# RegNet: Self-Regulated Network for Image Classification

arXiv: https://arxiv.org/abs/2101.00590 · HTML: https://mlsanity.com/paper/2101.00590/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 42 references that are in the map.
- First posted on arXiv 3 Jan 2021.

## Builds on (most cited first, 30 of 30)

- [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)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [SkipNet: Learning Dynamic Routing in Convolutional Networks](https://mlsanity.com/paper/1711.09485/) (2017)
- [Highway Networks](https://mlsanity.com/paper/1505.00387/) (2015)
- [Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining](https://mlsanity.com/paper/1807.05698/) (2018)
- [BAM: Bottleneck Attention Module](https://mlsanity.com/paper/1807.06514/) (2018)
- [Delving Deeper into Convolutional Networks for Learning Video Representations](https://mlsanity.com/paper/1511.06432/) (2015)
- [Dual Path Networks](https://mlsanity.com/paper/1707.01629/) (2017)
- [Convolutional Gated Recurrent Networks for Video Segmentation](https://mlsanity.com/paper/1611.05435/) (2016)
- [Looking Fast and Slow: Memory-Guided Mobile Video Object Detection](https://mlsanity.com/paper/1903.10172/) (2019)
- [Non-Local ConvLSTM for Video Compression Artifact Reduction](https://mlsanity.com/paper/1910.12286/) (2019)
- [Mixed Link Networks](https://mlsanity.com/paper/1802.01808/) (2018)
- [Interleaved Group Convolutions for Deep Neural Networks](https://mlsanity.com/paper/1707.02725/) (2017)
- [Learning Identity Mappings with Residual Gates](https://mlsanity.com/paper/1611.01260/) (2016)
- [Weighted Residuals for Very Deep Networks](https://mlsanity.com/paper/1605.08831/) (2016)

## Built on by (most cited first, 30 of 44)

- [FEAR: Fast, Efficient, Accurate and Robust Visual Tracker](https://mlsanity.com/paper/2112.07957/) (2021)
- [Vicinity Vision Transformer](https://mlsanity.com/paper/2206.10552/) (2022)
- [ImageNet-OOD: Deciphering Modern Out-of-Distribution Detection Algorithms](https://mlsanity.com/paper/2310.01755/) (2023)
- [Alleviating the Sample Selection Bias in Few-shot Learning by Removing Projection to the Centroid](https://mlsanity.com/paper/2210.16834/) (2022)
- [Vision-Language Dataset Distillation](https://mlsanity.com/paper/2308.07545/) (2023)
- [Panoptic Out-of-Distribution Segmentation](https://mlsanity.com/paper/2310.11797/) (2023)
- [Exploring the Synergies of Hybrid CNNs and ViTs Architectures for Computer Vision: A survey](https://mlsanity.com/paper/2402.02941/) (2024)
- [Plug-and-Play Regulators for Image-Text Matching](https://mlsanity.com/paper/2303.13371/) (2023)
- [On the Vulnerability of Skip Connections to Model Inversion Attacks](https://mlsanity.com/paper/2409.01696/) (2024)
- [Scaling Laws for Black box Adversarial Attacks](https://mlsanity.com/paper/2411.16782/) (2024)
- [Heterogeneous Continual Learning](https://mlsanity.com/paper/2306.08593/) (2023)
- [X-MLP: A Patch Embedding-Free MLP Architecture for Vision](https://mlsanity.com/paper/2307.00592/) (2023)
- [On the Joint Interaction of Models, Data, and Features](https://mlsanity.com/paper/2306.04793/) (2023)
- [DACov: A Deeper Analysis of Data Augmentation on the Computed Tomography Segmentation Problem](https://mlsanity.com/paper/2303.05912/) (2023)
- [MaskFuser: Masked Fusion of Joint Multi-Modal Tokenization for End-to-End Autonomous Driving](https://mlsanity.com/paper/2405.07573/) (2024)
- [VyAnG-Net: A Novel Multi-Modal Sarcasm Recognition Model by Uncovering Visual, Acoustic and Glossary Features](https://mlsanity.com/paper/2408.10246/) (2024)
- [CovMatch: Cross-Covariance Guided Multimodal Dataset Distillation with Trainable Text Encoder](https://mlsanity.com/paper/2510.18583/) (2025)
- [Light In The Black: An Evaluation of Data Augmentation Techniques for COVID-19 CT's Semantic Segmentation](https://mlsanity.com/paper/2205.09722/) (2022)
- [Modelling Visual Semantics via Image Captioning to extract Enhanced Multi-Level Cross-Modal Semantic Incongruity Representation with Attention for Multimodal Sarcasm Detection](https://mlsanity.com/paper/2408.02595/) (2024)
- [GS-TransUNet: Integrated 2D Gaussian Splatting and Transformer UNet for Accurate Skin Lesion Analysis](https://mlsanity.com/paper/2502.16748/) (2025)
- [Understanding Dataset Distillation via Spectral Filtering](https://mlsanity.com/paper/2503.01212/) (2025)
- [A Spatial-Frequency Aware Multi-Scale Fusion Network for Real-Time Deepfake Detection](https://mlsanity.com/paper/2508.20449/) (2025)
- [AppleVLM: End-to-end Autonomous Driving with Advanced Perception and Planning-Enhanced Vision-Language Models](https://mlsanity.com/paper/2602.04256/) (2026)
- [AFINet: Attentive Feature Integration Networks for Image Classification](https://mlsanity.com/paper/2105.04354/) (2021)
- [Single-cell Subcellular Protein Localisation Using Novel Ensembles of Diverse Deep Architectures](https://mlsanity.com/paper/2205.09841/) (2022)
- [Connecting metrics for shape-texture knowledge in computer vision](https://mlsanity.com/paper/2301.10608/) (2023)
- [3D detection of roof sections from a single satellite image and application to LOD2-building reconstruction](https://mlsanity.com/paper/2307.05409/) (2023)
- [Optimized Deep Feature Selection for Pneumonia Detection: A Novel RegNet and XOR-Based PSO Approach](https://mlsanity.com/paper/2309.00147/) (2023)
- [Learning from the few: Fine-grained approach to pediatric wrist pathology recognition on a limited dataset](https://mlsanity.com/paper/2408.13542/) (2024)
- [RowDetr: End-to-End Crop Row Detection Using Polynomials](https://mlsanity.com/paper/2412.10525/) (2024)

## Abstract (arXiv)

The ResNet and its variants have achieved remarkable successes in various computer vision tasks. Despite its success in making gradient flow through building blocks, the simple shortcut connection mechanism limits the ability of re-exploring new potentially complementary features due to the additive function. To address this issue, in this paper, we propose to introduce a regulator module as a memory mechanism to extract complementary features, which are further fed to the ResNet. In particular, the regulator module is composed of convolutional RNNs (e.g., Convolutional LSTMs or Convolutional GRUs), which are shown to be good at extracting Spatio-temporal information. We named the new regulated networks as RegNet. The regulator module can be easily implemented and appended to any ResNet architecture. We also apply the regulator module for improving the Squeeze-and-Excitation ResNet to show the generalization ability of our method. Experimental results on three image classification datasets have demonstrated the promising performance of the proposed architecture compared with the standard ResNet, SE-ResNet, and other state-of-the-art architectures.