Methods › Computer Vision › Image Model Blocks › Fire Module
Fire Module
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
A Fire Module is a building block for convolutional neural networks, notably used as part of SqueezeNet. A Fire module is comprised of: a squeeze convolution layer (which has only 1x1 filters), feeding into an expand layer that has a mix of 1x1 and 3x3 convolution filters. We expose three tunable dimensions (hyperparameters) in a Fire module: s₁ₓ₁, e₁ₓ₁, and e₃ₓ₃. In a Fire module, s₁ₓ₁ is the number of filters in the squeeze layer (all 1x1), e₁ₓ₁ is the number of 1x1 filters in the expand layer, and e₃ₓ₃ is the number of 3x3 filters in the expand layer. When we use Fire modules we set s₁ₓ₁ to be less than (e₁ₓ₁ + e₃ₓ₃), so the squeeze layer helps to limit the number of input channels to the 3x3 filters.
Papers archive 2025-07-28
30 shown of 95, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Comparative Analysis of Lightweight Deep Learning Models for Memory-Constrained Devices 6 May 2025 · 0 repositories · arXiv:2505.03303
-
Deepfake Detection with Optimized Hybrid Model: EAR Biometric Descriptor via Improved RCNN 16 Mar 2025 · 0 repositories · arXiv:2503.12381
-
Comparison of Neural Models for X-ray Image Classification in COVID-19 Detection 8 Jan 2025 · 0 repositories · arXiv:2501.04196
-
Evaluating Convolutional Neural Networks for COVID-19 classification in chest X-ray images 26 Dec 2024 · 0 repositories · arXiv:2412.19362
-
Improving the network traffic classification using the Packet Vision approach 26 Dec 2024 · 0 repositories · arXiv:2412.19360
-
RNC: Efficient RRAM-aware NAS and Compilation for DNNs on Resource-Constrained Edge Devices 27 Sep 2024 · 1 repository · arXiv:2409.18841
-
Evaluating Deep Learning Models for Breast Cancer Classification: A Comparative Study 29 Aug 2024 · 2 repositories · arXiv:2408.16859
-
Deep Learning for Lung Disease Classification Using Transfer Learning and a Customized CNN Architecture with Attention 23 Aug 2024 · 0 repositories · arXiv:2408.13180
-
Deep Network Pruning: A Comparative Study on CNNs in Face Recognition 28 May 2024 · 0 repositories · arXiv:2405.18302
-
BanglaNum -- A Public Dataset for Bengali Digit Recognition from Speech 20 Mar 2024 · 0 repositories · arXiv:2403.13465
-
Quantization Effects on Neural Networks Perception: How would quantization change the perceptual field of vision models? 15 Mar 2024 · 1 repository · arXiv:2403.09939
-
The Potential of Wearable Sensors for Assessing Patient Acuity in Intensive Care Unit (ICU) 3 Nov 2023 · 0 repositories · arXiv:2311.02251
-
Multi-Transfer Learning Techniques for Detecting Auditory Brainstem Response 29 Aug 2023 · 0 repositories · arXiv:2308.16203
-
SqueezerFaceNet: Reducing a Small Face Recognition CNN Even More Via Filter Pruning 20 Jul 2023 · 0 repositories · arXiv:2307.10697
-
Modulation Classification Through Deep Learning Using Resolution Transformed Spectrograms 6 Jun 2023 · 0 repositories · arXiv:2306.04655
-
PSDNet: Determination of Particle Size Distributions Using Synthetic Soil Images and Convolutional Neural Networks 7 Mar 2023 · 0 repositories · arXiv:2303.04269
-
Use Cases for Time-Frequency Image Representations and Deep Learning Techniques for Improved Signal Classification 22 Feb 2023 · 0 repositories · arXiv:2302.11093
-
Optimization of FPGA-based CNN Accelerators Using Metaheuristics 22 Sep 2022 · 0 repositories · arXiv:2209.11272
-
Land Classification in Satellite Images by Injecting Traditional Features to CNN Models 21 Jul 2022 · 0 repositories · arXiv:2207.10368
-
Gator: Customizable Channel Pruning of Neural Networks with Gating 30 May 2022 · 1 repository · arXiv:2205.15404
-
Object Detection with Spiking Neural Networks on Automotive Event Data 9 May 2022 · 1 repository · arXiv:2205.04339Syntology ran 1 of 1 samples · 0 unverified
-
Detecting Violence in Video Based on Deep Features Fusion Technique 15 Apr 2022 · 0 repositories · arXiv:2204.07443
-
Quantune: Post-training Quantization of Convolutional Neural Networks using Extreme Gradient Boosting for Fast Deployment 10 Feb 2022 · 1 repository · arXiv:2202.05048
-
Asian Giant Hornet Control based on Image Processing and Biological Dispersal 26 Nov 2021 · 0 repositories · arXiv:2111.13562
-
A methodology for training homomorphicencryption friendly neural networks 5 Nov 2021 · 0 repositories · arXiv:2111.03362
-
Object Disparity 18 Aug 2021 · 0 repositories · arXiv:2108.07939
-
Pre-trained Models for Sonar Images 2 Aug 2021 · 1 repository · arXiv:2108.01111
-
An Efficient and Small Convolutional Neural Network for Pest Recognition -- ExquisiteNet 15 Jul 2021 · 0 repositories · arXiv:2107.07167
-
HEMET: A Homomorphic-Encryption-Friendly Privacy-Preserving Mobile Neural Network Architecture 31 May 2021 · 0 repositories · arXiv:2106.00038
-
Convolutional neural networks for Alzheimer’s disease detection on MRI images 29 Apr 2021 · 1 repository
Tasks archive 2025-07-28
20 shown of 90 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections