# No More Strided Convolutions or Pooling: A New CNN Building Block for Low-Resolution Images and Small Objects

arXiv: https://arxiv.org/abs/2208.03641 · HTML: https://mlsanity.com/paper/2208.03641/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 35 references that are in the map.
- First posted on arXiv 7 Aug 2022.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [YOLOv3: An Incremental Improvement](https://mlsanity.com/paper/1804.02767/) (2018)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [Path Aggregation Network for Instance Segmentation](https://mlsanity.com/paper/1803.01534/) (2018)
- [Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition](https://mlsanity.com/paper/1406.4729/) (2014)
- [CenterNet: Keypoint Triplets for Object Detection](https://mlsanity.com/paper/1904.08189/) (2019)
- [Distance-IoU Loss: Faster and Better Learning for Bounding Box Regression](https://mlsanity.com/paper/1911.08287/) (2019)
- [Scaled-YOLOv4: Scaling Cross Stage Partial Network](https://mlsanity.com/paper/2011.08036/) (2020)
- [Frame-Recurrent Video Super-Resolution](https://mlsanity.com/paper/1801.04590/) (2018)
- [An Analysis of Scale Invariance in Object Detection - SNIP](https://mlsanity.com/paper/1711.08189/) (2017)
- [SNIPER: Efficient Multi-Scale Training](https://mlsanity.com/paper/1805.09300/) (2018)
- [Task-Driven Super Resolution: Object Detection in Low-resolution Images](https://mlsanity.com/paper/1803.11316/) (2018)
- [Studying Very Low Resolution Recognition Using Deep Networks](https://mlsanity.com/paper/1601.04153/) (2016)
- [Fine-to-coarse Knowledge Transfer For Low-Res Image Classification](https://mlsanity.com/paper/1605.06695/) (2016)
- [SAN: Learning Relationship between Convolutional Features for Multi-Scale Object Detection](https://mlsanity.com/paper/1808.04974/) (2018)
- [Enhancing Fine-Grained Classification for Low Resolution Images](https://mlsanity.com/paper/2105.00241/) (2021)

## Built on by (most cited first, 27 of 27)

- [Uncertainty-aware Surrogate Models for Airfoil Flow Simulations with Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2312.05320/) (2023)
- [CCi-YOLOv8n: Enhanced Fire Detection with CARAFE and Context-Guided Modules](https://mlsanity.com/paper/2411.11011/) (2024)
- [LDConv: Linear deformable convolution for improving convolutional neural networks](https://mlsanity.com/paper/2311.11587/) (2023)
- [A Simple Detector with Frame Dynamics is a Strong Tracker](https://mlsanity.com/paper/2505.04917/) (2025)
- [SRPL-SFDA: SAM-Guided Reliable Pseudo-Labels for Source-Free Domain Adaptation in Medical Image Segmentation](https://mlsanity.com/paper/2506.09403/) (2025)
- [Fake or Compromised? Making Sense of Malicious Clients in Federated Learning](https://mlsanity.com/paper/2403.06319/) (2024)
- [RainPro-8: An Efficient Deep Learning Model to Estimate Rainfall Probabilities Over 8 Hours](https://mlsanity.com/paper/2505.10271/) (2025)
- [HieraEdgeNet: A Multi-Scale Edge-Enhanced Framework for Automated Pollen Recognition](https://mlsanity.com/paper/2506.07637/) (2025)
- [High-Frequency Semantics and Geometric Priors for End-to-End Detection Transformers in Challenging UAV Imagery](https://mlsanity.com/paper/2507.00825/) (2025)
- [Cott-ADNet: Lightweight Real-Time Cotton Boll and Flower Detection Under Field Conditions](https://mlsanity.com/paper/2509.12442/) (2025)
- [Cross-Domain Knowledge Distillation for Low-Resolution Human Pose Estimation](https://mlsanity.com/paper/2405.11448/) (2024)
- [Focus on Low-Resolution Information: Multi-Granular Information-Lossless Model for Low-Resolution Human Pose Estimation](https://mlsanity.com/paper/2405.12247/) (2024)
- [Mutual Learning for Acoustic Matching and Dereverberation via Visual Scene-driven Diffusion](https://mlsanity.com/paper/2407.10373/) (2024)
- [Target Detection of Safety Protective Gear Using the Improved YOLOv5](https://mlsanity.com/paper/2408.05964/) (2024)
- [DS MYOLO: A Reliable Object Detector Based on SSMs for Driving Scenarios](https://mlsanity.com/paper/2409.01093/) (2024)
- [Efficient Oriented Object Detection with Enhanced Small Object Recognition in Aerial Images](https://mlsanity.com/paper/2412.12562/) (2024)
- [Thermal Detection of People with Mobility Restrictions for Barrier Reduction at Traffic Lights Controlled Intersections](https://mlsanity.com/paper/2505.08568/) (2025)
- [MS-YOLO: A Multi-Scale Model for Accurate and Efficient Blood Cell Detection](https://mlsanity.com/paper/2506.03972/) (2025)
- [TinyDef-DETR: A Transformer-Based Framework for Defect Detection in Transmission Lines from UAV Imagery](https://mlsanity.com/paper/2509.06035/) (2025)
- [Forestpest-YOLO: A High-Performance Detection Framework for Small Forestry Pests](https://mlsanity.com/paper/2510.00547/) (2025)
- [PT-DETR: Small Target Detection Based on Partially-Aware Detail Focus](https://mlsanity.com/paper/2510.26630/) (2025)
- [You Only Look Omni Gradient Backpropagation for Moving Infrared Small Target Detection](https://mlsanity.com/paper/2511.13013/) (2025)
- [SARES-DEIM: Sparse Mixture-of-Experts Meets DETR for Robust SAR Ship Detection](https://mlsanity.com/paper/2604.04127/) (2026)
- [FSDETR: Frequency-Spatial Feature Enhancement for Small Object Detection](https://mlsanity.com/paper/2604.14884/) (2026)
- [UniPCB: A Generation-Assisted Vision-Based Measurement Framework for PCB Defect Inspection](https://mlsanity.com/paper/2605.04635/) (2026)
- [RDANet: Relative Degradation Aware Network for Infrared Small Target Detection](https://mlsanity.com/paper/2608.20870/) (2026)
- [Cross-Scenario Industrial Defect Detection via Domain-Robust Training and Metric-Aligned Selection](https://mlsanity.com/paper/2610.19540/) (2026)

## Abstract (arXiv)

Convolutional neural networks (CNNs) have made resounding success in many computer vision tasks such as image classification and object detection. However, their performance degrades rapidly on tougher tasks where images are of low resolution or objects are small. In this paper, we point out that this roots in a defective yet common design in existing CNN architectures, namely the use of strided convolution and/or pooling layers, which results in a loss of fine-grained information and learning of less effective feature representations. To this end, we propose a new CNN building block called SPD-Conv in place of each strided convolution layer and each pooling layer (thus eliminates them altogether). SPD-Conv is comprised of a space-to-depth (SPD) layer followed by a non-strided convolution (Conv) layer, and can be applied in most if not all CNN architectures. We explain this new design under two most representative computer vision tasks: object detection and image classification. We then create new CNN architectures by applying SPD-Conv to YOLOv5 and ResNet, and empirically show that our approach significantly outperforms state-of-the-art deep learning models, especially on tougher tasks with low-resolution images and small objects. We have open-sourced our code at https://github.com/LabSAINT/SPD-Conv.