AutoFocus-IL: VLMによる顕著性マップで人間アノテーション不要のデータ効率の良い視覚模倣学習
AutoFocus-IL: VLM-based Saliency Maps for Data-Efficient Visual Imitation Learning without Extra Human Annotations
視覚言語モデルを使ってデモ中の重要物体を自動特定し、時間的顕著性マップを生成して模倣学習ポリシーを正則化することで、人間の注視データなしにデータ効率と汎化性能を向上させる手法を提案。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Litian Gong, Fatemeh Bahrani, Yutai Zhou, Amin Banayeeanzade, Jiachen Li, Erdem Bıyık
分類: cs.RO, cs.CV
原文アブストラクト
AutoFocus-IL is a simple yet effective method to improve data efficiency and generalization in visual imitation learning by guiding policies to attend to task-relevant features rather than distractors and spurious correlations. Although saliency regularization has emerged as a promising way to achieve this, existing approaches typically require costly supervision such as human gaze data or manual saliency annotations. In contrast, AutoFocus-IL leverages vision-language models (VLMs) to automatically identify and track key objects in demonstrations, generating temporal saliency maps that highlight causal visual signals while suppressing distractors. These maps are then used to regularize behavior cloning policies, yielding stronger alignment between visual attention and task-relevant cues. Experiments in both the CARLA simulator and real-robot manipulation tasks demonstrate that AutoFocus-IL not only outperforms standard behavior cloning but also surpasses state-of-the-art baselines that assume privileged access to human supervision, such as gaze data. Code, datasets, and trained policy videos are available at https://AutoFocus-IL.github.io/.
