全卷积暹罗网络：提升实时对象跟踪性能 - CSDN文库

163 浏览量更新于2024-06-15 收藏 1.73MB PDF 举报

身份认证购VIP最低享 7 折!

领优惠券(最高得80元）

资源详情

资源推荐

4 L. Bertinetto, J. Valmadre, J. F. Henriques, A. Vedaldi, P. H. S. Torr

where b

1

denotes a signal which takes value b ∈ R in every location. The output

of this network is not a single score but rather a score map deﬁned on a ﬁnite

grid D ⊂ Z

2

as illustrated in Figure 1. Note that the output of the embedding

function is a feature map with spatial support as opposed to a plain vector. The

same technique has been applied in contemporary work on stereo matching [23].

During tracking, we use a search image centred at the previous position of

the target. The position of the maximum score relative to the centre of the

score map, multiplied by the stride of the network, gives the displacement of the

target from frame to frame. Multiple scales are searched in a single forward-pass

by assembling a mini-batch of scaled images.

Combining feature maps using cross-correlation and evaluating the network

once on the larger search image is mathematically equivalent to combining fea-

ture maps using the inner product and evaluating the network on each translated

sub-window independently. However, the cross-correlation layer provides an in-

credibly simple method to implement this operation eﬃciently within the frame-

work of existing conv-net libraries. While this is clearly useful during testing, it

can also be exploited during training.

2.2 Training with large search images

We employ a discriminative approach, training the network on positive and

negative pairs and adopting the logistic loss

`(y, v) = log(1 + exp(−yv)) (3)

where v is the real-valued score of a single exemplar-candidate pair and y ∈

{+1, −1} is its ground-truth label. We exploit the fully-convolutional nature of

our network during training by using pairs that comprise an exemplar image and

a larger search image. This will produce a map of scores v : D → R, eﬀectively

generating many examples per pair. We deﬁne the loss of a score map to be the

mean of the individual losses

L(y, v) =

1

|D|

X

u∈D

`(y[u], v[u]) , (4)

requiring a true label y[u] ∈ {+1, −1} for each position u ∈ D in the score map.

The parameters of the conv-net θ are obtained by applying Stochastic Gradient

Descent (SGD) to the problem

arg min

θ

E

(z,x,y)

L(y, f(z, x; θ)) . (5)

Pairs are obtained from a dataset of annotated videos by extracting exemplar

and search images that are centred on the target, as shown in Figure 2. The

images are extracted from two frames of a video that both contain the object

and are at most T frames apart. The class of the object is ignored during training.

The scale of the object within each image is normalized without corrupting the

剩余15页未读，继续阅读

初心不忘产学研

粉丝: 5390
资源: 180

会员权益专享

图片转文字

全年可省5，000元立即开通

最新资源

资源上传下载、课程学习等过程中有任何疑问或建议，欢迎提出宝贵意见哦~我们会及时处理！点击此处反馈