Deep long-tailed learning, one of the most challenging problems in visual recognition, aims to train well-performing deep models from a large number of images that follow a long-tailed class distribution. In the last decade, deep learning has emerged as a powerful recognition model for learning high-quality image representations and has led to remarkable breakthroughs in generic visual recognition. However, long-tailed class imbalance, a common problem in practical visual recognition tasks, often limits the practicality of deep network based recognition models in real-world applications, since they can be easily biased towards dominant classes and perform poorly on tail classes. To address this problem, a large number of studies have been conducted in recent years, making promising progress in the field of deep long-tailed learning. Considering the rapid evolution of this field, this paper aims to provide a comprehensive survey on recent advances in deep long-tailed learning. To be specific, we group existing deep long-tailed learning studies into three main categories (i.e., class re-balancing, information augmentation and module improvement), and review these methods following this taxonomy in detail. Afterward, we empirically analyze several state-of-the-art methods by evaluating to what extent they address the issue of class imbalance via a newly proposed evaluation metric, i.e., relative accuracy. We conclude the survey by highlighting important applications of deep long-tailed learning and identifying several promising directions for future research.

0
7
下載
關閉預覽

相關內容

主題:Video Super Resolution Based on Deep Learning: A comprehensive survey

摘要:近年來,深度學習在圖像識別,視頻分析,自然語言處理和語音識別(包括視頻超分辨率任務)領域取得了長足的進步。在這項調查中,我們全麵研究了基於深度學習的28種最先進的視頻超分辨率方法。眾所周知,視頻幀內信息的杠杆作用對於視頻超分辨率很重要。因此,我們提出了一種分類法,並根據利用幀間信息的方法將這些方法分為六個子類別。此外,詳細描述了所有方法的體係結構和實現細節(包括輸入和輸出,損失函數和學習率)。最後,我們總結並比較了它們在不同放大率下在一些基準數據集上的性能。我們還討論了一些挑戰,視頻超分辨率社區的研究人員需要進一步解決這些挑戰。因此,這項工作有望為視頻超分辨率研究的未來發展做出貢獻,並減輕現有和未來技術的可理解性和可移植性。

成為VIP會員查看完整內容
2
20
0

題目:Time Series Forecasting With Deep Learning: A Survey

摘要:

為了適應不同領域的時間序列數據集的多樣性,已經開發了大量的深度學習體係結構。在這篇文章中,我們調查了常用的編碼器和譯碼器設計,它們都被用於一階前和多視距的時間序列預測——描述了時間信息是如何被每個模型合並到預測中的。接下來,將重點介紹混合深度學習模型的最新發展,該模型將經過充分研究的統計模型與神經網絡組件相結合,以改進這兩類中的純方法。最後,我們概述了一些方法,即深度學習也可以促進決策支持與時間序列數據。

成為VIP會員查看完整內容
2
88
0

題目:The Deep Learning Compiler: A Comprehensive Survey

摘要:在不同的DL硬件上部署各種深度學習(deep learning,DL)模型的困難,推動了DL編譯器在社區中的研究和開發。業界和學術界都提出了一些DL編譯器,如Tensorflow XLA和TVM。類似地,DL編譯器將不同DL框架中描述的DL模型作為輸入,然後為不同的DL硬件生成優化代碼作為輸出。然而,現有的調查沒有全麵分析DL編譯器的獨特設計。在本文中,我們對現有DL編譯器進行了全麵的調查,通過對常用設計的詳細剖析,著重介紹了麵向DL的多級IRS,以及前端/後端優化。具體來說,我們提供了一個全麵的比較現有的DL編譯器從各個方麵。此外,我們還詳細分析了多級IR設計和編譯器優化技術。最後,提出了DL編譯器潛在的研究方向。這是第一篇針對DL編譯器獨特設計的綜述性論文,希望能為以後的研究鋪平道路。

成為VIP會員查看完整內容
2
27
0

題目:Deep Learning for Visual Tracking: A Comprehensive Survey

簡介:視覺目標跟蹤是計算機視覺領域中最受關注和最具挑戰性的研究課題之一。考慮到這個問題的不適定性質及其在現實世界中廣泛應用的情況,已經建立了大量的大型基準數據集,在這些數據集上已經開發了相當多的方法,並在近年來取得了顯著進展——主要是最近基於深度學習(DL)的方法。這項綜述的目的是係統地調查當前基於深度學習的視覺跟蹤方法、基準數據集和評估指標。它也廣泛地評價和分析領先的視覺跟蹤方法。首先,從網絡體係結構、網絡利用、視覺跟蹤網絡訓練、網絡目標、網絡輸出、相關濾波優勢利用六個關鍵方麵,總結了基於dll的方法的基本特征、主要動機和貢獻。其次,比較了常用的視覺跟蹤基準及其各自的性能,總結了它們的評價指標。第三,在OTB2013、OTB2015、VOT2018和LaSOT等一係列成熟的基準上,全麵檢查最先進的基於dll的方法。最後,通過對這些最先進的方法進行定量和定性的批判性分析,研究它們在各種常見場景下的優缺點。它可以作為一個溫和的使用指南,讓從業者在什麼時候、在什麼條件下選擇哪種方法。它還促進了對正在進行的問題的討論,並為有希望的研究方向帶來光明。

成為VIP會員查看完整內容
Deep_Learning_for_Visual_Tracking.pdf
6
44
0

文章題目

圖論深度學習研究綜述:A comprehensive collection of recent papers on graph deep learning

文章內容

作者懷著大公無私的精神,致力於服務廣大AI從事人員,此次將關於圖深度學習的最新最經典的書籍,論文等資料全部搜集了一下,以供廣大圖深度學習者參考,內容海納百川,包羅萬象,精彩豐富,實在不容錯過。

成為VIP會員查看完整內容
0
32
0

《Deep Learning Based Detection and Correction of Cardiac MR Motion Artefacts During Reconstruction for High-Quality Segmentation》I Oksuz, J R. Clough, B Ruijsink, E P Anton, A Bustin, G Cruz, C Prieto, A P. King, J A. Schnabel [King’s College London] (2019)

成為VIP會員查看完整內容
0
23
0

Deep Learning with Python introduces the field of deep learning using the Python language and the powerful Keras library. Written by Keras creator and Google AI researcher François Chollet, this book builds your understanding through intuitive explanations and practical examples.

成為VIP會員查看完整內容
17
87
0

The tutorial is written for those who would like an introduction to reinforcement learning (RL). The aim is to provide an intuitive presentation of the ideas rather than concentrate on the deeper mathematics underlying the topic. RL is generally used to solve the so-called Markov decision problem (MDP). In other words, the problem that you are attempting to solve with RL should be an MDP or its variant. The theory of RL relies on dynamic programming (DP) and artificial intelligence (AI). We will begin with a quick description of MDPs. We will discuss what we mean by “complex” and “large-scale” MDPs. Then we will explain why RL is needed to solve complex and large-scale MDPs. The semi-Markov decision problem (SMDP) will also be covered.

The tutorial is meant to serve as an introduction to these topics and is based mostly on the book: “Simulation-based optimization: Parametric Optimization techniques and reinforcement learning” [4]. The book discusses this topic in greater detail in the context of simulators. There are at least two other textbooks that I would recommend you to read: (i) Neuro-dynamic programming [2] (lots of details on convergence analysis) and (ii) Reinforcement Learning: An Introduction [11] (lots of details on underlying AI concepts). A more recent tutorial on this topic is [8]. This tutorial has 2 sections: • Section 2 discusses MDPs and SMDPs. • Section 3 discusses RL. By the end of this tutorial, you should be able to • Identify problem structures that can be set up as MDPs / SMDPs. • Use some RL algorithms.

成為VIP會員查看完整內容
3
79
0

With the rise and development of deep learning, computer vision has been tremendously transformed and reshaped. As an important research area in computer vision, scene text detection and recognition has been inescapably influenced by this wave of revolution, consequentially entering the era of deep learning. In recent years, the community has witnessed substantial advancements in mindset, approach and performance. This survey is aimed at summarizing and analyzing the major changes and significant progresses of scene text detection and recognition in the deep learning era. Through this article, we devote to: (1) introduce new insights and ideas; (2) highlight recent techniques and benchmarks; (3) look ahead into future trends. Specifically, we will emphasize the dramatic differences brought by deep learning and the grand challenges still remained. We expect that this review paper would serve as a reference book for researchers in this field. Related resources are also collected and compiled in our Github repository:https://github.com/Jyouhou/SceneTextPapers.

成為VIP會員查看完整內容
2
48
0

The Growing Pushback Against Harmful AI,AI Now co-founders Kate Crawford and Meredith Whittaker opened the Symposium with a short talk summarizing some key moments of opposition over the year, focusing on five themes: (1) facial and affect recognition; (2) the movement from “AI bias” to justice; (3) cities, surveillance, borders; (4) labor, worker organizing, and AI, and; (5) AI’s climate impact. Below is an excerpt from their talk.

成為VIP會員查看完整內容
1
32
0
小貼士
文章信息
相關主題
相關論文
Arxiv
0+閱讀 · 2021年12月5日
Arxiv
109+閱讀 · 2020年9月6日
Image Segmentation Using Deep Learning: A Survey
Arxiv
34+閱讀 · 2020年1月15日
Arxiv
40+閱讀 · 2018年12月11日
Deep Learning for Generic Object Detection: A Survey
Arxiv
9+閱讀 · 2018年9月6日
A Survey on Deep Transfer Learning
Arxiv
11+閱讀 · 2018年8月6日
Arxiv
10+閱讀 · 2018年7月31日
Arxiv
5+閱讀 · 2017年7月25日
相關資訊
Multi-Task Learning的幾篇綜述文章
深度學習自然語言處理
11+閱讀 · 2020年6月15日
人工智能 | SCI期刊專刊信息3條
Call4Papers
5+閱讀 · 2019年1月10日
強化學習的Unsupervised Meta-Learning
CreateAMind
7+閱讀 · 2019年1月7日
Unsupervised Learning via Meta-Learning
CreateAMind
32+閱讀 · 2019年1月3日
A Technical Overview of AI & ML in 2018 & Trends for 2019
待字閨中
10+閱讀 · 2018年12月24日
Hierarchical Imitation - Reinforcement Learning
CreateAMind
16+閱讀 · 2018年5月25日
Hierarchical Disentangled Representations
CreateAMind
3+閱讀 · 2018年4月15日
深度學習(deep learning)發展史
機器學習算法與Python學習
7+閱讀 · 2018年3月19日
資源|斯坦福課程:深度學習理論!
全球人工智能
14+閱讀 · 2017年11月9日
Top
微信掃碼谘詢專知VIP會員
Top