Search Results for author: Zilong Ji

Found 7 papers, 1 papers with code

An Attention-driven Two-stage Clustering Method for Unsupervised Person Re-Identification

no code implementations ECCV 2020 Zilong Ji, Xiaolong Zou, Xiaohan Lin, Xiao Liu, Tiejun Huang, Si Wu

By iteratively learning with the two strategies, the attentive regions are gradually shifted from the background to the foreground and the features become more discriminative.

Clustering Unsupervised Person Re-Identification

Noisy Adaptation Generates Lévy Flights in Attractor Neural Networks

no code implementations NeurIPS 2021 Xingsi Dong, Tianhao Chu, Tiejun Huang, Zilong Ji, Si Wu

To elucidate the underlying mechanism clearly, we first study continuous attractor neural networks (CANNs), and find that noisy neural adaptation, exemplified by spike frequency adaptation (SFA) in this work, can generate Lévy flights representing transitions of the network state in the attractor space.

Retrieval

Vision at A Glance: Interplay between Fine and Coarse Information Processing Pathways

no code implementations23 Aug 2020 Zilong Ji, Xiaolong Zou, Tiejun Huang, Si Wu

In this study, we build a computational model to elucidate the computational advantages associated with the interactions between two pathways.

Object Recognition

Unsupervised Few-shot Learning via Self-supervised Training

no code implementations20 Dec 2019 Zilong Ji, Xiaolong Zou, Tiejun Huang, Si Wu

The proposed model consists of two alternate processes, progressive clustering and episodic training.

BIG-bench Machine Learning Clustering +3

Unsupervised Few Shot Learning via Self-supervised Training

no code implementations25 Sep 2019 Zilong Ji, Xiaolong Zou, Tiejun Huang, Si Wu

Using the benchmark dataset Omniglot, we show that our model outperforms other unsupervised few-shot learning methods to a large extend and approaches to the performances of supervised methods.

Person Re-Identification Unsupervised Few-Shot Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.