Improving Autoencoder Training Performance for Hyperspectral Unmixing with Network Reinitialisation
원문 초록
Neural networks, in particular autoencoders, are one of the most promising solutions for unmixing hyperspectral data, i.e. reconstructing the spectra of observed substances (endmembers) and their relative mixing fractions (abundances), which is needed for effective hyperspectral analysis and classification. However, as we show in this paper, the training of autoencoders for unmixing is highly dependent on weights initialisation; some sets of weights lead to degenerate or low-performance solutions, introducing negative bias in the expected performance. In this work, we experimentally investigate autoencoders stability as well as network reinitialisation methods based on coefficients of neurons' dead activations. We demonstrate that the proposed techniques have a positive effect on autoencoder training in terms of reconstruction, abundances and endmembers errors.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
MultiHU-TD: Multifeature Hyperspectral Unmixing Based on Tensor Decomposition
UnMix-NeRF: Spectral Unmixing Meets Neural Radiance Fields
Dual Simplex Volume Maximization for Simplex-Structured Matrix Factorization
Learning Interpretable Deep Disentangled Neural Networks for Hyperspectral Unmixing
Image Processing and Machine Learning for Hyperspectral Unmixing: An Overview and the HySUPP Python Package
Dynamical Hyperspectral Unmixing with Variational Recurrent Neural Networks
토론
이 논문과 연결된 포럼 글이 아직 없습니다.