Conservative-Progressive Collaborative Learning for Semi-supervised Semantic Segmentation
Siqi Fan, Fenghua Zhu, Zunlei Feng, Yisheng Lv, Mingli Song, Fei-Yue Wang
Introduction
SSL技術主要有兩種典型的作法,Entropy minimization和consistency regularization,兩種做法都仰賴於pseudo supervision,導致不正確的pseudo label產生confirmation bias,大部分方法為了解決此問題而使用預測分數(設立threshold)來選擇可信賴的pseudo label,這樣的作法可能使大量的unlabel data資源被浪費。
Image Not Showing
Possible Reasons
- The image was uploaded to a note which you don't have access to
- The note which the image was originally uploaded to has been deleted
Learn More →
Teacher-Student和Student-Student是兩種典型的double branch學習方式,Student-Student訓練時的兩種網路結構容易有模型偶合的問題產生,導致錯誤的結果和限制性。
作者提出Conservative-Progressive Collaborative Learning (CPCL),平行使用兩種相同結構的網路但使用不同初始值,Conservative只使用高質量的pseudo label做intersection(交集) supervision; Progressive則使用大數量的pseudo label做union supervision。藉由這兩個網路的預測結果生成pseudo label,且兩個網路是在相異知識下進行訓練,因此可降低偶合的問題。
除此之外預測結果的信心值被使用在 loss re-weighting當中,為了解決不可避免的noisy pseudo labels。
Image Not Showing
Possible Reasons
- The image was uploaded to a note which you don't have access to
- The note which the image was originally uploaded to has been deleted
Learn More →
Contribution
- CPCL在使用union supervision保留相異部份時也透過intersection supervision尋找共通點已達成保守評估和進步挖掘兩方面的合作,且由與兩個網路結構在相異知識下訓練的性質可有效解決耦合問題。
- 使用class-wise的不一致指標用來產生不一致部分的pseudo label,且基於信心值對loss做re-weighting,避免noise pseudo label造成的錯誤太巨大
Framework
Image Not Showing
Possible Reasons
- The image was uploaded to a note which you don't have access to
- The note which the image was originally uploaded to has been deleted
Learn More →
Problem Definition
為label data數量
為unlabel data數量,且
label data使用傳統的supervised方式做訓練,此篇論文著重將unlabel data 在兩個相同結構但不同初始值的和做訓練
Data augmentation
作者採用srtong augmentation的cutmix方式,將任兩張圖片做隨機區塊裁切上
取得強化後的
兩個網路分支的前處理近乎相同,首先會先輸入三張影像,以來舉例:
Image Not Showing
Possible Reasons
- The image was uploaded to a note which you don't have access to
- The note which the image was originally uploaded to has been deleted
Learn More →
接著利用及做cutmix,取得 :
相同作法也在Progressive分支下取得及,利用及來生成pseudo label
pseudo label generation
Image Not Showing
Possible Reasons
- The image was uploaded to a note which you don't have access to
- The note which the image was originally uploaded to has been deleted
Learn More →
根據每個pixel判斷若經由兩網路結果相等則此pixel為agreement,否則為disagreement
Agreement
為agreement 部分的第i個pixel, 直接使用 當作pseudo label
Disagreement
Image Not Showing
Possible Reasons
- The image was uploaded to a note which you don't have access to
- The note which the image was originally uploaded to has been deleted
Learn More →
先計算出class-wise的pseudo label指標,上圖的矩陣縱軸及橫軸分別為不同網路預測的結果,為A網路預測結果為第j類別及B網路預測結果為第k類別的pixel總數量,對角線綠色區塊為agreement的預測類別數量,紅色為disagreement
Image Not Showing
Possible Reasons
- The image was uploaded to a note which you don't have access to
- The note which the image was originally uploaded to has been deleted
Learn More →
為第i個pixel最後的pseudo label,A網路預測的class為j;B網路預測為k,根據計算出來的指標若,選擇 作為該pixel的pseudo label,,則選擇