Long-tailed recognition學習目錄

Yanwei Liu

Jan 22·4 min read

為何稱為Long-tailed recognition？在日常生活中，很多的資料分布都遵循長尾分布。同樣地，在電腦視覺中的dataset也會出現這樣的分布情形。例如某些類別的圖片很多，某些類別的圖片特別少。這樣的情形會造成在圖片較少的類別上，辨識準確度較差的情形產生。Long-tailed recognition的研究旨在減緩dataset不平衡所造成的問題。

20210218更新：A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection

主要想法是使用Object-Centric的圖片進行資料增強，進而提升偵測結果，實驗結果看起來是目前常見方法中最佳的，優於Balanced Meta-softmax

A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection

Object frequencies in daily scenes follow a long-tailed distribution. Many objects do not appear frequently enough in…

arxiv.org

Balanced Meta-Softmax for Long-Tailed Visual Recognition

Deep classifiers have achieved great success in visual recognition. However, real-world data is long-tailed by nature…

arxiv.org

Equalization Loss for Long-Tailed Object Recognition

Object recognition techniques using convolutional neural networks (CNN) have achieved great success. However…

arxiv.org

Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax

Solving long-tail large vocabulary object detection with deep learning based models is a challenging and demanding…

arxiv.org

Seesaw Loss for Long-Tailed Instance Segmentation

Instance segmentation has witnessed a remarkable progress on class-balanced benchmarks. However, they fail to perform…

arxiv.org

Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect

As the class size grows, maintaining a balanced dataset across many classes is challenging because the data are…

arxiv.org

Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation

Despite the previous success of object analysis, detecting and segmenting a large number of object categories with a…

arxiv.org

Long-tailed recognition學習目錄

A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection

Object frequencies in daily scenes follow a long-tailed distribution. Many objects do not appear frequently enough in…

Balanced Meta-Softmax for Long-Tailed Visual Recognition

Deep classifiers have achieved great success in visual recognition. However, real-world data is long-tailed by nature…

Equalization Loss for Long-Tailed Object Recognition

Object recognition techniques using convolutional neural networks (CNN) have achieved great success. However…

Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax

Solving long-tail large vocabulary object detection with deep learning based models is a challenging and demanding…

Seesaw Loss for Long-Tailed Instance Segmentation

Instance segmentation has witnessed a remarkable progress on class-balanced benchmarks. However, they fail to perform…

Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect

As the class size grows, maintaining a balanced dataset across many classes is challenging because the data are…

Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation

Despite the previous success of object analysis, detecting and segmenting a large number of object categories with a…

Yanwei Liu

More from Yanwei Liu

More From Medium

Androgyny: Reviving a Lost Human Condition

Introduction to Transfer Learning

Be Rigorous, Not Ruthless

An Attack on Deep Learning

Artificial Intelligence, Surgery, and Trust

ML: Decision Trees & Random Forests

A.I. against the Odds

Blockchain + AI = Jobs Killer