基盤モデル整合による生成的イベント事前学習
Generative Event Pretraining with Foundation Model Alignment
イベントカメラのデータに、画像基盤モデルの知識を整合させつつ、時系列生成事前学習を行う2段階フレームワークを提案し、認識・セグメンテーション・深度推定などで最先端性能を達成した。
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: Jianwen Cao, Jiaxu Xing, Nico Messikommer, Davide Scaramuzza
分類: cs.CV, cs.RO
原文アブストラクト
Event cameras provide robust visual signals under fast motion and challenging illumination conditions thanks to their microsecond latency and high dynamic range. However, their unique sensing characteristics and limited labeled data make it challenging to train event-based visual foundation models (VFMs), which are crucial for learning visual features transferable across tasks. To tackle this problem, we propose GEP (Generative Event Pretraining), a two-stage framework that transfers semantic knowledge learned from internet-scale image datasets to event data while learning event-specific temporal dynamics. First, an event encoder is aligned to a frozen VFM through a joint regression-contrastive objective, grounding event features in image semantics. Second, a transformer backbone is autoregressively pretrained on mixed event-image sequences to capture the temporal structure unique to events. Our approach outperforms state-of-the-art event pretraining methods on a diverse range of downstream tasks, including object recognition, segmentation, and depth estimation. Together, VFM-guided alignment and generative sequence modeling yield a semantically rich, temporally aware event model that generalizes robustly across domains.
