DynaNav: Dynamic Feature and Layer Selection for Efficient Visual Navigation
Visual navigation is essential for robotics and embodied AI. However, existing foundation models, particularly those with transformer decoders, suffer from high computational overhead and lack interpretability, limiting their deployment in resource-tight scenarios. To address this, we propose DynaNav, a Dynamic Visual Navigation framework that adapts feature and layer selection based on scene complexity. It employs a trainable hard feature selector for sparse operations, enhancing efficiency and interpretability. Additionally, we integrate feature selection into an early-exit mechanism, with Bayesian Optimization determining optimal exit thresholds to reduce computational cost. Extensive experiments in real-world-based datasets and simulated environments demonstrate the effectiveness of DynaNav. Compared to ViNT, DynaNav achieves a 2.26x reduction in FLOPs, 42.3% lower inference time, and 32.8% lower memory usage, while improving navigation performance across four public datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
Visual NavigationSimilar Papers 제목 키워드 기반
Fine-Grained Visual Classification via Internal Ensemble Learning Transformer
Recently, vision transformers (ViTs) have been investigated in fine-grained visual recognition (FGVC) and are now considered state of the art. However, most ViT-based works ignore the different learning performances of…
ClassificationEnsemble LearningFine-Grained Image ClassificationFine-Grained Visual RecognitionMulti-Layer Visual Feature Fusion in Multimodal LLMs: Methods, Analysis, and Best Practices
Multimodal Large Language Models (MLLMs) have made significant advancements in recent years, with visual features playing an increasingly critical role in enhancing model performance. However, the integration of multi-la…
Language ModelingLanguage ModellingTIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic Environments
Robots in dynamic, human-centric environments must follow language instructions while maintaining real-time reactive control. Vision-language-action (VLA) models offer a promising framework, but they assume temporally al…
Reinforcement LearningRobot NavigationStage-adaptive Token Selection for Efficient Omni-modal LLMs
Omni-modal large language models (om-LLMs) achieve unified audio-visual understanding by encoding video and audio into temporally aligned token sequences interleaved at the window level. However, processing these dense n…
Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection
Vision Transformers (ViTs) have become increasingly popular in large-scale Vision and Language Pre-training (VLP) models. Although previous VLP research has demonstrated the efficacy of ViTs, these efforts still struggle…