Open in app

Sign In

Write

Sign In

Sieun Park
Sieun Park

248 Followers

Home

About

Pinned

My Academic readings & Medium Stories

Table of content for my academic readings and medium stories as of November 11, 2021. Best Selections Swin Transformers: The most powerful tool in Computer Vision The title is catchy, but it is true(at least as of writing the article). Swin transformers seem to be a game-changer in…sieunpark77.medium.com R-Drop, a simple trick to improve DropOut The method is simple, but results are significant. R-Drop achieves SOTA on NMT tasks even with the VANILLA Transformer…medium.com

Deep Learning

3 min read

Deep Learning

3 min read


Published in

CodeX

·May 19

Sentencepiece: A simple and language-independent subword tokenizer and detokenizer for neural text processing

Tokenization method for LLaMA, T5, XLNet — Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates [ACL 2018] [github] Publish month(arxiv): 2018.08 Code: [Colab] Tags: nlp, tokenization ✰ Best viewed in [Notion] Overview Sentencepiece is both an improved tokenization algorithm and implementation by the researchers at Google. The terms below seem overwhelming, but they are very…

Naturallanguageprocessing

9 min read

Sentencepiece: A simple and language independent subword tokenizer and detokenizer for neural text…
Sentencepiece: A simple and language independent subword tokenizer and detokenizer for neural text…
Naturallanguageprocessing

9 min read


Published in

CodeX

·Apr 16

An Introduction to Multiprocessing Using Python

Is multithreading or multiprocessing faster than another? — ✰ Best viewed in [Notion] Overview In Python, multiprocessing and multithreading are primarily important for improved performance. Both multiprocessing and multithreading help maximize the utilization of a system’s CPU and other resources. By distributing tasks across multiple threads or processes, they enable parallel execution, which can lead to significant performance improvements…

Python

10 min read

An Introduction to Multiprocessing Using Python
An Introduction to Multiprocessing Using Python
Python

10 min read


Mar 5

Improving subword tokenization with Subword Regularization

Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates [ACL 2018] Publish month(arxiv): 2018.04 Tags: nlp, tokenization ✰ Best viewed in [Notion] Subword Regularization: Improving Neural Network Translation Models with Multiple Subword… A sentence can be represented in multiple subword sequences even with the same vocabulary. Previous methods don't…deep-learning.notion.site

Deep Learning

5 min read

Subword Regularization
Subword Regularization
Deep Learning

5 min read


Published in

MLearning.ai

·Jun 7, 2022

Fundamentals of Object Detection: Faster, Mask, Cascade R-CNN 🔥

Faster R-CNN is still an actively cited benchmark for comparing object detection performance of modern network architectures. In this post, we will discuss the insights and contributions of the papers. Introduction — Why do we even care in 2022? Faster R-CNN was a huge breakthrough in computer vision because it enabled real-time object detection and enabled end-to-end training of…

Deep Learning

19 min read

Details of Faster, Mask, Cascade R-CNN 🔥
Details of Faster, Mask, Cascade R-CNN 🔥
Deep Learning

19 min read


Published in

CodeX

·Nov 1, 2021

ConvMixer: Patches Are All You Need? Overview and thoughts 🤷

CNNs don’t always have to progressively decrease resolution. A revolutionary idea that might shape the next-gen architectures for Computer Vision. — TL;DR: Transformers(NLP): Isotropic architecture+Self-attention ViT: Transformers(NLP)+Patch representation CNNs: Pyramid architecture(decreasing resolution)+Convolution ConvMixer: Isotropic architecture+Patch representation+Convolution Transformers are represented by the extensive use of attention and their isotropic architecture, which repeats the same block multiple times. They demonstrated amazing performance for many problems, especially in natural language processing. However, the…

Deep Learning

8 min read

ConvMixer: Patches Are All You Need? Overview and thoughts 🤷
ConvMixer: Patches Are All You Need? Overview and thoughts 🤷
Deep Learning

8 min read


Published in

CodeX

·Oct 29, 2021

7 Different Convolutions for designing CNNs that will Level-up your Computer Vision project

In-depth review on Basic, Transposed, Dilated, Separable, Depthwise, and Pointwise convolutions and their applications. — Recent research on CNN architectures include so much different variants of convolutions that confused me while reading these papers. I thought it would be worth it to go through the precise definitions, effects, and use cases(in computer vision & deep-learning) of some of the more popular convolution variants. …

Deep Learning

8 min read

7 Different Convolutions for designing CNNs that will Level-up your Computer Vision project
7 Different Convolutions for designing CNNs that will Level-up your Computer Vision project
Deep Learning

8 min read


Published in

CodeX

·Oct 27, 2021

R-Drop, a simple trick to improve DropOut

Deep-learning is used everywhere, but they often overfit the training data and are not generalizable to unseen samples. Various regularization techniques prevent such overfitting. Dropout is one of the most popular and powerful regularization techniques, used regardless of network architecture and type of task. …

NLP

8 min read

R-Drop, a simple trick to improve DropOut
R-Drop, a simple trick to improve DropOut
NLP

8 min read


Published in

CodeX

·Oct 26, 2021

Making VGG-style convnets great again with RepVGG

VGG is considered one of the cornerstones of deep CNNs. The authors of VGG provided widely accepted principles for designing CNNs. In particular, they suggest that multiple 3 × 3 convolutions are more efficient than using larger kernel sizes. However, the VGG architecture, composed of nothing but successive stacks of…

Deep Learning

8 min read

Making VGG-style convnets great again with RepVGG
Making VGG-style convnets great again with RepVGG
Deep Learning

8 min read


Published in

CodeX

·Oct 22, 2021

Implementing R-CNN object detection on VOC2012 with PyTorch

Object detection is a complex problem in computer vision that involves localizing and classifying multiple objects from a given image. It is one of the most practically important and widely researched problem in computer vision. There is a wide variety of approaches to object detection including deep-learning based methods. These…

Deep Learning

12 min read

Implementing R-CNN object detection on VOC2012 with PyTorch
Implementing R-CNN object detection on VOC2012 with PyTorch
Deep Learning

12 min read

Sieun Park

Sieun Park

248 Followers

AI Engineer at allganize.ai, Korean student, 18 years old, contact me/coffee chat LinkedIn: https://bit.ly/2VTkth7 😀

Following
  • Sik-Ho Tsang

    Sik-Ho Tsang

  • Barack Obama

    Barack Obama

  • Whale Learning

    Whale Learning

  • Diego Bonilla

    Diego Bonilla

  • AI Hater

    AI Hater

See all (20)

Help

Status

Writers

Blog

Careers

Privacy

Terms

About

Text to speech