Deep Self-Taught Learning for Weakly Supervised Object Localization
Abstract 弱監督定位：訓練圖像只有針對圖像的註釋，沒有包含物體的矩形框。弱監督定位越來越重要，因爲它不需要昂貴的邊界框註釋。 大多數現有的弱監督定位（WSL）方法都是通過在圖像級監督學習的特徵的基礎上尋找正的邊界盒來學習檢測器的。但是，這種特徵不包含與空間位置相關的信息，並且通常提供低質量的正樣本來訓練檢測器。 爲了克服這一難題，文章提出了一種深度自學習的方法，使檢測器學習對象級 特徵，從
相關文章
- 1. Deep Self-Taught Learning for Weakly Supervised Object Localization
- 2. 《Deep Self-Taught Learning for Weakly Supervised Object Localization》
- 3. Two-Phase Learning for Weakly Supervised Object Localization
- 4. [CVPR2017] Deep Self-Taught Learning for Weakly Supervised Object Localization 論文筆記
- 5. [CVPR2015] Is object localization for free? – Weakly-supervised learning with convolutional neural n...
- 6. [CVPR2015] Is object localization for free? – Weakly-supervised learning with convolutional neural n
- 7. Rethinking the Route Towards Weakly Supervised Object Localization筆記
- 8. 17-WILDCAT-Weakly-Supervised-Learning-of-DeepConvNets
- 9. Thinking in Weakly Supervised Learning
- 10. 【文獻閱讀】Zigzag Learning for Weakly Supervised Object Detection
- 更多相關文章...
- • Scala for循環 - Scala教程
- • Swift for 循環 - Swift 教程
- • Java Agent入門實戰（三）-JVM Attach原理與使用
- • Java Agent入門實戰（一）-Instrumentation介紹與使用
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. Deep Self-Taught Learning for Weakly Supervised Object Localization
- 2. 《Deep Self-Taught Learning for Weakly Supervised Object Localization》
- 3. Two-Phase Learning for Weakly Supervised Object Localization
- 4. [CVPR2017] Deep Self-Taught Learning for Weakly Supervised Object Localization 論文筆記
- 5. [CVPR2015] Is object localization for free? – Weakly-supervised learning with convolutional neural n...
- 6. [CVPR2015] Is object localization for free? – Weakly-supervised learning with convolutional neural n
- 7. Rethinking the Route Towards Weakly Supervised Object Localization筆記
- 8. 17-WILDCAT-Weakly-Supervised-Learning-of-DeepConvNets
- 9. Thinking in Weakly Supervised Learning
- 10. 【文獻閱讀】Zigzag Learning for Weakly Supervised Object Detection