Search Results for author: Insu Lee

Found 1 papers, 0 papers with code

Expand-and-Quantize: Unsupervised Semantic Segmentation Using High-Dimensional Space and Product Quantization

no code implementations12 Dec 2023 Jiyoung Kim, Kyuhong Shim, Insu Lee, Byonghyo Shim

In this paper, we propose a novel USS framework called Expand-and-Quantize Unsupervised Semantic Segmentation (EQUSS), which combines the benefits of high-dimensional spaces for better clustering and product quantization for effective information compression.

Clustering Dimensionality Reduction +3

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