Papers › Which Backbone to Use: A Resource-efficient Domain Specific Comparison for Computer Vision

Which Backbone to Use: A Resource-efficient Domain Specific Comparison for Computer Vision

9 Jun 2024arXiv:2406.05612archive 2025-07-28

Pranav Jeevan, Amit Sethi

In contemporary computer vision applications, particularly image classification, architectural backbones pre-trained on large datasets like ImageNet are commonly employed as feature extractors. Despite the widespread use of these pre-trained convolutional neural networks (CNNs), there remains a gap in understanding the performance of various resource-efficient backbones across diverse domains and dataset sizes. Our study systematically evaluates multiple lightweight, pre-trained CNN backbones under consistent training settings across a variety of datasets, including natural images, medical images, galaxy images, and remote sensing images. This comprehensive analysis aims to aid machine learning practitioners in selecting the most suitable backbone for their specific problem, especially in scenarios involving small datasets where fine-tuning a pre-trained network is crucial. Even though attention-based architectures are gaining popularity, we observed that they tend to perform poorly under low data finetuning tasks compared to CNNs. We also observed that some CNN architectures such as ConvNeXt, RegNet and EfficientNet performs well compared to others on a diverse set of domains consistently. Our findings provide actionable insights into the performance trade-offs and effectiveness of different backbones, facilitating informed decision-making in model selection for a broad spectrum of computer vision domains. Our code is available here: https://github.com/pranavphoenix/Backbones

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

pranavphoenix/Backbones officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Breast Cancer Histology Image Classification Decision Making Image Classification Model Selection image-classification

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Breast Cancer Histology Image Classification	BreakHis	WaveMix	Accuracy (%)	99.39	#1 of 5	Archive leaderboard	report
Image Classification	BreakHis	WaveMix	Average Test Accuracy over all magnifications	99.39	#1 of 3	Archive leaderboard	report
Image Classification	EuroSAT	WaveMix	Accuracy (%)	98.96	#6 of 15	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 Convolution Average Pooling Batch Normalization ConvNeXt Convolution Dense Connections Depthwise Convolution Depthwise Separable Convolution Discriminative Fine-Tuning Dropout EfficientNet Inverted Residual Block Pointwise Convolution RMSProp ReLU SET Sigmoid Activation Squeeze-and-Excitation Block

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