# FLIM Networks with Bag of Feature Points

arXiv: https://arxiv.org/abs/2602.20845 · HTML: https://mlsanity.com/paper/2602.20845/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 21 references that are in the map.
- First posted on arXiv 24 Feb 2026.

## Builds on (most cited first, 8 of 8)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection](https://mlsanity.com/paper/2005.09007/) (2020)
- [AutoML: A Survey of the State-of-the-Art](https://mlsanity.com/paper/1908.00709/) (2019)
- [Lightweight Salient Object Detection in Optical Remote-Sensing Images via Semantic Matching and Edge Alignment](https://mlsanity.com/paper/2301.02778/) (2023)
- [Learning CNN filters from user-drawn image markers for coconut-tree image classification](https://mlsanity.com/paper/2008.03549/) (2020)
- [Building Flyweight FLIM-based CNNs with Adaptive Decoding for Object Detection](https://mlsanity.com/paper/2306.14840/) (2023)
- [Multi-level Cellular Automata for FLIM networks](https://mlsanity.com/paper/2504.11406/) (2025)
- [FLIM-based Salient Object Detection Networks with Adaptive Decoders](https://mlsanity.com/paper/2504.20872/) (2025)

## Abstract (arXiv)

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.