Methods › Computer Vision › Convolutions › Convolution
Convolution
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the part of the input it is on, then summing the results into an output.
Intuitively, a convolution allows for weight sharing - reducing the number of effective parameters - and image translation (allowing for the same feature to be detected in different parts of the input space).
Image Source: https://arxiv.org/pdf/1603.07285.pdf
Papers archive 2025-07-28
30 shown of 19,586, 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.
-
Joint angle model based learning to refine kinematic human pose estimation 15 Jul 2025 · 0 repositories · arXiv:2507.11075
-
Admissibility of Stein Shrinkage for Batch Normalization in the Presence of Adversarial Attacks 11 Jul 2025 · 0 repositories · arXiv:2507.08261
-
Towards Imperceptible JPEG Image Hiding: Multi-range Representations-driven Adversarial Stego Generation 11 Jul 2025 · 0 repositories · arXiv:2507.08343
-
HVI-CIDNet+: Beyond Extreme Darkness for Low-Light Image Enhancement 9 Jul 2025 · 1 repository · arXiv:2507.06814
-
Aliasing in Convnets: A Frame-Theoretic Perspective 8 Jul 2025 · 0 repositories · arXiv:2507.06152
-
Detecting and Mitigating Reward Hacking in Reinforcement Learning Systems: A Comprehensive Empirical Study 8 Jul 2025 · 0 repositories · arXiv:2507.05619
-
ECORE: Energy-Conscious Optimized Routing for Deep Learning Models at the Edge 8 Jul 2025 · 0 repositories · arXiv:2507.06011
-
Normalizing Diffusion Kernels with Optimal Transport 8 Jul 2025 · 0 repositories · arXiv:2507.06161Syntology ran 0 of 26 samples · 26 unverified
-
2048: Reinforcement Learning in a Delayed Reward Environment 7 Jul 2025 · 0 repositories · arXiv:2507.05465
-
Real-Time Graph-based Point Cloud Networks on FPGAs via Stall-Free Deep Pipelining 7 Jul 2025 · 1 repository · arXiv:2507.05099
-
MVNet: Hyperspectral Remote Sensing Image Classification Based on Hybrid Mamba-Transformer Vision Backbone Architecture 6 Jul 2025 · 1 repository · arXiv:2507.04409
-
Determination Of Structural Cracks Using Deep Learning Frameworks 3 Jul 2025 · 0 repositories · arXiv:2507.02416
-
RLHGNN: Reinforcement Learning-driven Heterogeneous Graph Neural Network for Next Activity Prediction in Business Processes 3 Jul 2025 · 1 repository · arXiv:2507.02690
-
StruMamba3D: Exploring Structural Mamba for Self-supervised Point Cloud Representation Learning 26 Jun 2025 · 0 repositories · arXiv:2506.21541
-
YOLO-FDA: Integrating Hierarchical Attention and Detail Enhancement for Surface Defect Detection 26 Jun 2025 · 0 repositories · arXiv:2506.21135
-
FINN-GL: Generalized Mixed-Precision Extensions for FPGA-Accelerated LSTMs 25 Jun 2025 · 0 repositories · arXiv:2506.20810
-
Multi-Objective Reinforcement Learning for Cognitive Radar Resource Management 25 Jun 2025 · 0 repositories · arXiv:2506.20853
-
Time-series surrogates from energy consumers generated by machine learning approaches for long-term forecasting scenarios 25 Jun 2025 · 0 repositories · arXiv:2506.20253
-
U-R-VEDA: Integrating UNET, Residual Links, Edge and Dual Attention, and Vision Transformer for Accurate Semantic Segmentation of CMRs 25 Jun 2025 · 0 repositories · arXiv:2506.20689
-
ReCoGNet: Recurrent Context-Guided Network for 3D MRI Prostate Segmentation 24 Jun 2025 · 0 repositories · arXiv:2506.19687
-
MedSeg-R: Medical Image Segmentation with Clinical Reasoning 23 Jun 2025 · 0 repositories · arXiv:2506.18669
-
Physics-Guided Radiotherapy Treatment Planning with Deep Learning 23 Jun 2025 · 0 repositories · arXiv:2506.19880
-
ADA-DPM: A Neural Descriptors-based Adaptive Noise Point Filtering Strategy for SLAM 22 Jun 2025 · 0 repositories · arXiv:2506.18016
-
Pattern-Based Phase-Separation of Tracer and Dispersed Phase Particles in Two-Phase Defocusing Particle Tracking Velocimetry 22 Jun 2025 · 0 repositories · arXiv:2506.18157
-
MTSIC: Multi-stage Transformer-based GAN for Spectral Infrared Image Colorization 21 Jun 2025 · 0 repositories · arXiv:2506.17540
-
Residual Connection-Enhanced ConvLSTM for Lithium Dendrite Growth Prediction 21 Jun 2025 · 0 repositories · arXiv:2506.17756
-
Efficient Feedback Gate Network for Hyperspectral Image Super-Resolution 20 Jun 2025 · 0 repositories · arXiv:2506.17361
-
Prmpt2Adpt: Prompt-Based Zero-Shot Domain Adaptation for Resource-Constrained Environments 20 Jun 2025 · 0 repositories · arXiv:2506.16994
-
Category-based Galaxy Image Generation via Diffusion Models 19 Jun 2025 · 0 repositories · arXiv:2506.16255
-
VRAIL: Vectorized Reward-based Attribution for Interpretable Learning 19 Jun 2025 · 0 repositories · arXiv:2506.16014
Tasks archive 2025-07-28
20 shown of 2,121 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Semantic Segmentation | 2,045 |
| Segmentation | 1,823 |
| Object Detection | 1,691 |
| object-detection | 1,561 |
| Image Classification | 1,252 |
| image-classification | 1,008 |
| Object | 943 |
| General Classification | 837 |
| Decoder | 822 |
| Image Segmentation | 776 |
| Classification | 719 |
| Transfer Learning | 684 |
| Reinforcement Learning (RL) | 648 |
| Image Generation | 647 |
| Deep Learning | 628 |
| Generative Adversarial Network | 603 |
| Data Augmentation | 587 |
| Reinforcement Learning | 579 |
| reinforcement-learning | 578 |
| GPU | 497 |
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