Methods › General › Regularization › Stochastic Depth
Stochastic Depth
Introduced by Gao Huang et al. in Deep Networks with Stochastic Depth
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Stochastic Depth aims to shrink the depth of a network during training, while keeping it unchanged during testing. This is achieved by randomly dropping entire ResBlocks during training and bypassing their transformations through skip connections.
Let bₗ ∈ {$0, 1$} denote a Bernoulli random variable, which indicates whether the $l$th ResBlock is active (bₗ = 1) or inactive (bₗ = 0). Further, let us denote the “survival” probability of ResBlock l as pₗ = Pr(bₗ = 1). With this definition we can bypass the $l$th ResBlock by multiplying its function fₗ with bₗ and we extend the update rule to:
Hₗ = ReLU(bₗfₗ(Hₗ₋₁) + id(Hₗ₋₁))
If bₗ = 1, this reduces to the original ResNet update and this ResBlock remains unchanged. If bₗ = 0, the ResBlock reduces to the identity function, Hₗ = id((Hₗ−1).
Papers archive 2025-07-28
30 shown of 463, 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.
-
MD-ViSCo: A Unified Model for Multi-Directional Vital Sign Waveform Conversion 10 Jun 2025 · 1 repository · arXiv:2506.08357
-
MedMoE: Modality-Specialized Mixture of Experts for Medical Vision-Language Understanding 10 Jun 2025 · 0 repositories · arXiv:2506.08356
-
Multi-modal brain MRI synthesis based on SwinUNETR 3 Jun 2025 · 0 repositories · arXiv:2506.02467
-
SST: Self-training with Self-adaptive Thresholding for Semi-supervised Learning 31 May 2025 · 0 repositories · arXiv:2506.00467
-
Deep Modeling and Optimization of Medical Image Classification 29 May 2025 · 1 repository · arXiv:2505.23040
-
ZIPA: A family of efficient models for multilingual phone recognition 29 May 2025 · 1 repository · arXiv:2505.23170Syntology ran 0 of 1 samples · 1 unverified
-
AgriFM: A Multi-source Temporal Remote Sensing Foundation Model for Crop Mapping 27 May 2025 · 1 repository · arXiv:2505.21357
-
Structured Initialization for Vision Transformers 26 May 2025 · 0 repositories · arXiv:2505.19985
-
Explainable Anatomy-Guided AI for Prostate MRI: Foundation Models and In Silico Clinical Trials for Virtual Biopsy-based Risk Assessment 23 May 2025 · 0 repositories · arXiv:2505.17971
-
Leveraging Stochastic Depth Training for Adaptive Inference 23 May 2025 · 0 repositories · arXiv:2505.17626
-
Fusion of Foundation and Vision Transformer Model Features for Dermatoscopic Image Classification 22 May 2025 · 0 repositories · arXiv:2505.16338
-
Swin Transformer for Robust CGI Images Detection: Intra- and Inter-Dataset Analysis across Multiple Color Spaces 22 May 2025 · 0 repositories · arXiv:2505.16253
-
Multi-Channel Swin Transformer Framework for Bearing Remaining Useful Life Prediction 20 May 2025 · 0 repositories · arXiv:2505.14897
-
CheX-DS: Improving Chest X-ray Image Classification with Ensemble Learning Based on DenseNet and Swin Transformer 16 May 2025 · 0 repositories · arXiv:2505.11168
-
A Deep Learning-Driven Inhalation Injury Grading Assistant Using Bronchoscopy Images 13 May 2025 · 0 repositories · arXiv:2505.08517
-
Technical Report for ICRA 2025 GOOSE 2D Semantic Segmentation Challenge: Leveraging Color Shift Correction, RoPE-Swin Backbone, and Quantile-based Label Denoising Strategy for Robust Outdoor Scene Understanding 11 May 2025 · 0 repositories · arXiv:2505.06991
-
DFEN: Dual Feature Equalization Network for Medical Image Segmentation 9 May 2025 · 1 repository · arXiv:2505.05913
-
Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise 7 May 2025 · 0 repositories · arXiv:2505.04375
-
SwinLip: An Efficient Visual Speech Encoder for Lip Reading Using Swin Transformer 7 May 2025 · 0 repositories · arXiv:2505.04394
-
Enhancing DR Classification with Swin Transformer and Shifted Window Attention 20 Apr 2025 · 0 repositories · arXiv:2504.15317
-
SatelliteCalculator: A Multi-Task Vision Foundation Model for Quantitative Remote Sensing Inversion 18 Apr 2025 · 0 repositories · arXiv:2504.13442
-
Towards Accurate and Interpretable Neuroblastoma Diagnosis via Contrastive Multi-scale Pathological Image Analysis 18 Apr 2025 · 1 repository · arXiv:2504.13754
-
Deep Learning-based Bathymetry Retrieval without In-situ Depths using Remote Sensing Imagery and SfM-MVS DSMs with Data Gaps 15 Apr 2025 · 1 repository · arXiv:2504.11416
-
HDC: Hierarchical Distillation for Multi-level Noisy Consistency in Semi-Supervised Fetal Ultrasound Segmentation 14 Apr 2025 · 0 repositories · arXiv:2504.09876
-
Foundation Models For Seismic Data Processing: An Extensive Review 31 Mar 2025 · 1 repository · arXiv:2503.24166
-
Camera Model Identification with SPAIR-Swin and Entropy based Non-Homogeneous Patches 28 Mar 2025 · 0 repositories · arXiv:2503.22120
-
Context-Aware Semantic Segmentation: Enhancing Pixel-Level Understanding with Large Language Models for Advanced Vision Applications 25 Mar 2025 · 0 repositories · arXiv:2503.19276
-
iNatAg: Multi-Class Classification Models Enabled by a Large-Scale Benchmark Dataset with 4.7M Images of 2,959 Crop and Weed Species 25 Mar 2025 · 1 repository · arXiv:2503.20068
-
Binarized Mamba-Transformer for Lightweight Quad Bayer HybridEVS Demosaicing 20 Mar 2025 · 1 repository · arXiv:2503.16134
-
Alzheimer's Disease Classification Using Retinal OCT: TransnetOCT and Swin Transformer Models 14 Mar 2025 · 0 repositories · arXiv:2503.11511
Tasks archive 2025-07-28
20 shown of 371 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