FreqCache: 適応的な周波数ガイド型トークンキャッシングによる身体化VLNモデルの高速化
FreqCache: Accelerating Embodied VLN Models with Adaptive Frequency-Guided Token Caching
VLNモデルの計算コストを削減するため、周波数領域の特性を利用してトークンキャッシュの構築・更新・適応調整を行うFreqCacheを提案した。
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: Zihao Zheng, Xingyue Zhou, Zhihao Mao, Songyu Sun, Lingyue Zhang, Yulong Ao, Yupu Feng, Qiongqiong Zhang, Yonghua Lin, Xiang Chen
分類: cs.RO
原文アブストラクト
Vision-Language-Navigation (VLN) models exhibit excellent navigation accuracy but incur high computational overhead. Token caching has emerged as a promising training-free strategy to reduce this cost by reusing token computation results; however, existing token caching approaches rely on visual domain methods for cacheable token selection, leading to challenges when adapted to VLN models. 1) Visual domain methods become invalid when there is viewpoint migration. 2) Visual domain methods neglect critical edge information without the aid of additional algorithms. 3) Visual domain methods overlook the temporal variation of scenarios and lack adjustability in cache budgets. In this paper, we develop detailed analyses and find that the impacts of these challenges exhibit invariance and analyzability in the frequency domain. Based on these, we propose a frequency-guided token caching framework, called FreqCache. Utilizing the inherent properties of the frequency domain, FreqCache achieves optimal token cache establishment, refreshment, and adaptive adjustment. Experiments show that FreqCache achieves 1.59x speedup with ignorable overhead, showing the effect of integrating frequency domain methods in VLN token caching.
