KS-DETR: Knowledge Sharing in Attention Learning for Detection Transformer

1 code implementation • 22 Feb 2023 • Kaikai Zhao, Norimichi Ukita

We propose a triple-attention module in which the first attention is a plain scaled dot-product attention, the second/third attention generates high-quality weights/values (with the assistance of GT Fg-Bg Mask) and shares the values/weights with the first attention to improve the quality of values/weights.

Knowledge Distillation Transfer Learning

Application-Driven AI Paradigm for Human Action Recognition

no code implementations • 30 Sep 2022 • Zezhou Chen, Yajie Cui, Kaikai Zhao, Zhaoxiang Liu, Shiguo Lian

Human action recognition in computer vision has been widely studied in recent years.

Action Classification Action Recognition +2

A Waste Copper Granules Rating System Based on Machine Vision

no code implementations • 11 Jul 2022 • Kaikai Zhao, Yajie Cui, Zhaoxiang Liu, Shiguo Lian

Our rating network includes a segmentation network and a purity regression network, which respectively calculate the semantic segmentation heatmaps and purity results of the waste copper granules.

regression Segmentation +1

ESmodels: An Epistemic Specification Solver

no code implementations • 14 May 2014 • Zhizheng Zhang, Kaikai Zhao

(To appear in Theory and Practice of Logic Programming (TPLP)) ESmodels is designed and implemented as an experiment platform to investigate the semantics, language, related reasoning algorithms, and possible applications of epistemic specifications. We first give the epistemic specification language of ESmodels and its semantics.