文章目錄

• • 一、背景
  • 二、動機
  • 三、方法
  • • 3.1 IACS——IoU-Aware Classification Score
    • 3.2 Varifocal loss
    • 3.3 Star-Shaped Box Feature Representation
    • 4.4 Bounding-box refinement
    • 4.5 VarifocalNet
  • 四、效果
  • 五、代碼
  • • 5.1 修改數據集路徑
    • 5.2 VFNet

代碼已開源： https://github.com/hyz-xmaster/VarifocalNet

一、背景

現有的目標檢測器中，大多都是先生成大量的候選框，然后使用NMS來進行濾除，NMS是基于分類得分來排序的。

由于分類得分高的框，并不一定是框的最準的框，得分較低但框的很準確的框很可能會被濾掉。因此，[11]使用額外的 IoU 得分，[9] 使用centerness 得分作為衡量框位置準確率的標準，將其得分和分類得分相乘來作為 NMS 排序的標準。

二、動機

上述兩個方法雖然可能會有一些優勢，但是相乘的方法并不是最優的，可能會導致更差的排序，且性能提升有限，并且單獨的分支來預測位置得分會引起計算量上升。

可以不使用額外分支來預測位置得分，而是將其和分類得分分支融合起來？
——作者提出了一個 localization-aware/IoU-aware 的 classification score (IACS)

作者在FOCS+ATSS 上進行了一系列實驗，將類別、位置、centerness得分分別替換為真值，尋找哪個得分對最終結果影響最大：

上表中，效果最好的是 74.4 AP，這是將真實類別得分替換為預測box和gt box的 IoU 得分得到的，這實際上表明，對于大多數對象，在大量候選框中已經存在精確的局部邊界框。實現優秀檢測性能的關鍵是準確地從池中選擇出這些高質量的檢測，這些結果表明，用gt IoU替代ground-truth類的分類分數是最有希望的選擇措施。

三、方法

本文作者提出了基于 FCOS+ATSS 的 VarifocalNet（去掉了 centerness 分支），相比 FCOS+ATSS，該網絡有三個新模塊：

• varifocal loss
• star-shaped box feature representation
• bounding box refinement

3.1 IACS——IoU-Aware Classification Score

IACS：分類得分向量中的一個標量元素

• 真實類別位置的得分：預測框和真實框的 IoU
• 其他位置的得分：0

3.2 Varifocal loss

為了學習 IACS 得分，作者設計了一個 Varifocal Loss，靈感得益于 Focal Loss。

Focal Loss：

• p：預測得分
• y：真實類別
• 降低前景/背景中，簡單樣例對 Loss 的貢獻

Varifocal Loss：

• p：預測的 IACS
• q：target score（真實類別：q為預測和真值的 IoU，其他類別：0）

不對稱的處理前景和背景對loss的貢獻：

• 只降低負例對loss的貢獻
• 不降低正例對loss的貢獻（因為正例相比負例而言，更加珍貴）
• 作者使用 target $q$ 作為正例的權重做了一個實驗，實驗發現當正例的 gt_IoU 高時，其對 loss 的貢獻很大，也就是說訓練高質量的正例對AP的提升比低質量的更大一些。

3.3 Star-Shaped Box Feature Representation

作者定義了一種 star-shaped 的 bounding-box 特征的表達方式，使用9個采樣點來表達 可變形卷積得到的 bounding-box。

為什么用9個點來表達？

• 作者認為現在基于關鍵點的表達方法雖然有效，但是丟失了box中的特征和上下文信息

首先，給定一個采樣點（x，y），使用 3x3 卷積來回歸初始 box （$l^{\prime },t^{\prime },r^{\prime },b^{\prime }$），分別為其到左、上、右、下的距離（圖1紅框）。選中的9個點為黃色圈。相對位移作為可變形卷積的偏移，然后使用可變形卷積對這9個點卷積，來表示這個box。

4.4 Bounding-box refinement

作者還從 bounding box refinement 的角度來嘗試提升目標定位的準確性。

原始四個偏移：$(l^{\prime },t^{\prime },r^{\prime },b^{\prime })$
學習的四個縮放因子：$(\Delta l,\Delta t,\Delta r,\Delta b)$
refine 后的偏移：$(l,t,r,b)=(\Delta l\times l^{\prime },\Delta t\times t^{\prime },\Delta r\times r^{\prime },\Delta b\times b^{\prime })$

4.5 VarifocalNet

Backbone:

• FCN

Heads:

• bounding-box
• IoU-aware classification score

四、效果

$\alpha =0.75,\gamma =2$

可視化效果：

五、代碼

該文章實現基于mmdetection，本文代碼的 github倉庫中有安裝方式，安裝成功后，下載作者訓練好的模型，修改coco數據路徑即可成功訓練和測試。

訓練：

./tools/dist_train.sh configs/vfnet/vfnet_r50_fpn_1x_coco.py 8

測試：

# 測試指標 ./tools/dist_test.sh configs/vfnet/vfnet_r50_fpn_1x_coco.py checkpoints/vfnet_r50_1x_41.6.pth 8 --eval bbox # 可視化 ./tools/dist_test.sh configs/vfnet/vfnet_r50_fpn_1x_coco.py checkpoints/vfnet_r50_1x_41.6.pth 8 --show-dir results/

demo：

python demo/image_demo.py demo/demo.jpg configs/vfnet/vfnet_r50_fpn_1x_coco.py checkpoints/vfnet_r50_1x_41.6.pth

5.1 修改數據集路徑

在運行代碼之前，一定要執行下面的語句，不然代碼走的路徑不對：

python setup.py develop # 1 ./configs/_base_/coco_detection.py

# 2 ./configs/vfnet/vfnet_r50_fpn_1x_coco.py

5.2 VFNet

# vfnet_r50_fpn_1x_coco.py # model settings model = dict(type='VFNet',pretrained='torchvision://resnet50',backbone=dict(type='ResNet',depth=50,num_stages=4,out_indices=(0, 1, 2, 3),frozen_stages=1,norm_cfg=dict(type='BN', requires_grad=True),norm_eval=True,style='pytorch'),neck=dict(type='FPN',in_channels=[256, 512, 1024, 2048],out_channels=256,start_level=1,add_extra_convs=True,extra_convs_on_inputs=False, # use P5num_outs=5,relu_before_extra_convs=True),bbox_head=dict(type='VFNetHead',num_classes=80,in_channels=256,stacked_convs=3,feat_channels=256,strides=[8, 16, 32, 64, 128],center_sampling=False,dcn_on_last_conv=False,use_atss=True,use_vfl=True,loss_cls=dict(type='VarifocalLoss',use_sigmoid=True,alpha=0.75,gamma=2.0,iou_weighted=True,loss_weight=1.0),loss_bbox=dict(type='GIoULoss', loss_weight=1.5),loss_bbox_refine=dict(type='GIoULoss', loss_weight=2.0)),# training and testing settingstrain_cfg=dict(assigner=dict(type='ATSSAssigner', topk=9),allowed_border=-1,pos_weight=-1,debug=False),test_cfg=dict(nms_pre=1000,min_bbox_size=0,score_thr=0.05,nms=dict(type='nms', iou_threshold=0.6),max_per_img=100))

VFNet Head:

/mmdet/models/dense_heads/vfnet_head.py (bbox_head): VFNetHead((loss_cls): VarifocalLoss()(loss_bbox): GIoULoss()(cls_convs): ModuleList((0): ConvModule((conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(gn): GroupNorm(32, 256, eps=1e-05, affine=True)(activate): ReLU(inplace=True))(1): ConvModule((conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(gn): GroupNorm(32, 256, eps=1e-05, affine=True)(activate): ReLU(inplace=True))(2): ConvModule((conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(gn): GroupNorm(32, 256, eps=1e-05, affine=True)(activate): ReLU(inplace=True)))(reg_convs): ModuleList((0): ConvModule((conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(gn): GroupNorm(32, 256, eps=1e-05, affine=True)(activate): ReLU(inplace=True))(1): ConvModule((conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(gn): GroupNorm(32, 256, eps=1e-05, affine=True)(activate): ReLU(inplace=True))(2): ConvModule((conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(gn): GroupNorm(32, 256, eps=1e-05, affine=True)(activate): ReLU(inplace=True)))(relu): ReLU(inplace=True)(vfnet_reg_conv): ConvModule((conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(gn): GroupNorm(32, 256, eps=1e-05, affine=True)(activate): ReLU(inplace=True))(vfnet_reg): Conv2d(256, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(scales): ModuleList((0): Scale()(1): Scale()(2): Scale()(3): Scale()(4): Scale())(vfnet_reg_refine_dconv): DeformConv2d(in_channels=256,out_channels=256,kernel_size=(3, 3),stride=(1, 1),padding=(1, 1),dilation=(1, 1),groups=1,deform_groups=1,deform_groups=False)(vfnet_reg_refine): Conv2d(256, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(scales_refine): ModuleList((0): Scale()(1): Scale()(2): Scale()(3): Scale()(4): Scale())(vfnet_cls_dconv): DeformConv2d(in_channels=256,out_channels=256,kernel_size=(3, 3),stride=(1, 1),padding=(1, 1),dilation=(1, 1),groups=1,deform_groups=1,deform_groups=False)(vfnet_cls): Conv2d(256, 80, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(loss_bbox_refine): GIoULoss())init_cfg={'type': 'Normal', 'layer': 'Conv2d', 'std': 0.01, 'override': {'type': 'Normal', 'name': 'vfnet_cls', 'std': 0.01, 'bias_prob': 0.01}} )

VFNet model:

VFNet((backbone): ResNet((conv1): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True)(maxpool): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)(layer1): ResLayer((0): Bottleneck((conv1): Conv2d(64, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True)(downsample): Sequential((0): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(1): Bottleneck((conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True))(2): Bottleneck((conv1): Conv2d(256, 64, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True)))(layer2): ResLayer((0): Bottleneck((conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True)(downsample): Sequential((0): Conv2d(256, 512, kernel_size=(1, 1), stride=(2, 2), bias=False)(1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(1): Bottleneck((conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True))(2): Bottleneck((conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True))(3): Bottleneck((conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(128, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True)))(layer3): ResLayer((0): Bottleneck((conv1): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True)(downsample): Sequential((0): Conv2d(512, 1024, kernel_size=(1, 1), stride=(2, 2), bias=False)(1): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(1): Bottleneck((conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True))(2): Bottleneck((conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True))(3): Bottleneck((conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True))(4): Bottleneck((conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True))(5): Bottleneck((conv1): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(256, 1024, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True)))(layer4): ResLayer((0): Bottleneck((conv1): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False)(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True)(downsample): Sequential((0): Conv2d(1024, 2048, kernel_size=(1, 1), stride=(2, 2), bias=False)(1): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)))(1): Bottleneck((conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True))(2): Bottleneck((conv1): Conv2d(2048, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv2): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(bn2): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(conv3): Conv2d(512, 2048, kernel_size=(1, 1), stride=(1, 1), bias=False)(bn3): BatchNorm2d(2048, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)(relu): ReLU(inplace=True))))init_cfg={'type': 'Pretrained', 'checkpoint': 'torchvision://resnet50'}(neck): FPN((lateral_convs): ModuleList((0): ConvModule((conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1)))(1): ConvModule((conv): Conv2d(1024, 256, kernel_size=(1, 1), stride=(1, 1)))(2): ConvModule((conv): Conv2d(2048, 256, kernel_size=(1, 1), stride=(1, 1))))(fpn_convs): ModuleList((0): ConvModule((conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)))(1): ConvModule((conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)))(2): ConvModule((conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)))(3): ConvModule((conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1)))(4): ConvModule((conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1)))))init_cfg={'type': 'Xavier', 'layer': 'Conv2d', 'distribution': 'uniform'}(bbox_head): VFNetHead((loss_cls): VarifocalLoss()(loss_bbox): GIoULoss()(cls_convs): ModuleList((0): ConvModule((conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(gn): GroupNorm(32, 256, eps=1e-05, affine=True)(activate): ReLU(inplace=True))(1): ConvModule((conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(gn): GroupNorm(32, 256, eps=1e-05, affine=True)(activate): ReLU(inplace=True))(2): ConvModule((conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(gn): GroupNorm(32, 256, eps=1e-05, affine=True)(activate): ReLU(inplace=True)))(reg_convs): ModuleList((0): ConvModule((conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(gn): GroupNorm(32, 256, eps=1e-05, affine=True)(activate): ReLU(inplace=True))(1): ConvModule((conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(gn): GroupNorm(32, 256, eps=1e-05, affine=True)(activate): ReLU(inplace=True))(2): ConvModule((conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(gn): GroupNorm(32, 256, eps=1e-05, affine=True)(activate): ReLU(inplace=True)))(relu): ReLU(inplace=True)(vfnet_reg_conv): ConvModule((conv): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)(gn): GroupNorm(32, 256, eps=1e-05, affine=True)(activate): ReLU(inplace=True))(vfnet_reg): Conv2d(256, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(scales): ModuleList((0): Scale()(1): Scale()(2): Scale()(3): Scale()(4): Scale())(vfnet_reg_refine_dconv): DeformConv2d(in_channels=256,out_channels=256,kernel_size=(3, 3),stride=(1, 1),padding=(1, 1),dilation=(1, 1),groups=1,deform_groups=1,deform_groups=False)(vfnet_reg_refine): Conv2d(256, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(scales_refine): ModuleList((0): Scale()(1): Scale()(2): Scale()(3): Scale()(4): Scale())(vfnet_cls_dconv): DeformConv2d(in_channels=256,out_channels=256,kernel_size=(3, 3),stride=(1, 1),padding=(1, 1),dilation=(1, 1),groups=1,deform_groups=1,deform_groups=False)(vfnet_cls): Conv2d(256, 80, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))(loss_bbox_refine): GIoULoss())init_cfg={'type': 'Normal', 'layer': 'Conv2d', 'std': 0.01, 'override': {'type': 'Normal', 'name': 'vfnet_cls', 'std': 0.01, 'bias_prob': 0.01}} )

Varifocal loss:

def varifocal_loss(pred,target,weight=None,alpha=0.75,gamma=2.0,iou_weighted=True,reduction='mean',avg_factor=None):"""`Varifocal Loss <https://arxiv.org/abs/2008.13367>`_Args:pred (torch.Tensor): The prediction with shape (N, C), C is thenumber of classestarget (torch.Tensor): The learning target of the iou-awareclassification score with shape (N, C), C is the number of classes.weight (torch.Tensor, optional): The weight of loss for eachprediction. Defaults to None.alpha (float, optional): A balance factor for the negative part ofVarifocal Loss, which is different from the alpha of Focal Loss.Defaults to 0.75.gamma (float, optional): The gamma for calculating the modulatingfactor. Defaults to 2.0.iou_weighted (bool, optional): Whether to weight the loss of thepositive example with the iou target. Defaults to True.reduction (str, optional): The method used to reduce the loss intoa scalar. Defaults to 'mean'. Options are "none", "mean" and"sum".avg_factor (int, optional): Average factor that is used to averagethe loss. Defaults to None."""# pred and target should be of the same sizeassert pred.size() == target.size()import pdb; pdb.set_trace();pred_sigmoid = pred.sigmoid()target = target.type_as(pred)if iou_weighted:focal_weight = target * (target > 0.0).float() + \alpha * (pred_sigmoid - target).abs().pow(gamma) * \(target <= 0.0).float()else:focal_weight = (target > 0.0).float() + \alpha * (pred_sigmoid - target).abs().pow(gamma) * \(target <= 0.0).float()loss = F.binary_cross_entropy_with_logits(pred, target, reduction='none') * focal_weightloss = weight_reduce_loss(loss, weight, reduction, avg_factor)return loss

總結

以上是生活随笔為你收集整理的【目标检测】cvpr2021_VarifocalNet: An IoU-Aware Dense Object Detector的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。