Data to 7 Oct 2026

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

arXiv 1602.07360 ↗First posted 24 Feb 2016cs.CV cs.AIcited by 1,054

Not on the map. Why?

Abstract (arXiv)

Recent research on deep neural networks has focused primarily on improving accuracy. For a given accuracy level, it is typically possible to identify multiple DNN architectures that achieve that accuracy level. With equivalent accuracy, smaller DNN architectures offer at least three advantages: (1) Smaller DNNs require less communication across servers during distributed training. (2) Smaller DNNs require less bandwidth to export a new model from the cloud to an autonomous car. (3) Smaller DNNs are more feasible to deploy on FPGAs and other hardware with limited memory. To provide all of these advantages, we propose a small DNN architecture called SqueezeNet. SqueezeNet achieves AlexNet-level accuracy on ImageNet with 50x fewer parameters. Additionally, with model compression techniques we are able to compress SqueezeNet to less than 0.5MB (510x smaller than AlexNet). The SqueezeNet architecture is available for download here: https://github.com/DeepScale/SqueezeNet

Key facts. Cited by 1,054 papers in the map (data through 7 Oct 2026). First posted on arXiv 24 Feb 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 280; 2022: 236; 2023: 191; 2024: 171; 2025: 118; 2026: 58.

1,054 papers.

Sort:

By area:

2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
2023Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectivescited by 477
2021CMT: Convolutional Neural Networks Meet Vision Transformerscited by 310
2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 259
2021I-BERT: Integer-only BERT Quantizationcited by 250
2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 248
2021Accelerating Sparse Deep Neural Networkscited by 213
2022Beyond Transmitting Bits: Context, Semantics, and Task-Oriented Communicationscited by 166
2021(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Networkcited by 164
2021IntentNet: Learning to Predict Intention from Raw Sensor Datacited by 158
2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 156
2021Rethinking BiSeNet For Real-time Semantic Segmentationcited by 124

38 more

2024AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Errorcited by 123
2022EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applicationscited by 121
2022MobileOne: An Improved One millisecond Mobile Backbonecited by 109
2021A Survey of Modern Deep Learning based Object Detection Modelscited by 97
2022Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shiftcited by 94
2023Vision-Language Models in Remote Sensing: Current Progress and Future Trendscited by 93
2023Rethinking Model Ensemble in Transfer-based Adversarial Attackscited by 88
2021A Study of Face Obfuscation in ImageNetcited by 83
2024Marabou 2.0: A Versatile Formal Analyzer of Neural Networkscited by 81
2021Active Learning for Deep Object Detection via Probabilistic Modelingcited by 79
2022Object Detection with Spiking Neural Networks on Automotive Event Datacited by 79
2023Full Stack Optimization of Transformer Inference: a Surveycited by 79
2022MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentationcited by 76
2022Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learningcited by 71
2022TCTrack: Temporal Contexts for Aerial Trackingcited by 69
2021SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)cited by 67
2022Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Spacecited by 66
2023Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifierscited by 66
2022A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classificationcited by 64
2023Omni Aggregation Networks for Lightweight Image Super-Resolutioncited by 62
2021Pufferfish: Communication-efficient Models At No Extra Costcited by 61
2023SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformercited by 60
2021PolyViT: Co-training Vision Transformers on Images, Videos and Audiocited by 58
2021Collaborative Federated Learning For Healthcare: Multi-Modal COVID-19 Diagnosis at the Edgecited by 56
2021Anycost GANs for Interactive Image Synthesis and Editingcited by 54
2021Meaningfully Debugging Model Mistakes using Conceptual Counterfactual Explanationscited by 53
2024MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformercited by 53
2021A Survey on Green Deep Learningcited by 52
2022RankFeat: Rank-1 Feature Removal for Out-of-distribution Detectioncited by 52
2023FRNet: Frustum-Range Networks for Scalable LiDAR Segmentationcited by 50
2021FedGEMS: Federated Learning of Larger Server Models via Selective Knowledge Fusioncited by 49
2022Packed-Ensembles for Efficient Uncertainty Estimationcited by 49
2022Online Continual Learning for Embedded Devicescited by 48
2023Intriguing Properties of Quantization at Scalecited by 48
2021The Low-Resource Double Bind: An Empirical Study of Pruning for Low-Resource Machine Translationcited by 46
2022Blueprint Separable Residual Network for Efficient Image Super-Resolutioncited by 44
2022Shift-tolerant Perceptual Similarity Metriccited by 44
2022MobileViTv3: Mobile-Friendly Vision Transformer with Simple and Effective Fusion of Local, Global and Input Featurescited by 44

50 most cited of 1,054 All 1,054 (JSON)