AI Research Graph: Residual Neural Network (ResNet)

This AI research graph edition covers the key knowledge areas and important research papers related to Residual Neural Network (ResNet), including Kaiming He's 10-min presentation of "Deep Residual Learning for Image Recognition” paper.

May 28, 2021
Research Spotlights

Google Brain and UC Berkeley's new paper "Revisiting ResNets: Improved Training and Scaling Strategies" has brought more attention to Residual Networks lately. First introduced by Kaiming He, et al. (2015 ), ResNets is created by reformulating the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. It is easier to optimize, and can gain accuracy from considerably increased depth. This edition of AI research graph focuses on the key knowledge areas and research papers related to this research technique, including some of the most cited work and the latest development.

Top ResNet papers with video:

The graph below demonstrates a paper-knowledge mapping for the top 10 research papers with video derived from the core knowledge node of ResNet.

Crossminds AI Research Graph: Residual Neural Network (ResNet)
ResNet Research Graph

Click to view video presentations of the top papers:

Deep Residual Learning for Image Recognition
He et al., 2015
EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
Tan, 2019
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks
Wang et al., 2020
CPM R-CNN: Calibrating Point-guided Misalignment in Object Detection
Zhu et al., 2020
Weakly supervised discriminative feature learning with state information for person identification
Yu, 2020
Learning in the Frequency Domain
Xu et al., 2020
An Investigation into the Stochasticity of Batch Whitening
Huang et al., 2020
High-Performance Large-Scale Image Recognition Without Normalization
Brock et al., 2021
Discriminative Multi-modality Speech Recognition
Xu et al., 2020

Check out our curated playlist for all related research videos on ResNet.

Additional highly-cited papers with video :

We further look into related research papers with high impacts based on the citations. Click to view video presentations of the top papers:

Supervised Contrastive Learning
Khosla et al., 2020
What makes for good views for contrastive learning
Tian et al., 2020
Neural Ordinary Differential Equations
Chen et al., 2019

Additional papers with video:

Here are some of the most recent publications in this research area. Click to view video presentations:

The Devil is in the Boundary: Exploiting Boundary Representation for Basis-based Instance Segmentation
Kim et al., 2020
YolactEdge: Real-time Instance Segmentation on the Edge (Jetson AGX Xavier: 30 FPS, RTX 2080 Ti: 170 FPS)
Liu et al., 2020
Learning Transferable Visual Models From Natural Language Supervision
Radford et al., 2021

Additional papers worth reading:

Sign up with to get personalized recommendations of the latest tech research videos!

Join Crossminds Now!
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form
Crossminds is a personalized research video platform for tech professionals. We aim to empower your growth with the latest and most relevant research, industry, and career updates.