Methods › General › Activation Functions › ReLU6
ReLU6
Introduced by Andrew G. Howard et al. in MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
ReLU6 is a modification of the rectified linear unit where we limit the activation to a maximum size of $6$. This is due to increased robustness when used with low-precision computation.
Image Credit: PyTorch
In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 95 · with a code link: 50 · where Syntology ran a sample: 18 (18 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (18 of 95 tagged: 18 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 95 of 95, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
Comparative Analysis of Lightweight Deep Learning Models for Memory-Constrained Devices 6 May 2025 · 0 repositories · arXiv:2505.03303
-
VeLU: Variance-enhanced Learning Unit for Deep Neural Networks 21 Apr 2025 · 0 repositories · arXiv:2504.15051
-
Time Frequency Analysis of EMG Signal for Gesture Recognition using Fine grained Features 20 Apr 2025 · 0 repositories · arXiv:2504.14708
-
A Light Perspective for 3D Object Detection 10 Mar 2025 · 0 repositories · arXiv:2503.07133
-
Pulmonary Tuberculosis Edge Diagnosis System Based on MindSpore Framework: Low-cost and High-precision Implementation with Ascend 310 Chip 15 Feb 2025 · 0 repositories · arXiv:2502.14885
-
HyperCam: Low-Power Onboard Computer Vision for IoT Cameras 17 Jan 2025 · 0 repositories · arXiv:2501.10547
-
Revolutionizing Communication with Deep Learning and XAI for Enhanced Arabic Sign Language Recognition 14 Jan 2025 · 0 repositories · arXiv:2501.08169
-
Scalable Forward-Forward Algorithm 6 Jan 2025 · 0 repositories · arXiv:2501.03176
-
Towards Efficient IMC Accelerator Design Through Joint Hardware-Workload Co-optimization 22 Oct 2024 · 0 repositories · arXiv:2410.16759
-
Efficient Deep Learning Board: Training Feedback Is Not All You Need 17 Oct 2024 · 0 repositories · arXiv:2410.14743
-
Real-time Monitoring of Lower Limb Movement Resistance Based on Deep Learning 13 Oct 2024 · 0 repositories · arXiv:2410.19769
-
POMONAG: Pareto-Optimal Many-Objective Neural Architecture Generator 30 Sep 2024 · 0 repositories · arXiv:2409.20447
-
RNC: Efficient RRAM-aware NAS and Compilation for DNNs on Resource-Constrained Edge Devices 27 Sep 2024 · 1 repository · arXiv:2409.18841
-
PlainUSR: Chasing Faster ConvNet for Efficient Super-Resolution 20 Sep 2024 · 1 repository · arXiv:2409.13435
-
WaterMAS: Sharpness-Aware Maximization for Neural Network Watermarking 5 Sep 2024 · 0 repositories · arXiv:2409.03902
-
Analysis of Modern Computer Vision Models for Blood Cell Classification 30 Jun 2024 · 1 repository · arXiv:2407.00759
-
HASS: Hardware-Aware Sparsity Search for Dataflow DNN Accelerator 5 Jun 2024 · 1 repository · arXiv:2406.03088
-
Vision-Based Approach for Food Weight Estimation from 2D Images 26 May 2024 · 0 repositories · arXiv:2405.16478
-
Impact of Synthetic Images on Morphing Attack Detection Using a Siamese Network 14 Mar 2024 · 0 repositories · arXiv:2403.09380
-
A New Machine Learning Dataset of Bulldog Nostril Images for Stenosis Degree Classification 11 Mar 2024 · 0 repositories · arXiv:2403.07132
-
Multi-objective Differentiable Neural Architecture Search 28 Feb 2024 · 1 repository · arXiv:2402.18213
-
Model Evaluation for Domain Identification of Unknown Classes in Open-World Recognition: A Proposal 9 Dec 2023 · 0 repositories · arXiv:2312.05454
-
Learning Cortical Anomaly through Masked Encoding for Unsupervised Heterogeneity Mapping 5 Dec 2023 · 1 repository · arXiv:2312.02762
-
A Reusable AI-Enabled Defect Detection System for Railway Using Ensembled CNN 24 Nov 2023 · 0 repositories · arXiv:2311.14824
-
Unleashing Modified Deep Learning Models in Efficient COVID19 Detection 21 Oct 2023 · 0 repositories · arXiv:2310.14081
-
On-Chip Hardware-Aware Quantization for Mixed Precision Neural Networks 5 Sep 2023 · 0 repositories · arXiv:2309.01945
-
A Lightweight and Accurate Face Detection Algorithm Based on Retinaface 8 Aug 2023 · 0 repositories · arXiv:2308.04340
-
RepViT: Revisiting Mobile CNN From ViT Perspective 18 Jul 2023 · 8 repositories · arXiv:2307.09283Syntology 6 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 3 where Syntology's instrument failed) · 6 unverified (of 12 harvested samples) · 5 pointer-only (licence)
-
An open-source deep learning algorithm for efficient and fully-automatic analysis of the choroid in optical coherence tomography 3 Jul 2023 · 1 repository · arXiv:2307.00904
-
End-to-End Neural Network Compression via ℓ₁/ℓ₂ Regularized Latency Surrogates 9 Jun 2023 · 0 repositories · arXiv:2306.05785
-
DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models 26 May 2023 · 1 repository · arXiv:2305.16943Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples) · 3 pointer-only (licence)
-
Combining Multi-Objective Bayesian Optimization with Reinforcement Learning for TinyML 23 May 2023 · 0 repositories · arXiv:2305.14109
-
Advancing Ischemic Stroke Diagnosis: A Novel Two-Stage Approach for Blood Clot Origin Identification 26 Apr 2023 · 0 repositories · arXiv:2304.13775
-
LayerNAS: Neural Architecture Search in Polynomial Complexity 23 Apr 2023 · 0 repositories · arXiv:2304.11517
-
Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement 15 Mar 2023 · 1 repository · arXiv:2303.08983
-
A General-Purpose Transferable Predictor for Neural Architecture Search 21 Feb 2023 · 0 repositories · arXiv:2302.10835
-
Trainable Activations for Image Classification 26 Jan 2023 · 1 repository
-
M3E-Yolo: A New Lightweight Network for Traffic Sign Recognition 19 Jan 2023 · 0 repositories
-
MobileTL: On-device Transfer Learning with Inverted Residual Blocks 5 Dec 2022 · 0 repositories · arXiv:2212.03246
-
Receptive Field Refinement for Convolutional Neural Networks Reliably Improves Predictive Performance 26 Nov 2022 · 0 repositories · arXiv:2211.14487
-
RepGhost: A Hardware-Efficient Ghost Module via Re-parameterization 11 Nov 2022 · 3 repositories · arXiv:2211.06088Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified (of 17 harvested samples)
-
Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation 9 Nov 2022 · 2 repositories · arXiv:2211.04772Syntology community repositories only · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 1 pointer-only (licence)
-
Vitruvio: 3D Building Meshes via Single Perspective Sketches 24 Oct 2022 · 1 repository · arXiv:2210.13634
-
Neural Network Compression by Joint Sparsity Promotion and Redundancy Reduction 14 Oct 2022 · 0 repositories · arXiv:2210.07451
-
Multiclass ASMA vs Targeted PGD Attack in Image Segmentation 3 Aug 2022 · 0 repositories · arXiv:2208.01844
-
A Real-time Fire Segmentation Method Based on A Deep Learning Approach 22 Jul 2022 · 1 repository
-
Improved lightweight identification of agricultural diseases based on MobileNetV3 19 Jul 2022 · 0 repositories · arXiv:2207.11238
-
Grouped Pointwise Convolutions Reduce Parameters in Convolutional Neural Networks 30 Jun 2022 · 2 repositories
-
Mushroom image recognition and distance generation based on attention-mechanism model and genetic information 27 Jun 2022 · 0 repositories · arXiv:2206.13383
-
Bag of Tricks for Long-Tail Visual Recognition of Animal Species in Camera-Trap Images 24 Jun 2022 · 1 repository · arXiv:2206.12458
-
MoCoViT: Mobile Convolutional Vision Transformer 25 May 2022 · 1 repository · arXiv:2205.12635
-
Novel Multicolumn Kernel Extreme Learning Machine for Food Detection via Optimal Features from CNN 15 May 2022 · 0 repositories · arXiv:2205.07348
-
Deeply Supervised Skin Lesions Diagnosis with Stage and Branch Attention 9 May 2022 · 2 repositories · arXiv:2205.04326
-
TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation 12 Apr 2022 · 3 repositories · arXiv:2204.05525Syntology community repositories only · 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 5 harvested samples)
-
Overcoming Oscillations in Quantization-Aware Training 21 Mar 2022 · 1 repository · arXiv:2203.11086Syntology official: harvested, nothing ran · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
A Hardware-Aware System for Accelerating Deep Neural Network Optimization 25 Feb 2022 · 0 repositories · arXiv:2202.12954
-
CondenseNeXt: An Ultra-Efficient Deep Neural Network for Embedded Systems 1 Dec 2021 · 1 repository · arXiv:2112.00698
-
A Simple Approach to Image Tilt Correction with Self-Attention MobileNet for Smartphones 31 Oct 2021 · 0 repositories · arXiv:2111.00398
-
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer 5 Oct 2021 · 31 repositories · arXiv:2110.02178Syntology official: no sample here; runs from other or unrecorded repositories · 53 ran (of which 31 constructed an object rather than computing a result; 44 with no instrument failure: 1 honoured, 0 violated, 43 with no contract checked; 9 where Syntology's instrument failed) · 15 unverified (of 68 harvested samples) · 18 pointer-only (licence)
-
Hybrid Cloud-Edge Networks for Efficient Inference 29 Sep 2021 · 1 repository
-
L²NAS: Learning to Optimize Neural Architectures via Continuous-Action Reinforcement Learning 25 Sep 2021 · 0 repositories · arXiv:2109.12425
-
LIGAR: Lightweight General-purpose Action Recognition 30 Aug 2021 · 1 repository · arXiv:2108.13153
-
MicroNet: Improving Image Recognition with Extremely Low FLOPs 12 Aug 2021 · 1 repository · arXiv:2108.05894Syntology official (archive's flag): 10 ran · 10 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified (of 11 harvested samples)
-
Mobile-Former: Bridging MobileNet and Transformer 12 Aug 2021 · 4 repositories · arXiv:2108.05895
-
Bias Loss for Mobile Neural Networks 23 Jul 2021 · 2 repositories · arXiv:2107.11170
-
Automated age-related macular degeneration area estimation -- first results 5 Jul 2021 · 0 repositories · arXiv:2107.02211
-
Rapid Neural Architecture Search by Learning to Generate Graphs from Datasets 2 Jul 2021 · 1 repository · arXiv:2107.00860Syntology official (archive's flag): 7 ran · 12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified (of 19 harvested samples) · 6 pointer-only (licence)
-
Encoder-Decoder Architectures for Clinically Relevant Coronary Artery Segmentation 21 Jun 2021 · 1 repository · arXiv:2106.11447
-
The Care Label Concept: A Certification Suite for Trustworthy and Resource-Aware Machine Learning 1 Jun 2021 · 0 repositories · arXiv:2106.00512
-
Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness 26 May 2021 · 2 repositories · arXiv:2105.12639Syntology official (archive's flag): 5 ran · 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 8 harvested samples)
-
Learning Mobile CNN Feature Extraction Toward Fast Computation of Visual Object Tracking 3 Apr 2021 · 0 repositories · arXiv:2104.01381
-
LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference 2 Apr 2021 · 12 repositories · arXiv:2104.01136Syntology official (archive's flag): 3 ran · 23 ran (of which 16 constructed an object rather than computing a result; 21 with no instrument failure: 3 honoured, 1 violated, 17 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified (of 30 harvested samples)
-
One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking 1 Apr 2021 · 1 repository · arXiv:2104.00597
-
NetAdaptV2: Efficient Neural Architecture Search with Fast Super-Network Training and Architecture Optimization 31 Mar 2021 · 0 repositories · arXiv:2104.00031
-
Cascade Weight Shedding in Deep Neural Networks: Benefits and Pitfalls for Network Pruning 19 Mar 2021 · 0 repositories · arXiv:2103.10629
-
HR-Depth: High Resolution Self-Supervised Monocular Depth Estimation 14 Dec 2020 · 1 repository · arXiv:2012.07356Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
Model Rubik’s Cube: Twisting Resolution, Depth and Width for TinyNets 1 Dec 2020 · 3 repositories
-
MicroNet: Towards Image Recognition with Extremely Low FLOPs 24 Nov 2020 · 0 repositories · arXiv:2011.12289
-
MGIC: Multigrid-in-Channels Neural Network Architectures 17 Nov 2020 · 1 repository · arXiv:2011.09128
-
Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search 29 Oct 2020 · 2 repositories · arXiv:2010.15821Syntology community repositories only · 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result (of 1 harvested sample) · 1 pointer-only (licence)
-
Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets 28 Oct 2020 · 9 repositories · arXiv:2010.14819Syntology official: harvested for another paper · 0 ran · 1 unverified (of 1 harvested sample) · 1 pointer-only (licence)
-
Once Quantization-Aware Training: High Performance Extremely Low-bit Architecture Search 9 Oct 2020 · 1 repository · arXiv:2010.04354
-
Detecting soccer balls with reduced neural networks: a comparison of multiple architectures under constrained hardware scenarios 28 Sep 2020 · 1 repository · arXiv:2009.13684
-
Discovering Multi-Hardware Mobile Models via Architecture Search 18 Aug 2020 · 0 repositories · arXiv:2008.08178
-
Joslim: Joint Widths and Weights Optimization for Slimmable Neural Networks 23 Jul 2020 · 2 repositories · arXiv:2007.11752Syntology community repositories only · 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result (of 2 harvested samples) · 2 pointer-only (licence)
-
Fine-Grained Stochastic Architecture Search 17 Jun 2020 · 1 repository · arXiv:2006.09581Syntology 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)
-
Efficient Model for Image Classification With Regularization Tricks 1 Feb 2020 · 1 repository
-
GhostNet: More Features from Cheap Operations 27 Nov 2019 · 33 repositories · arXiv:1911.11907Syntology community repositories only · 19 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 3 honoured, 0 violated, 13 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified (of 23 harvested samples) · 5 pointer-only (licence)
-
Structured Multi-Hashing for Model Compression 25 Nov 2019 · 0 repositories · arXiv:1911.11177
-
Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation 22 Nov 2019 · 9 repositories · arXiv:1911.10194Syntology official: harvested, nothing ran · 5 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified (of 9 harvested samples) · 1 pointer-only (licence)
-
Street Crossing Aid Using Light-weight CNNs for the Visually Impaired 14 Sep 2019 · 1 repository · arXiv:1909.09598
-
MoGA: Searching Beyond MobileNetV3 4 Aug 2019 · 2 repositories · arXiv:1908.01314
-
Butterfly Transform: An Efficient FFT Based Neural Architecture Design 5 Jun 2019 · 1 repository · arXiv:1906.02256
-
Searching for MobileNetV3 6 May 2019 · 67 repositories · arXiv:1905.02244Syntology 86 ran (of which 22 constructed an object rather than computing a result; 75 with no instrument failure: 9 honoured, 2 violated, 64 with no contract checked; 11 where Syntology's instrument failed) · 19 unverified (of 105 harvested samples) · 46 pointer-only (licence)
-
MobileNetV2: Inverted Residuals and Linear Bottlenecks 13 Jan 2018 · 159 repositories · arXiv:1801.04381Syntology 85 ran (of which 40 constructed an object rather than computing a result; 64 with no instrument failure: 8 honoured, 0 violated, 56 with no contract checked; 21 where Syntology's instrument failed) · 26 unverified (of 111 harvested samples) · 64 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 95 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