|国家预印本平台
首页|Building Flyweight FLIM-based CNNs with Adaptive Decoding for Object Detection

Building Flyweight FLIM-based CNNs with Adaptive Decoding for Object Detection

Building Flyweight FLIM-based CNNs with Adaptive Decoding for Object Detection

来源:Arxiv_logoArxiv
英文摘要

State-of-the-art (SOTA) object detection methods have succeeded in several applications at the price of relying on heavyweight neural networks, which makes them inefficient and inviable for many applications with computational resource constraints. This work presents a method to build a Convolutional Neural Network (CNN) layer by layer for object detection from user-drawn markers on discriminative regions of representative images. We address the detection of Schistosomiasis mansoni eggs in microscopy images of fecal samples, and the detection of ships in satellite images as application examples. We could create a flyweight CNN without backpropagation from very few input images. Our method explores a recent methodology, Feature Learning from Image Markers (FLIM), to build convolutional feature extractors (encoders) from marker pixels. We extend FLIM to include a single-layer adaptive decoder, whose weights vary with the input image -- a concept never explored in CNNs. Our CNN weighs thousands of times less than SOTA object detectors, being suitable for CPU execution and showing superior or equivalent performance to three methods in five measures.

Alexandre Xavier Falcao、Bianca Martins dos Santos、Leonardo de Melo Joao、Azael de Melo e Sousa、Silvio Jamil Ferzoli Guimaraes、Jancarlo Ferreira Gomes、Ewa Kijak

计算技术、计算机技术生物科学现状、生物科学发展生物科学研究方法、生物科学研究技术

Alexandre Xavier Falcao,Bianca Martins dos Santos,Leonardo de Melo Joao,Azael de Melo e Sousa,Silvio Jamil Ferzoli Guimaraes,Jancarlo Ferreira Gomes,Ewa Kijak.Building Flyweight FLIM-based CNNs with Adaptive Decoding for Object Detection[EB/OL].(2023-06-26)[2025-08-02].https://arxiv.org/abs/2306.14840.点此复制

评论