List: computer vison | Curated by Yoshiyuki Igarashi

Feb 25, 2023

25 stories

computer vison
Megagon Labs
Hybrid Active Learning for Low-Resource LM Fine-tuningWe identified two key designs that can improve the effectiveness and efficiency of sample acquisition.
Feb 21, 2023
Feb 21, 2023
In
Towards AI
by
Chinmay Bhalerao
Improving Accuracy of Text Extraction with Simple Techniquesunderstanding data and problem statements to make predictions better
Feb 14, 2023
4
Feb 14, 2023
4
In
TDS Archive
by
Bex T.
5 Best Python Synthetic Data Generators And How to Use Them When You Lack DataLet's get even more data
Jan 23, 2023
1
Jan 23, 2023
1
In
Towards AI
by
Sergi Castella i Sapé
Trends in AI — 2023 Round-upWhat’s next for Language Models, Reinforcement Learning, Computer Vision, and leading AI companies like OpenAI and Google?
Jan 25, 2023
1
Jan 25, 2023
1
Chinmay Bhalerao
Comprehensive Guide: Top Computer Vision Resources All in One BlogSave this blog for comprehensive resources for computer vision
Jan 27, 2023
4
Jan 27, 2023
4
In
Towards AI
by
Chinmay Bhalerao
Working on a Computer Vision project? These code chunks will help you !!!An introduction to a few “used to” methods in a computer vision project
Nov 27, 2022
1
Nov 27, 2022
1
In
ML6team
by
Mathias Leys
The Art  of Pooling Embeddings 🎨In this blogpost we will discover the complexity of pooling that hides behind its apparent simplicity.
Jun 20, 2022
2
Jun 20, 2022
2
In
Deelvin Machine Learning
by
Maxim Ivanov
The evolution of the YOLO neural networks family from v1 to v7.In the previous parts (part 1, part 2) of the article, we reviewed the first 9 architectures of the YOLO family. In this final article, we…
Nov 14, 2022
1
Nov 14, 2022
1
Leo Wang
UNet 3+ Fully Explained — Next Generation UNetTable of Contents
Jul 28, 2022
1
Jul 28, 2022
1
Stanislau Beliasau
How to fine tune VERY large model if it doesn’t fit on your GPUMemory-efficient techniques to defeat the problem of “CUDA memory error..” during training
Apr 11, 2022
2
Apr 11, 2022
2
In
VirtusLab
by
Paweł Pęczek
Computer Vision in production –Nvidia DeepStreamWe examine Nvidia DeepStream, an emerging solution for implementing computer vision within your software projects.
Jan 28, 2022
3
Jan 28, 2022
3
In
ML Summaries
by
Gowthami Somepalli
When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations —…Paper: When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations
Link…
Feb 21, 2022
1
Feb 21, 2022
1
Sik-Ho Tsang
Review — PVTv2: Improved Baselines with Pyramid Vision TransformerOutperforms PVT/PVTv1, Swin Transformer, Twins
Jul 7, 2022
Jul 7, 2022
In
Towards Dev
by
Amal
YOLOv7 now Outperforms All Known Object Detectors!YOLOv7 has now surpassed all of the known object detectors like YOLOR, YOLOX, Scaled-YOLOv4, YOLOv5, DETR, Deformable DETR…
Jul 13, 2022
4
Jul 13, 2022
4
Sik-Ho Tsang
Review — DINO: Emerging Properties in Self-Supervised Vision TransformersDINO, A Form of Self-Distillation with No Labels
Jun 14, 2022
Jun 14, 2022
In
RenderedAI
by
Chris Andrews
AI Job of the Future: Synthetic Data EngineerWe don’t teach data scientists about 3D Graphics — and we shouldn’t. The skillset required to create synthetic datasets fundamentally…
Apr 15, 2022
5
Apr 15, 2022
5
yanis labrak
How to Train a Custom Vision Transformer (ViT) Image Classifier to Help Endoscopists in under 5 minMake your own Image Classifier for the healthcare industry in less than 5 min with HuggingFace and HugsVision.
Sep 2, 2021
3
Sep 2, 2021
3
Sik-Ho Tsang
Review — What Makes Instance Discrimination Good for Transfer Learning?Exemplar-v1 & Exemplar-v2, Supervised Contrastive Learning
Jul 10, 2022
Jul 10, 2022
Revca - Helping Companies achieve AI completeness
YOLOv6 : Explanation, Features and ImplementationYOLOv6 is a recent addition to the long line of state-of-the-art object detection YOLO models, which has shown quite a decent performance…
Jun 29, 2022
Jun 29, 2022
In
DataSeries
by
Jesus Rodriguez
DeepMind and OpenAI Ideas to Incorporate Human Feedback in Reinforcement Learning AgentsA paper from two years ago introduces some clever ideas to fine tune reward functions in reinforcement learning agents.
Jan 4, 2022
Jan 4, 2022

computer vison

Hybrid Active Learning for Low-Resource LM Fine-tuning

We identified two key designs that can improve the effectiveness and efficiency of sample acquisition.

Improving Accuracy of Text Extraction with Simple Techniques

understanding data and problem statements to make predictions better

5 Best Python Synthetic Data Generators And How to Use Them When You Lack Data

Let's get even more data

Trends in AI — 2023 Round-up

What’s next for Language Models, Reinforcement Learning, Computer Vision, and leading AI companies like OpenAI and Google?

Comprehensive Guide: Top Computer Vision Resources All in One Blog

Save this blog for comprehensive resources for computer vision

Working on a Computer Vision project? These code chunks will help you !!!

An introduction to a few “used to” methods in a computer vision project

The Art of Pooling Embeddings 🎨

In this blogpost we will discover the complexity of pooling that hides behind its apparent simplicity.

The evolution of the YOLO neural networks family from v1 to v7.

In the previous parts (part 1, part 2) of the article, we reviewed the first 9 architectures of the YOLO family. In this final article, we…

UNet 3+ Fully Explained — Next Generation UNet

Table of Contents

How to fine tune VERY large model if it doesn’t fit on your GPU

Memory-efficient techniques to defeat the problem of “CUDA memory error..” during training

Computer Vision in production –Nvidia DeepStream

We examine Nvidia DeepStream, an emerging solution for implementing computer vision within your software projects.

When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations —…

Paper: When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations Link…

Review — PVTv2: Improved Baselines with Pyramid Vision Transformer

Outperforms PVT/PVTv1, Swin Transformer, Twins

YOLOv7 now Outperforms All Known Object Detectors!

YOLOv7 has now surpassed all of the known object detectors like YOLOR, YOLOX, Scaled-YOLOv4, YOLOv5, DETR, Deformable DETR…

Review — DINO: Emerging Properties in Self-Supervised Vision Transformers

DINO, A Form of Self-Distillation with No Labels

AI Job of the Future: Synthetic Data Engineer

We don’t teach data scientists about 3D Graphics — and we shouldn’t. The skillset required to create synthetic datasets fundamentally…

How to Train a Custom Vision Transformer (ViT) Image Classifier to Help Endoscopists in under 5 min

Make your own Image Classifier for the healthcare industry in less than 5 min with HuggingFace and HugsVision.

Review — What Makes Instance Discrimination Good for Transfer Learning?

Exemplar-v1 & Exemplar-v2, Supervised Contrastive Learning

YOLOv6 : Explanation, Features and Implementation

YOLOv6 is a recent addition to the long line of state-of-the-art object detection YOLO models, which has shown quite a decent performance…

DeepMind and OpenAI Ideas to Incorporate Human Feedback in Reinforcement Learning Agents

A paper from two years ago introduces some clever ideas to fine tune reward functions in reinforcement learning agents.

Yoshiyuki Igarashi