# Improved Residual Networks for Image and Video Recognition

arXiv: https://arxiv.org/abs/2004.04989 · HTML: https://mlsanity.com/paper/2004.04989/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Apr 2020.

## Built on by (most cited first, 30 of 52)

- [Transcending Forgery Specificity with Latent Space Augmentation for Generalizable Deepfake Detection](https://mlsanity.com/paper/2311.11278/) (2023)
- [How Good is ChatGPT at Face Biometrics? A First Look into Recognition, Soft Biometrics, and Explainability](https://mlsanity.com/paper/2401.13641/) (2024)
- [QMagFace: Simple and Accurate Quality-Aware Face Recognition](https://mlsanity.com/paper/2111.13475/) (2021)
- [Multi-modal Facial Affective Analysis based on Masked Autoencoder](https://mlsanity.com/paper/2303.10849/) (2023)
- [Multi-modal Emotion Estimation for in-the-wild Videos](https://mlsanity.com/paper/2203.13032/) (2022)
- [Leveraging Diffusion For Strong and High Quality Face Morphing Attacks](https://mlsanity.com/paper/2301.04218/) (2023)
- [Second FRCSyn-onGoing: Winning Solutions and Post-Challenge Analysis to Improve Face Recognition with Synthetic Data](https://mlsanity.com/paper/2412.01383/) (2024)
- [Machine learning for modelling unstructured grid data in computational physics: a review](https://mlsanity.com/paper/2502.09346/) (2025)
- [Data Synthesis with Diverse Styles for Face Recognition via 3DMM-Guided Diffusion](https://mlsanity.com/paper/2504.00430/) (2025)
- [Facial Action Unit Recognition With Multi-models Ensembling](https://mlsanity.com/paper/2203.13046/) (2022)
- [Greedy-DiM: Greedy Algorithms for Unreasonably Effective Face Morphs](https://mlsanity.com/paper/2404.06025/) (2024)
- [AdjointDEIS: Efficient Gradients for Diffusion Models](https://mlsanity.com/paper/2405.15020/) (2024)
- [Octuplet Loss: Make Face Recognition Robust to Image Resolution](https://mlsanity.com/paper/2207.06726/) (2022)
- [Local Region Perception and Relationship Learning Combined with Feature Fusion for Facial Action Unit Detection](https://mlsanity.com/paper/2303.08545/) (2023)
- [Multimodal Fusion Method with Spatiotemporal Sequences and Relationship Learning for Valence-Arousal Estimation](https://mlsanity.com/paper/2403.12425/) (2024)
- [GHOST 2.0: generative high-fidelity one shot transfer of heads](https://mlsanity.com/paper/2502.18417/) (2025)
- [Improving Deep Facial Phenotyping for Ultra-rare Disorder Verification Using Model Ensembles](https://mlsanity.com/paper/2211.06764/) (2022)
- [GestaltMML: Enhancing Rare Genetic Disease Diagnosis through Multimodal Machine Learning Combining Facial Images and Clinical Text](https://mlsanity.com/paper/2312.15320/) (2023)
- [Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches](https://mlsanity.com/paper/2404.00540/) (2024)
- [Score Normalization for Demographic Fairness in Face Recognition](https://mlsanity.com/paper/2407.14087/) (2024)
- [Multi-modal Expression Recognition with Ensemble Method](https://mlsanity.com/paper/2303.10033/) (2023)
- [AUD-TGN: Advancing Action Unit Detection with Temporal Convolution and GPT-2 in Wild Audiovisual Contexts](https://mlsanity.com/paper/2403.13678/) (2024)
- [DIP-Watermark: A Double Identity Protection Method Based on Robust Adversarial Watermark](https://mlsanity.com/paper/2404.14693/) (2024)
- [SynMorph: Generating Synthetic Face Morphing Dataset with Mated Samples](https://mlsanity.com/paper/2409.05595/) (2024)
- [Harmonizing Geometry and Uncertainty: Diffusion with Hyperspheres](https://mlsanity.com/paper/2506.10576/) (2025)
- [Generating 2D and 3D Master Faces for Dictionary Attacks with a Network-Assisted Latent Space Evolution](https://mlsanity.com/paper/2211.13964/) (2022)
- [MixBCT: Towards Self-Adapting Backward-Compatible Training](https://mlsanity.com/paper/2308.06948/) (2023)
- [Privacy-preserving Multi-biometric Indexing based on Frequent Binary Patterns](https://mlsanity.com/paper/2310.03091/) (2023)
- [Dealing with Subject Similarity in Differential Morphing Attack Detection](https://mlsanity.com/paper/2404.07667/) (2024)
- [HyperSpaceX: Radial and Angular Exploration of HyperSpherical Dimensions](https://mlsanity.com/paper/2408.02494/) (2024)

## Abstract (arXiv)

Residual networks (ResNets) represent a powerful type of convolutional neural network (CNN) architecture, widely adopted and used in various tasks. In this work we propose an improved version of ResNets. Our proposed improvements address all three main components of a ResNet: the flow of information through the network layers, the residual building block, and the projection shortcut. We are able to show consistent improvements in accuracy and learning convergence over the baseline. For instance, on ImageNet dataset, using the ResNet with 50 layers, for top-1 accuracy we can report a 1.19% improvement over the baseline in one setting and around 2% boost in another. Importantly, these improvements are obtained without increasing the model complexity. Our proposed approach allows us to train extremely deep networks, while the baseline shows severe optimization issues. We report results on three tasks over six datasets: image classification (ImageNet, CIFAR-10 and CIFAR-100), object detection (COCO) and video action recognition (Kinetics-400 and Something-Something-v2). In the deep learning era, we establish a new milestone for the depth of a CNN. We successfully train a 404-layer deep CNN on the ImageNet dataset and a 3002-layer network on CIFAR-10 and CIFAR-100, while the baseline is not able to converge at such extreme depths. Code is available at: https://github.com/iduta/iresnet