13:50 〜 14:10
[2U4-IS-2c-02] MANet: Mixed Attention Network for Visual Explanation
[[Online, Regular]]
キーワード:attention mechanism, image recognition, attention map
Visual explanation methods, such as CAM and Grad-CAM, have been proposed to visualize and interpret the decision-making of CNNs. Recently, there are some other works that not only aim to provide better visual explanations, but also to improve the performance of CNNs by using visual explanations. In this work, we propose a network architecture — MANet that generates visual explanation during the inference process using a mixed attention module for adaptive feature refinement and also uses the generated attention map to improve network performance on image recognition tasks. Experimental results show that our proposed MANet achieves better visual performance and outperforms the baseline models on both image classification and object detection tasks.
講演PDFパスワード認証
論文PDFの閲覧にはログインが必要です。参加登録者の方は「参加者用ログイン」画面からログインしてください。あるいは論文PDF閲覧用のパスワードを以下にご入力ください。