Biologically-inspired Semi-supervised Semantic Segmentation for Biomedical Imaging
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913743530622976 |
|---|---|
| author | Ciampi, Luca Lagani, Gabriele Amato, Giuseppe Falchi, Fabrizio |
| author_facet | Ciampi, Luca Lagani, Gabriele Amato, Giuseppe Falchi, Fabrizio |
| contents | We propose a novel bio-inspired semi-supervised learning approach for training downsampling-upsampling semantic segmentation architectures. The first stage does not use backpropagation. Rather, it exploits the Hebbian principle ``fire together, wire together'' as a local learning rule for updating the weights of both convolutional and transpose-convolutional layers, allowing unsupervised discovery of data features. In the second stage, the model is fine-tuned with standard backpropagation on a small subset of labeled data. We evaluate our methodology through experiments conducted on several widely used biomedical datasets, deeming that this domain is paramount in computer vision and is notably impacted by data scarcity. Results show that our proposed method outperforms SOTA approaches across different levels of label availability. Furthermore, we show that using our unsupervised stage to initialize the SOTA approaches leads to performance improvements. The code to replicate our experiments can be found at https://github.com/ciampluca/hebbian-bootstraping-semi-supervised-medical-imaging |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_03192 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Biologically-inspired Semi-supervised Semantic Segmentation for Biomedical Imaging Ciampi, Luca Lagani, Gabriele Amato, Giuseppe Falchi, Fabrizio Computer Vision and Pattern Recognition We propose a novel bio-inspired semi-supervised learning approach for training downsampling-upsampling semantic segmentation architectures. The first stage does not use backpropagation. Rather, it exploits the Hebbian principle ``fire together, wire together'' as a local learning rule for updating the weights of both convolutional and transpose-convolutional layers, allowing unsupervised discovery of data features. In the second stage, the model is fine-tuned with standard backpropagation on a small subset of labeled data. We evaluate our methodology through experiments conducted on several widely used biomedical datasets, deeming that this domain is paramount in computer vision and is notably impacted by data scarcity. Results show that our proposed method outperforms SOTA approaches across different levels of label availability. Furthermore, we show that using our unsupervised stage to initialize the SOTA approaches leads to performance improvements. The code to replicate our experiments can be found at https://github.com/ciampluca/hebbian-bootstraping-semi-supervised-medical-imaging |
| title | Biologically-inspired Semi-supervised Semantic Segmentation for Biomedical Imaging |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.03192 |