.png){kind=icon}
.png){kind=icon}
Return
A Robust Visual Tracking Method Based on Reconstruction Patch Transformer Tracking
.png){kind=icon}
OA
AI
DOI：10.3390/s22176558.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Recently, the transformer model has progressed from the field of visual classification to target tracking. Its primary method replaces the cross-correlation operation in the Siamese tracker. The backbone of the network is still a convolutional neural network (CNN). However, the existing transformer-based tracker simply deforms the features extracted by the CNN into patches and feeds them into the transformer encoder. Each patch contains a single element of the spatial dimension of the extracted features and inputs into the transformer structure to use cross-attention instead of cross-correlation operations. This paper proposes a reconstruction patch strategy which combines the extracted features with multiple elements of the spatial dimension into a new patch. The reconstruction operation has the following advantages: (1) the correlation between adjacent elements combines well, and the features extracted by the CNN are usable for classification and regression; (2) using the performer operation reduces the amount of network computation and the dimension of the patch sent to the transformer, thereby sharply reducing the network parameters and improving the model-tracking speed.
Keywords:
transformer
cross-attention
CNN
transformer-based tracker
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.