2023年全國碩士研究生考試考研英語一試題真題(含答案詳解+作文范文)_第1頁
已閱讀1頁,還剩150頁未讀 繼續(xù)免費閱讀

下載本文檔

版權(quán)說明:本文檔由用戶提供并上傳,收益歸屬內(nèi)容提供方,若內(nèi)容存在侵權(quán),請進(jìn)行舉報或認(rèn)領(lǐng)

文檔簡介

1、Object recognition has been extensively studied in the history of computer vision as one of the most fundamental problems.Among years,the research objective has evolved drastically,especially with the growth of data scal

2、e available on the web.In this dissertation,we study one of the latest and most challenging ob ject recognition tasks-fine-grained visual categorization(FGVC).Inparticular,we consider several practical issues for conduct

3、ing FGVC in real-world applications,including classification accuracy,generalization ability,model interpretation and runtime e?ciency.To do so,several FGVC algorithms are proposed to cover application scenarios where va

4、rious kinds of supervision are provided for training models. The main con-tribution of this thesis,therefore,is to propose a general pipeline for conducting fine-grained visual categorization in a variety of real-world a

5、pplications based on the proposed algorithms.
  Our first work aims to improve the generalization ability of FGVC algorithms by reducing the extensive requirement of human-labeled annotations.We study FGVC under the w

6、eakest form of supervi-sion,where only image-level labels are provided for training.For this challenging task,the proposed weakly supervised FGVC al-gorithm employs the widely used multi-instance learning framework,but c

7、onducting a carefully designed initialization strategy via a novel multi-task co-localization algorithm.The localization results,mean-while,also enable object-level domain-specific fine-tuning of deep neu-ral networks,wh

8、ich significantly boosts the performance.
  Our second work targets on further improving the classification accu-racyof FGVC.Motivated by the recent success of part-based models and deep convolutional features in

9、 FGVC,the proposed method fol-lows a semi-supervised framework that exploits inexhaustible web data to augment existing strongly supervised FGVC datasets,so that the scale of extensive labeled training data could keep pa

10、ce with the rapid evolution of the convolutional neural network(CNN)architec-tures. Our key discovery is that by transferring explicit knowledge learned from strongly supervised datasets using sophisticated object recogn

11、ition methods,each web image can now carry additional do-main specific knowledge,which leads to an increased information gain.The proposed method achieves state-of-the-art performance on sev-eral FGVC benchmarks,where th

12、e improvement comes from both the perspective of features and classifiers.
  In addition to the pursuit of the classification performance,we also investigate a set of other practical issues on performing FGVC in real-

13、world applications,i.e.,the model interpretability and runtime e?ciency.Implementing asa strongly supervised FGVC algo-rithm,a novel Part-Stacked CNN architecture is proposed,which is able to run at real-time by utilizin

14、g a set of computational sharing and architectural sharing strategies on multiple ob ject parts,and provide human understandable visual manuals for explaining the classifica-tion results through part-level analysis.Exper

溫馨提示

  • 1. 本站所有資源如無特殊說明,都需要本地電腦安裝OFFICE2007和PDF閱讀器。圖紙軟件為CAD,CAXA,PROE,UG,SolidWorks等.壓縮文件請下載最新的WinRAR軟件解壓。
  • 2. 本站的文檔不包含任何第三方提供的附件圖紙等,如果需要附件,請聯(lián)系上傳者。文件的所有權(quán)益歸上傳用戶所有。
  • 3. 本站RAR壓縮包中若帶圖紙,網(wǎng)頁內(nèi)容里面會有圖紙預(yù)覽,若沒有圖紙預(yù)覽就沒有圖紙。
  • 4. 未經(jīng)權(quán)益所有人同意不得將文件中的內(nèi)容挪作商業(yè)或盈利用途。
  • 5. 眾賞文庫僅提供信息存儲空間,僅對用戶上傳內(nèi)容的表現(xiàn)方式做保護處理,對用戶上傳分享的文檔內(nèi)容本身不做任何修改或編輯,并不能對任何下載內(nèi)容負(fù)責(zé)。
  • 6. 下載文件中如有侵權(quán)或不適當(dāng)內(nèi)容,請與我們聯(lián)系,我們立即糾正。
  • 7. 本站不保證下載資源的準(zhǔn)確性、安全性和完整性, 同時也不承擔(dān)用戶因使用這些下載資源對自己和他人造成任何形式的傷害或損失。

評論

0/150

提交評論