區域(RoI)池化層從特征映射feature map中提取一個固定長度的特征向量。每個特征向量被送到一個全連接序列中，最終分支成兩個sibling的輸出層；其中一個對K個對象類加上一個“背景”類產生softmax 概率估計，另一個輸出層為K個對象類中的每一個輸出四個實數值，每組4個值對K個類別之一精確的邊界框(bounding box)位置進行編碼。

2.1?The RoI pooling layer

2.2 Initializing from pre-trained networks

2.3 Fine-tuning for detection

為什么SPPnet不能更新空間金字塔池化層以下的權重？其根本原因是，當每個訓練樣本(即RoI)來自不同的圖像時，通過SPP層的反向傳播效率非常低，這正是R-CNN和SPPnet網絡的訓練方式。效率低的原因是每個RoI可能有一個非常大的接受野，通常跨越整個輸入圖像。因此前向傳播必須處理整個感受野，所以訓練輸入量很大(通常是整個圖像)。

fast R-cnn training advantage：(than R-cnn and SPPnet)

We propose a more efficient training method that takes advantage of feature sharing during training.In Fast R-CNN training, stochastic gradient descent (SGD) mini-batches are sampled hierarchically, first by sampling N images and then by sampling R/N RoIs from each image. Critically, RoIs from the same image share computation and memory in the forward and backward passes. Making N small decreases mini-batch computation. For example, when using N = 2 and R = 128, the proposed training scheme is roughly 64× faster than sampling one RoI from 128 different images (i.e., the R-CNN and SPPnet strategy)

Q：從每一個image 采樣R/N個ROIs,（R是什么？N是什么？N是images的個數，mini-batches of size R = 128）

IOU(重疊度)(Intersection over Union)：

物體檢測需要定位出物體的bounding box，就像下面的圖片一樣，我們不僅要定位出車輛的bounding box 我們還要識別出bounding box 里面的物體就是車輛。

? ? ?