Corner2Net用级联角点检测，提升精度与速度。
Corner2Net: Detecting Objects as Cascade Corners
- 分两步级联预测角点对，避免传统匹配错误
- 在COCO上精度和速度均超越现有角点检测器
- 兼容主流骨干网络，适合目标检测研究者
基于角点的检测范式具有生成高质量边界框的潜力，但受限于三大因素：1）角点匹配困难，启发式匹配易出错，尤其在相似物体共现时；2）实例上下文信息不足，两个独立角点难以保留充分语义，难保证同类别角点在同一热图通道；3）骨干网络不友好，堆叠网络训练成本高。为此，我们提出新型角点检测框架Corner2Net。为实现无角点匹配，设计级联角点流程：分两步逐步预测关联角点对，而非并行搜索两个独立角点。Corner2Net解耦角点定位与分类，两个角点均为类别无关，实例特异性右下角进一步缩小搜索空间；同时提取富含语义的区域特征用于分类。可轻松接入主流骨干网络（如ResNeXt）。在COCO数据集上的实验表明，Corner2Net在精度和速度上均显著超越现有角点检测器。
原文摘要 · Abstract (English)
The corner-based detection paradigm enjoys the potential to produce high-quality boxes. But the development is constrained by three factors: 1) Hard to match corners. Heuristic corner matching algorithms can lead to incorrect boxes, especially when similar-looking objects co-occur. 2) Poor instance context. Two separate corners preserve few instance semantics, so it is difficult to guarantee getting both two class-specific corners on the same heatmap channel. 3) Unfriendly backbone. The training cost of the hourglass network is high. Accordingly, we build a novel corner-based framework, named Corner2Net. To achieve the corner-matching-free manner, we devise the cascade corner pipeline which progressively predicts the associated corner pair in two steps instead of synchronously searching two independent corners via parallel heads. Corner2Net decouples corner localization and object classification. Both two corners are class-agnostic and the instance-specific bottom-right corner further simplifies its search space. Meanwhile, RoI features with rich semantics are extracted for classification. Popular backbones (e.g., ResNeXt) can be easily connected to Corner2Net. Experimental results on COCO show Corner2Net surpasses all existing corner-based detectors by a large margin in accuracy and speed.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。