Zero shot Learning 論文學習筆記(未完待續)
Zero shot Learning 論文學習筆記
- 前言
- zero-shot learning
- Learning To Detect Unseen Object Classes by Between-Class Attribute Transfer
- Label-Embedding for Attribute-Based Classification
- An embarrassingly simple approach to zero-shot learning
- Transductive Multi-View Zero-Shot Learning
- Zero-shot recognition using dual visualsemantic mapping paths
- Predicting visual exemplars of unseen classes for zero-shot learning
- Semantic Autoencoder for Zero-Shot Learning
- Zero-Shot Learning - A Comprehensive Evaluation of the Good, the Bad and the Ugly
- Zero-Shot Learning via Class-Conditioned Deep Generative Models
- Preserving Semantic Relations for Zero-Shot Learning
- Recent Advances in Zero-shot Recognition
前言
我跨過山河大海,也穿過人山人海…然而前面還是高山大海,人山人海。初入機器學習的大門,爬上DEEPLEARNING的高山,發現前面還是高山,更多,更高,更難爬…ZST就是一座待爬的高山,很顯然,“不學習就會ZST”,“或者一學就會OST”的願景是美好的,正如小時候看的武俠小說和電影裡講的迴夢心經等等神奇武功,但現實卻告訴你,要想達成這樣的本領,你要學的就更多了,學多了就可以觸類旁通,事半功倍,機器學習也是這個道理。知乎專欄裡的前輩分享了一篇博文零次學習(Zero-Shot Learning)入門,給我們準備了爬山的攻略,我就跟著前人的腳步,試讀一下這十篇ZST的論文,跟著前輩啃paper,順便做個讀書筆記,看看能不能對這個問題收穫一知半解,找到解決我困境的鑰匙,再次突破自我。
zero-shot learning
ZSL在人類世界中是存在的,比如今早在地鐵上看到一位姑娘,雖然她帶著口罩,以前從未見過,我也斷定這是個美女,為什麼呢?因為在我的腦海裡,美女都有白皙的皮膚,苗條的身段,還有一雙清澈透明,會說話的眼睛…其實講到這裡,zero-shot的思想也就有了眉目,正如經典的斑馬問題,雖然大多數人沒有見過斑馬,但是擁有馬的外形和黑白相間的線條兩個顯著的特徵,人類就可以推斷出這是斑馬,機器只要在學習特徵和未訓練標籤再做一次決策樹之類的分類,就能得出這樣的推論。
Learning To Detect Unseen Object Classes by Between-Class Attribute Transfer
這是2009年(人工智慧boost次世代前夕)的文章,學習網路用的還是SVM,所以文章也沒有大篇幅的吹噓神經網路的神奇,而是很樸素的提出了自己的基於屬性學習的分類觀點:Attribute-Based Classification。文中提到了人類能至少識別出30000個相關目標的類別,然後用斑馬的例子引出了他的觀點,其主要的工作和貢獻就在下圖裡講述了,即DAP-直接特徵學習和IAP-間接特徵學習。DAP是比較直觀的,各種特徵被平等對待。而IAP對特徵做了一層中間層,可以理解為對特徵做了加權處理,很像DP中的預訓練,凍結層之後做轉移學習的場景,這顯然像一個全連線層。
英文中關於attribute和feature在文中分的比較清,但6級英語水平的我很顯然對此有些困惑。翻遍了baidu和谷歌也是見仁見智,嗨。最後找一篇stanford大學網站機器學習術語表關於兩者的闡述:
An attribute has a domain defined by the attribute type, which denotes the values that can be taken by an attribute.
A feature is the specification of an attribute and its value.
For example, color is an attribute. ``Color is blue'' is a feature of an example.
差強人意的理解一下,但feature, attribute兩個概念將貫穿整個系列論文的學習中,慢慢領悟吧。
Label-Embedding for Attribute-Based Classification
這篇論文誕生於2013年,算是比較早期的文章,作者對屬性Attributes在機器學習領域有個很具體的定義,屬性Attributes是機器學習的中間表示,這個表示允許引數(我理解為feature特徵)在不同的類別之間分享。基於此,論文將基於屬性的影像分類當做了一種標籤嵌入(向量)問題,每一個類別被嵌入到一個屬性向量空間。我覺得這個Abstract寫的非常好,原文如下:
Attributes are an intermediate representation, which en-ables parameter sharing between classes, a must when training
data is scarce. We propose to view attribute-basedimage classification as a label-embedding problem: each class is embedded
in the space of attribute vectors. Weintroduce a function which measures the compatibility be-tween an image and a label
embedding. The parameters ofthis function are learned on a training set of labeled sam-ples to ensure that, given an image,
thecorrect classes rankhigher than the incorrect ones. Results on the Animals WithAttributes and Caltech-UCSD-Birds datasets
show that theproposed framework outperforms the standard Direct At-tribute Prediction baseline in a zero-shot learning
scenario.The label embedding framework offers other advantagessuch as the ability to leverage alternative sources
of infor-mation in addition to attributes (e.g. class hierarchies) orto transition smoothly from zero-shot learning to learningwith large
quantities of data.
An embarrassingly simple approach to zero-shot learning
這篇文章成文與2015年,zero-shot的概念已經提出來了,而且在介紹的段落,文章很清晰的提出可以分訓練階段和預測階段提高zero shot能力。這篇論文的Related Work還是對zero shot做了很多的篇幅的介紹,還強化了Attributes learnings的定義,
Transductive Multi-View Zero-Shot Learning
Zero-shot recognition using dual visualsemantic mapping paths
Predicting visual exemplars of unseen classes for zero-shot learning
Semantic Autoencoder for Zero-Shot Learning
Zero-Shot Learning - A Comprehensive Evaluation of the Good, the Bad and the Ugly
Zero-Shot Learning via Class-Conditioned Deep Generative Models
Preserving Semantic Relations for Zero-Shot Learning
Recent Advances in Zero-shot Recognition
相關文章
- Zero-shot Learning零樣本學習 論文閱讀(三)——Semantic Autoencoder for Zero-Shot Learning
- GDI+學習筆記--未完待續筆記
- 小程式學習筆記(未完待續)筆記
- Zero-shot Learning零樣本學習 論文閱讀(四)——Zero-Shot Recognition using Dual Visual-Semantic Mapping PathsAPP
- Zero-shot Learning零樣本學習 論文閱讀(一)——Learning to detect unseen object classes by between-class attributeObject
- zero-shot-learning-definition-examples-comparison
- 前端學習整理資料(未完待續)前端
- 《Katana ZERO(武刃 零)》:嗑藥過量,未完待續
- 排序【未完待續】排序
- Text Augmented Spatial-aware Zero-shot Referring Image Segmentation論文閱讀筆記(EMNLP23 Findings)Segmentation筆記
- 【論文筆記】Recommendations as Treatments: Debiasing Learning and Evaluation筆記
- 【論文筆記】Learning Fashion Compatibility with Bidirectional LSTMs筆記
- android輸入法機制的學習總結(未完待續)Android
- 【論文筆記】A review of applications in federated learning(綜述)筆記ViewAPP
- 【論文筆記】A Survey on Deep Learning for Named Entity Recognition筆記
- 搜尋全家桶(未完待續)
- JAVA面試題(未完待續)Java面試題
- HashMap原始碼分析,未完待續HashMap原始碼
- Runtime 執行時(未完待續)
- Ensemble distillation for robust model fusion in federated learning論文筆記筆記
- [論文閱讀筆記] Adversarial Learning on Heterogeneous Information Networks筆記ORM
- 論文筆記:What makes instance discrimination good for transfer learning?筆記Go
- 【論文筆記】Neural machine translation by jointly learning to align and translate筆記Mac
- 深度學習 DEEP LEARNING 學習筆記(一)深度學習筆記
- 深度學習 DEEP LEARNING 學習筆記(二)深度學習筆記
- 常用揹包dp模板(未完待續)
- git安裝與使用,未完待續... ...Git
- Maven(個人整理)(一,未完待續)Maven
- AI大模型企業應用實戰(24)-什麼是zero-shot, one-shot和few-shot Learning?AI大模型
- 深度學習論文翻譯解析(十四):SSD: Single Shot MultiBox Detector深度學習
- 論文筆記 Deep Patch Learning for Weakly Supervised Object Classication and Discovery筆記Object
- [論文閱讀筆記] Adversarial Mutual Information Learning for Network Embedding筆記ORM
- Machine Learning 機器學習筆記Mac機器學習筆記
- Elementary OS折騰記錄( 未完待續,一直更新)
- 資料結構的練習day2(未完待續)資料結構
- What Are Zero-Shot Prompting and Few-Shot Prompting
- 字串匹配演算法【未完待續】字串匹配演算法
- Shell 入門系列: 導航 (未完待續)