Data to 7 Oct 2026

Torch.manual_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision

arXiv 2109.08203 ↗First posted 16 Sep 2021cs.CVcited by 76

Not on the map. Why?

Abstract (arXiv)

In this paper I investigate the effect of random seed selection on the accuracy when using popular deep learning architectures for computer vision. I scan a large amount of seeds (up to 104) on CIFAR 10 and I also scan fewer seeds on Imagenet using pre-trained models to investigate large scale datasets. The conclusions are that even if the variance is not very large, it is surprisingly easy to find an outlier that performs much better or much worse than the average.

Key facts. Cited by 76 papers in the map (data through 7 Oct 2026). Builds on 3 of its 4 references that are in the map. First posted on arXiv 16 Sep 2021.

Builds on

3 of 4 references.

References · 3

2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
2021Accounting for Variance in Machine Learning Benchmarkscited by 195
2018Analysis of DAWNBench, a Time-to-Accuracy Machine Learning Performance Benchmarkcited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 13; 2023: 10; 2024: 16; 2025: 17; 2026: 15.

76 papers.

Sort:

By area:

2021ResNet strikes back: An improved training procedure in timmcited by 365
2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
2024Good Seed Makes a Good Crop: Discovering Secret Seeds in Text-to-Image Diffusion Modelscited by 47
2023If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selectioncited by 40
2026Building Production-Ready Probes For Geminicited by 38
2021Augmenting Convolutional networks with attention-based aggregationcited by 29
2021Learned Queries for Efficient Local Attentioncited by 27
2023On the Variance of Neural Network Training with respect to Test Sets and Distributionscited by 20
2022The worst of both worlds: A comparative analysis of errors in learning from data in psychology and machine learningcited by 17
2025Systemizing Multiplicity: The Curious Case of Arbitrariness in Machine Learningcited by 17
2024Instant Adversarial Purification with Adversarial Consistency Distillationcited by 14
2025Probing Deep into Temporal Profile Makes the Infrared Small Target Detector Much Bettercited by 11

38 more

2025Assessing the Macro and Micro Effects of Random Seeds on Fine-Tuning Large Language Modelscited by 10
2024Artwork Protection Against Neural Style Transfer Using Locally Adaptive Adversarial Color Attackcited by 9
2022SOS! Self-supervised Learning Over Sets Of Handled Objects In Egocentric Action Recognitioncited by 8
2022Improving Deep Neural Network Random Initialization Through Neuronal Rewiringcited by 7
2022Confident AIcited by 6
2022CASS: Cross Architectural Self-Supervision for Medical Image Analysiscited by 6
2022A Data-Efficient Deep Learning Framework for Segmentation and Classification of Histopathology Imagescited by 6
2024Triamese-ViT: A 3D-Aware Method for Robust Brain Age Estimation from MRIscited by 5
2024Position: Embracing Negative Results in Machine Learningcited by 5
2025Multi-Loco: Unifying Multi-Embodiment Legged Locomotion via Reinforcement Learning Augmented Diffusioncited by 5
2024Positional encoding is not the same as context: A study on positional encoding for sequential recommendationcited by 4
2021Revisiting Batch Norm Initializationcited by 3
2022Learning More May Not Be Better: Knowledge Transferability in Vision and Language Taskscited by 3
2024Questionable practices in machine learningcited by 3
2024Differentiable SVD based on Moore-Penrose Pseudoinverse for Inverse Imaging Problemscited by 3
2022Engineering the Neural Automatic Passenger Countercited by 2
2022Merging of neural networkscited by 2
2023Efficient Representation Learning for Healthcare with Cross-Architectural Self-Supervisioncited by 2
2023Geometric instability of graph neural networks on large graphscited by 2
2023Data-Free Knowledge Distillation Using Adversarially Perturbed OpenGL Shader Imagescited by 2
2023TSPP: A Unified Benchmarking Tool for Time-series Forecastingcited by 2
2024Regulating AI Adaptation: An Analysis of AI Medical Device Updatescited by 2
2025OASIS: Order-Augmented Strategy for Improved Code Searchcited by 2
2025Towards more transferable adversarial attack in black-box mannercited by 2
2021SimpleTRON: Simple Transformer with O(N) Complexitycited by 1
2022CoShNet: A Hybrid Complex Valued Neural Network using Shearletscited by 1
2023Performance Comparison of Session-based Recommendation Algorithms based on GNNscited by 1
2024R+R: Revisiting Static Feature-Based Android Malware Detection using Machine Learningcited by 1
2024Drone Detection using Deep Neural Networks Trained on Pure Synthetic Datacited by 1
2025Probabilistic Neural Networks (PNNs) with t-Distributed Outputs: Adaptive Prediction Intervals Beyond Gaussian Assumptionscited by 1
2025Hybrid Layer-Wise ANN-SNN With Surrogate Spike Encoding-Decoding Structurecited by 1
2026An Exploration-Analysis-Disambiguation Reasoning Framework for Word Sense Disambiguation with Low-Parameter LLMscited by 1
2026Seeds Before Objectives: Rethinking Evaluation for Low-Resource Garhwali ASRcited by 1
2022Linear Self-Attention Approximation via Trainable Feedforward Kernelcited by 0
2022Analysis and application of multispectral data for water segmentation using machine learningcited by 0
2023Cross-Architectural Positive Pairs improve the effectiveness of Self-Supervised Learningcited by 0
2023Adversarial Semi-Supervised Domain Adaptation for Semantic Segmentation: A New Role for Labeled Target Samplescited by 0
2023A Cascaded Neural Network System For Rating Student Performance In Surgical Knot Tying Simulationcited by 0

50 most cited of 76 All 76 (JSON)