FLIM Networks with Bag of Feature Points
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913153371078656 |
|---|---|
| author | Martinelli, João Deltregia Filho, Marcelo Luis Rodrigues Salvagnini, Felipe Crispim da Rocha Soares, Gilson Junior Santos, Jefersson A. dos Falcão, Alexandre X. |
| author_facet | Martinelli, João Deltregia Filho, Marcelo Luis Rodrigues Salvagnini, Felipe Crispim da Rocha Soares, Gilson Junior Santos, Jefersson A. dos Falcão, Alexandre X. |
| contents | Convolutional networks require extensive image annotation, which can be costly and time-consuming. Feature Learning from Image Markers (FLIM) tackles this challenge by estimating encoder filters (i.e., kernel weights) from user-drawn markers on discriminative regions of a few representative images without traditional optimization. Such an encoder combined with an adaptive decoder comprises a FLIM network fully trained without backpropagation. Prior research has demonstrated their effectiveness in Salient Object Detection (SOD), being significantly lighter than existing lightweight models. This study revisits FLIM SOD and introduces FLIM-Bag of Feature Points (FLIM-BoFP), a considerably faster filter estimation method. The previous approach, FLIM-Cluster, derives filters through patch clustering at each encoder's block, leading to computational overhead and reduced control over filter locations. FLIM-BoFP streamlines this process by performing a single clustering at the input block, creating a bag of feature points, and defining filters directly from mapped feature points across all blocks. The paper evaluates the benefits in efficiency, effectiveness, and generalization of FLIM-BoFP compared to FLIM-Cluster and other state-of-the-art baselines for parasite detection in optical microscopy images. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_20845 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FLIM Networks with Bag of Feature Points Martinelli, João Deltregia Filho, Marcelo Luis Rodrigues Salvagnini, Felipe Crispim da Rocha Soares, Gilson Junior Santos, Jefersson A. dos Falcão, Alexandre X. Computer Vision and Pattern Recognition Convolutional networks require extensive image annotation, which can be costly and time-consuming. Feature Learning from Image Markers (FLIM) tackles this challenge by estimating encoder filters (i.e., kernel weights) from user-drawn markers on discriminative regions of a few representative images without traditional optimization. Such an encoder combined with an adaptive decoder comprises a FLIM network fully trained without backpropagation. Prior research has demonstrated their effectiveness in Salient Object Detection (SOD), being significantly lighter than existing lightweight models. This study revisits FLIM SOD and introduces FLIM-Bag of Feature Points (FLIM-BoFP), a considerably faster filter estimation method. The previous approach, FLIM-Cluster, derives filters through patch clustering at each encoder's block, leading to computational overhead and reduced control over filter locations. FLIM-BoFP streamlines this process by performing a single clustering at the input block, creating a bag of feature points, and defining filters directly from mapped feature points across all blocks. The paper evaluates the benefits in efficiency, effectiveness, and generalization of FLIM-BoFP compared to FLIM-Cluster and other state-of-the-art baselines for parasite detection in optical microscopy images. |
| title | FLIM Networks with Bag of Feature Points |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.20845 |