FLIM Networks with Bag of Feature Points

• URL: http://arxiv.org/abs/2602.20845v1
• Date: Tue, 24 Feb 2026 12:36:22 GMT
• Title: 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,
• Abstract summary: Feature Learning from Image Markers (FLIM) estimates encoder filters from user-drawn markers on discriminative regions of a few representative images without backpropagation.<n>FLIM-Bag of Feature Points (FLIM-BoFP) is a considerably faster filter estimation method.
• Score: 37.246787461927525
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• LMPNet for Weakly-supervised Keypoint Discovery [2.033434950296318]
  We explore the task of semantic object keypoint discovery weakly-supervised by only category labels.<n>This is achieved by transforming discriminatively-trained intermediate layer filters into keypoint detectors.<n>Experiments show that LMPNet can (i) automatically discover semantic keypoints that are robust to object pose and (ii) achieves strong prediction accuracy comparable to a supervised pose estimation model.
  arXiv  Detail & Related papers  (2025-07-03T04:36:03Z)
• Visual Multi-Object Tracking with Re-Identification and Occlusion Handling using Labeled Random Finite Sets [10.618186767487993]
  This paper proposes an online visual multi-object tracking (MOT) algorithm that resolves object appearance-reappearance and occlusion. Our solution is based on the labeled random finite set (LRFS) filtering approach. We propose a fuzzy detection model that takes into consideration the overlapping areas between tracks and their sizes.
  arXiv  Detail & Related papers  (2024-07-11T21:15:21Z)
• Building Brain Tumor Segmentation Networks with User-Assisted Filter Estimation and Selection [42.62139206176152]
  We present Multi-Step (MS) FLIM, a user-assisted approach to estimating and selecting the most relevant filters from multiple FLIM executions. MS-FLIM is used only for the first convolutional layer, and the results already indicate improvement over FLIM. We build a simple U-shaped encoder-decoder network, named sU-Net, for glioblastoma segmentation using T1Gd and FLAIR MRI scans.
  arXiv  Detail & Related papers  (2024-03-19T14:11:26Z)
• Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler [103.97487121678276]
  Filter pruning simultaneously accelerates the computation and reduces the memory overhead of CNNs. We propose a novel Knowledge-driven Differential Filter Sampler(KDFS) with Masked Filter Modeling(MFM) framework for filter pruning.
  arXiv  Detail & Related papers  (2023-07-01T02:28:41Z)
• Asymptotic Soft Cluster Pruning for Deep Neural Networks [5.311178623385279]
  Filter pruning method introduces structural sparsity by removing selected filters. We propose a novel filter pruning method called Asymptotic Soft Cluster Pruning. Our method can achieve competitive results compared with many state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2022-06-16T13:58:58Z)
• Batch Normalization Tells You Which Filter is Important [49.903610684578716]
  We propose a simple yet effective filter pruning method by evaluating the importance of each filter based on the BN parameters of pre-trained CNNs. The experimental results on CIFAR-10 and ImageNet demonstrate that the proposed method can achieve outstanding performance.
  arXiv  Detail & Related papers  (2021-12-02T12:04:59Z)
• Unsharp Mask Guided Filtering [53.14430987860308]
  The goal of this paper is guided image filtering, which emphasizes the importance of structure transfer during filtering. We propose a new and simplified formulation of the guided filter inspired by unsharp masking. Our formulation enjoys a filtering prior to a low-pass filter and enables explicit structure transfer by estimating a single coefficient.
  arXiv  Detail & Related papers  (2021-06-02T19:15:34Z)
• Data Agnostic Filter Gating for Efficient Deep Networks [72.4615632234314]
  Current filter pruning methods mainly leverage feature maps to generate important scores for filters and prune those with smaller scores. In this paper, we propose a data filter pruning method that uses an auxiliary network named Dagger module to induce pruning. In addition, to help prune filters with certain FLOPs constraints, we leverage an explicit FLOPs-aware regularization to directly promote pruning filters toward target FLOPs.
  arXiv  Detail & Related papers  (2020-10-28T15:26:40Z)
• iffDetector: Inference-aware Feature Filtering for Object Detection [70.8678270164057]
  We introduce a generic Inference-aware Feature Filtering (IFF) module that can easily be combined with modern detectors. IFF performs closed-loop optimization by leveraging high-level semantics to enhance the convolutional features. IFF can be fused with CNN-based object detectors in a plug-and-play manner with negligible computational cost overhead.
  arXiv  Detail & Related papers  (2020-06-23T02:57:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.