In this paper, we focus on scaling and we aim to equip the Siamese network with additional built-in scale equivariance to capture the natural variations of the target a priori. We develop the theory for scale-equivariant Siamese trackers, and provide a simple recipe for how to make a wide ...
The convolutional neural network (CNN) has achieved good performance in object classification due to its inherent translation equivariance, but its scale equivariance is poor. A Scale-Aware Network (SA Net) with scale equivariance is proposed to estimate the scale during classification. The SA Net ...
Scale Equivariance Improves Siamese Trackingdoi:10.1109/WACV48630.2021.00281Ivan SosnovikArtem MoskalevArnold SmeuldersIEEEWorkshop on Applications of Computer Vision
Kemp, G. (1996),"Scale equivariance and the Box‐Cox transformation", Economics Letters, Vol.51, pp.1‐6.Kemp, G. C. R. (1996). Scale equivariance and the Box- Cox transformation, EConomics Letters, 51, 1-6....