火には火を以て制す：プライミングによるDNNのショートカット回避
Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming
タスクに関連する入力特徴から粗い推定値を「プライミング」として与えることで、DNNがデータ分布の変化に弱い安易なショートカット解に陥るのを防ぐ手法を提案し、画像分類・連続制御・自動運転で有効性を示した。
著者: Chuan Wen, Jianing Qian, Jierui Lin, Jiaye Teng, Dinesh Jayaraman, Yang Gao
分類: cs.LG, cs.CV, cs.RO
原文アブストラクト
Across applications spanning supervised classification and sequential control, deep learning has been reported to find "shortcut" solutions that fail catastrophically under minor changes in the data distribution. In this paper, we show empirically that DNNs can be coaxed to avoid poor shortcuts by providing an additional "priming" feature computed from key input features, usually a coarse output estimate. Priming relies on approximate domain knowledge of these task-relevant key input features, which is often easy to obtain in practical settings. For example, one might prioritize recent frames over past frames in a video input for visual imitation learning, or salient foreground over background pixels for image classification. On NICO image classification, MuJoCo continuous control, and CARLA autonomous driving, our priming strategy works significantly better than several popular state-of-the-art approaches for feature selection and data augmentation. We connect these empirical findings to recent theoretical results on DNN optimization, and argue theoretically that priming distracts the optimizer away from poor shortcuts by creating better, simpler shortcuts.
