cs.CVFeb 24, 2026

FLIM Networks with Bag of Feature Points

Authors: João Deltregia Martinelli, Marcelo Luis Rodrigues Filho, Felipe Crispim da Rocha Salvagnini, Gilson Junior Soares, Jefersson A. dos Santos, Alexandre X. Falcão

Organizations: Institute of Computing UNICAMP Campinas, Brazil · School of Computer Science University of Sheffield Sheffield, United Kingdom

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

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.

Figures & tables

Figure 1: Training pipeline of a FLIM SOD Network from user-drawn markers on three representative images. In this example, the markers are red disks on the object ( Schistosoma Mansoni eggs) and white disks on the background (impurities and empty region).
Figure 2: Progressive saliency maps by decoding consecutive blocks. Figures 2(a) and 2(f) show the original and groundtruth images, respectively. Saliency maps obtained by decoding the output of blocks 1-4 for FLIM-BoFP in 2(b) - 2(e) and FLIM-Cluster in 2(g) - 2(j) .
Figure 3: Training of a FLIM encoder with BoFP begins with a single clustering-based feature point estimation to insert discriminative image locations in the BoFP. Filters for each block are then directly derived from mapped points in the feature map at the block’s input, ensuring precise filter placement and efficient processing.
Figure 4: Average F-measure curves across splits on test sets for each model. Figure 4(a) compares FLIM models with and without DT post-processing for S. Mansoni . Figure 4(b) contrasts FLIM DT models against deep-learning models on S. Mansoni , with the FLIM models at the top.
Figure 5: Qualitative detection results on test images of the S. Mansoni , Entamoeba and Ancylostoma datasets. GT is the ground-truth segmentation mask.
More in this topic

Salient Object Detection

Salient Object Detection finds visually prominent objects in images or video and predicts their pixel-level foreground masks.

See all 37 papers

Explore similar work

CardsList

  1. Beyond Classification: Pathology Foundation Models as Detection Encoders for Mitotic Figures

    Jul 30, 2026Sweta Banerjee, Alireza Teimoury, Nils Porsche +11Computational PathologyPathology Foundation Models

    Flensburg University of Applied Sciences, Flensburg, Germany · Julius-Maximilians-Universität Würzburg, Würzburg, Germany · Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany +4

  2. AnyDepth-DETR/-YOLO: Any-depth object detection with a single network

    May 10, 2026Woochul Kang, Hyungseop Lee, Jiho LeeEfficient Neural Network InferenceDynamic Neural Networks

    Incheon Nat’l Univ.

  3. Object Detection Based on Distributed Convolutional Neural Networks

    Mar 30, 2026Liang SunObject DetectionConvolutional Neural Networks

    Shandong University of Science and Technology, Jinan, 250031 P.R. China