This paper detailed the engineering system implementation of an automated machine learning system called YMIR, which completely relies on graphical interface to interact with users.
Experiment results show that the proposed EdgeFormer achieves better performance than popular light-weight ConvNets and vision transformer based models in common vision tasks and datasets, while having fewer parameters and faster inference speed.
Ranked #442 on Image Classification on ImageNet
This paper introduces an open source platform to support the rapid development of computer vision applications at scale.
Specifically, based on transformer, we propose a new network structure to compress the feature into a low dimensional space, and an inhomogeneous neighborhood relationship preserving (INRP) loss that aims to maintain high search accuracy.
Given a set of unannotated training images, a dictionary of such hierarchical templates are learned so that each training image can be represented by a small number of templates that are spatially translated, rotated and scaled versions of the templates in the learned dictionary.
We investigate an inhomogeneous version of the FRAME (Filters, Random field, And Maximum Entropy) model and apply it to modeling object patterns.