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

arXiv: https://arxiv.org/abs/2306.14840 · HTML: https://mlsanity.com/paper/2306.14840/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 33 references that are in the map.
- First posted on arXiv 26 Jun 2023.

## Builds on (most cited first, 19 of 19)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network](https://mlsanity.com/paper/1609.05158/) (2016)
- [U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection](https://mlsanity.com/paper/2005.09007/) (2020)
- [Deep Learning for Generic Object Detection: A Survey](https://mlsanity.com/paper/1809.02165/) (2018)
- [Few-shot Object Detection via Feature Reweighting](https://mlsanity.com/paper/1812.01866/) (2018)
- [Meta R-CNN : Towards General Solver for Instance-level Few-shot Learning](https://mlsanity.com/paper/1909.13032/) (2019)
- [Salient Object Detection in the Deep Learning Era: An In-Depth Survey](https://mlsanity.com/paper/1904.09146/) (2019)
- [Unsupervised Learning of Dense Visual Representations](https://mlsanity.com/paper/2011.05499/) (2020)
- [Multi-Scale Positive Sample Refinement for Few-Shot Object Detection](https://mlsanity.com/paper/2007.09384/) (2020)
- [Aligning Pretraining for Detection via Object-Level Contrastive Learning](https://mlsanity.com/paper/2106.02637/) (2021)
- [Instance Localization for Self-supervised Detection Pretraining](https://mlsanity.com/paper/2102.08318/) (2021)
- [A Survey of Modern Deep Learning based Object Detection Models](https://mlsanity.com/paper/2104.11892/) (2021)
- [DETReg: Unsupervised Pretraining with Region Priors for Object Detection](https://mlsanity.com/paper/2106.04550/) (2021)
- [A Survey of Self-Supervised and Few-Shot Object Detection](https://mlsanity.com/paper/2110.14711/) (2021)
- [SelfReformer: Self-Refined Network with Transformer for Salient Object Detection](https://mlsanity.com/paper/2205.11283/) (2022)
- [Learning CNN filters from user-drawn image markers for coconut-tree image classification](https://mlsanity.com/paper/2008.03549/) (2020)
- [CNN Filter Learning from Drawn Markers for the Detection of Suggestive Signs of COVID-19 in CT Images](https://mlsanity.com/paper/2111.08710/) (2021)

## Built on by (most cited first, 1 of 1)

- [FLIM Networks with Bag of Feature Points](https://mlsanity.com/paper/2602.20845/) (2026)

## Abstract (arXiv)

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.