List: Papers | Curated by Javier

Nov 10, 2023
17 stories
PapersInteresting AI papers to read
The Tenyks Blogger
The Foundation Models Reshaping Computer VisionLearn about the Foundation Models — for object classification, object detection, and segmentation —  that are redefining Computer Vision.
Oct 26, 2023
4
Oct 26, 2023
4
Jesus Rodriguez
The New ImageNet: DeepMind’s New Perception Benchmark for Deep Learning ModelsA new benchmark focuses focuses on multimodal computer vision models.
Oct 20, 2022
Oct 20, 2022
In
SyncedReview
by
Synced
DeepMind Paper Provides a Mathematically Precise Overview of Transformer Architectures and…Since their 2017 debut as a novel approach to natural language processing (NLP), transformers have achieved epoch-making performance across…
Jul 25, 2022
2
Jul 25, 2022
2
In
SyncedReview
by
Synced
Tsinghua & NKU’s Visual Attention Network Combines the Advantages of Convolution and…The powerful self-attention mechanisms in transformer architectures have significantly improved the state-of-the-art across a wide range of…
Feb 23, 2022
Feb 23, 2022
In
Deep-Learning-For-Computer-Vision
by
Inside AI
10. Introduction to Deep Learning with Computer Vision— Types of Convolutions & Atrous ConvolutionsWritten by Praveen Kumar.
Feb 16, 2020
Feb 16, 2020
In
SyncedReview
by
Synced
UC Berkeley & Google’s BoTNet Applies Self-Attention to CV BottlenecksResearchers from UC Berkeley and Google Research have introduced BoTNet, a “conceptually simple yet powerful” backbone architecture that…
Feb 17, 2021
Feb 17, 2021
In
Towards AI
by
Louis-François Bouchard
Create 3D Models from Images! AI and Game Development, Design…This promising model called GANverse3D only needs an image to create a 3D figure that can be customized and animated!
Apr 18, 2021
Apr 18, 2021
In
CodeX
by
MobiDev
Small Datasets-Based Object Detection: How Much Data is Enough?Getting started with any machine learning project often starts with the question: “How much data is enough?”. The response depends on a…
Sep 20, 2021
1
Sep 20, 2021
1
In
Geek Culture
by
Dickson Wu
A New Frontier of Machine LearningPaper Summary: “Deep Learning in Spiking Neural Networks”
Sep 18, 2021
2
Sep 18, 2021
2
In
SyncedReview
by
Synced
Are Patches All You Need?Vision transformer architectures (ViTs) have achieved compelling performance across many computer vision tasks, often outperforming…
Oct 12, 2021
1
Oct 12, 2021
1
In
SyncedReview
by
Synced
Microsoft Asia’s Swin Transformer V2 Scales the Award-Winning ViT to 3 Billion Parameters and…In the ICCV (International Conference on Computer Vision) 2021 paper awards announced last month, a team from Microsoft Asia Research was…
Nov 22, 2021
Nov 22, 2021
Cambridge Spark
CoordConv Layer: Deep LearningAn introduction to Uber’s new CoordConv architecture and its applications
Oct 25, 2019
Oct 25, 2019
In
SyncedReview
by
Synced
DeepMind’s PoG Excels in Perfect and Imperfect Information Games, Advancing Research on General…
Dec 8, 2021
Dec 8, 2021
Sahil Chachra
Paper Summary — MetaFormer is Actually What You Need for VisionIn recent times we have seen that Transformers (for vision) have performed very well, i.e., at par or at times surpassing the previously…
Jan 7, 2022
1
Jan 7, 2022
1
Sik-Ho Tsang
Review: Layer Normalization (LN)Stabilizing Training, Reduce Training Time
Feb 8, 2022
Feb 8, 2022
In
TDS Archive
by
Wanshun Wong
What is Group Normalization?An alternative to Batch Normalization
Jun 17, 2020
2
Jun 17, 2020
2
In
TDS Archive
by
Leon Sick
RegNet: The Most Flexible Network Architecture For Computer VisionA model design that scales for high-efficiency or high-accuracy
Dec 13, 2021
1
Dec 13, 2021
1