InterPruner：面向多模态目标检测的、基于泰勒隐式准则与语言先验调制器的交互式结构化剪枝框架
InterPruner: Interactive Structured Pruning via Taylor-Implicit Criterion and Language-Prior Modulator for Multimodal Object Detection
- Beijing University of Technology（北京工业大学）
- Southwest University（西南大学）
- China University of Geosciences Wuhan（中国地质大学（武汉））
- Tsinghua University（清华大学）
- Beijing Institute of Technology（北京理工大学）
- Yunnan Normal University（云南师范大学）
- Beijing Forestry University（北京林业大学）
- Ghent University（根特大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出首个面向红外-可见光目标检测器的交互式结构化通道剪枝框架InterPruner，结合TIC、MIRA、SPCA方法，在FLIR数据集剪枝50%通道时mAP提升0.6%，代码将发布于GitHub。
AI中文摘要：
多模态目标检测在遥感领域被证明是有效的，尤其是在红外-可见光（RGB-Infrared）范式中。并行特征提取器为鲁棒检测提供了丰富的多模态信息，但也带来了大量的通道冗余与计算开销。现有的剪枝方法可减少通道冗余，不过它们是为单模态骨干网络设计的，忽略了跨模态交互与动态场景相关的冗余。本文提出了InterPruner，首个面向红外-可见光目标检测器的交互式结构化通道剪枝框架。具体而言，我们首先推导了泰勒隐式准则（Taylor-Implicit Criterion, TIC），通过高阶泰勒展开与隐函数定理量化通道重要性；随后，模态交互冗余分析器（Modality Interaction Redundancy Analyzer, MIRA）通过互补偿性评估识别冗余通道；最后，场景先验通道锚定器（Scene-Prior Channel Anchor, SPCA）将语言先验作为语义锚点，衡量通道-场景相关性以实现动态通道重要性估计。针对红外-可见光检测的跨模态通道剪枝仍待探索，在红外-可见光目标检测数据集上开展的大量实验表明，InterPruner在性能几乎无下降的情况下保持了高检测性能，具体而言，在FLIR数据集上剪枝50%的通道时，其mAP甚至提升了0.6%。代码将在GitHub上发布以促进后续研究。
英文摘要：
Multimodal object detection proves effective in remote sensing, especially the RGB-Infrared paradigm. The parallel feature extractors provide rich multimodal information for robust detection, yet introduce substantial channel redundancy and computational overhead. Existing pruning methods can reduce channel redundancy, but they are designed for unimodal backbones, overlooking cross-modal interactions and dynamic scene-wise redundancy. In this paper, we propose InterPruner, the first interactive structured channel pruning framework for RGB-infrared object detectors. Specifically, we first derive a Taylor-Implicit Criterion(TIC) to quantify channel importance via high-order Taylor expansion and the implicit function theorem. Then, a Modality Interaction Redundancy Analyzer (MIRA) identifies redundant channels via mutual compensability assessment. Finally, a Scene-Prior Channel Anchor (SPCA) uses language priors as semantic anchors to measure channel-scene relevance for dynamic channel importance estimation. Cross-modality channel pruning for RGB-Infrared detection is yet unexplored. Extensive experiments on RGB-infrared object detection dataset demonstrate that InterPruner maintains high performance with negligible degradation. Specifically, it even achieves a 0.6% mAP increase on the FLIR dataset when pruning 50% of the channels. Code will be available on GitHub to facilitate future work.
