Continual Local Replacement for Few-shot Learning

no code implementations • 23 Jan 2020 • Canyu Le, Zhonggui Chen, Xihan Wei, Biao Wang, Lei Zhang

The goal of few-shot learning is to learn a model that can recognize novel classes based on one or few training data.

Few-Shot Learning General Classification

Learning Continually from Low-shot Data Stream

no code implementations • 27 Aug 2019 • Canyu Le, Xihan Wei, Biao Wang, Lei Zhang, Zhonggui Chen

To solve these two limits, the deep learning model should not only be able to learn from a few of data, but also incrementally learn new concepts from data stream over time without forgetting the previous knowledge.

Image Classification

Fast Regularity-Constrained Plane Reconstruction

no code implementations • 20 May 2019 • Yangbin Lin, Jialian Li, Cheng Wang, Zhonggui Chen, Zongyue Wang, Jonathan Li

Man-made environments typically comprise planar structures that exhibit numerous geometric relationships, such as parallelism, coplanarity, and orthogonality.

Texture Relative Superpixel Generation With Adaptive Parameters

no code implementations • IEEE 2019 • Xiao Pan, Yuanfeng Zhou, Zhonggui Chen, Caiming Zhang

Abstract—Superpixel generation, which is an essential step in many image processing applications, has attracted increasing attention from researchers.

Superpixels