Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Unsupervised Segmentation of Hyperspectral Images Using 3D Convolutional Autoencoders (1907.08870v1)

Published 20 Jul 2019 in cs.CV

Abstract: Hyperspectral image analysis has become an important topic widely researched by the remote sensing community. Classification and segmentation of such imagery help understand the underlying materials within a scanned scene, since hyperspectral images convey a detailed information captured in a number of spectral bands. Although deep learning has established the state of the art in the field, it still remains challenging to train well-generalizing models due to the lack of ground-truth data. In this letter, we tackle this problem and propose an end-to-end approach to segment hyperspectral images in a fully unsupervised way. We introduce a new deep architecture which couples 3D convolutional autoencoders with clustering. Our multi-faceted experimental study---performed over benchmark and real-life data---revealed that our approach delivers high-quality segmentation without any prior class labels.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Jakub Nalepa (35 papers)
  2. Michal Myller (5 papers)
  3. Yasuteru Imai (1 paper)
  4. Ken-ichi Honda (1 paper)
  5. Tomomi Takeda (1 paper)
  6. Marek Antoniak (1 paper)
Citations (54)

Summary

We haven't generated a summary for this paper yet.