论文标题
用自动对象密钥零件发现凝结两个阶段检测
Condensing Two-stage Detection with Automatic Object Key Part Discovery
论文作者
论文摘要
现代的两阶段对象探测器通常需要过多的模型才能实现高精度。为了解决这个问题，我们建议通过集中在对象关键部位上，可以将两阶段检测头的模型参数凝结和降低。为此，我们首先引入一个自动对象密钥零件发现任务，以使神经网络在每个前景对象中发现代表性子部分。借助这些发现的关键部分，我们将对象外观建模分解为关键部分建模过程和全局建模过程。关键零件建模编码发现的关键部分的精细和详细的特征，全局建模编码粗糙和整体的对象特征。实际上，这种分解使我们能够显着删除模型参数，而无需牺牲很大的检测准确性。流行数据集的实验表明，我们提出的技术始终保持原始性能，同时放弃了约50％的常见两阶段检测头的模型参数，而当放弃约96％的原始模型参数的96％时，性能只会下降1.5％。代码在以下内容上发布：https：//github.com/zhechen/condensing2StageTection。
Modern two-stage object detectors generally require excessively large models for their detection heads to achieve high accuracy. To address this problem, we propose that the model parameters of two-stage detection heads can be condensed and reduced by concentrating on object key parts. To this end, we first introduce an automatic object key part discovery task to make neural networks discover representative sub-parts in each foreground object. With these discovered key parts, we then decompose the object appearance modeling into a key part modeling process and a global modeling process for detection. Key part modeling encodes fine and detailed features from the discovered key parts, and global modeling encodes rough and holistic object characteristics. In practice, such decomposition allows us to significantly abridge model parameters without sacrificing much detection accuracy. Experiments on popular datasets illustrate that our proposed technique consistently maintains original performance while waiving around 50% of the model parameters of common two-stage detection heads, with the performance only deteriorating by 1.5% when waiving around 96% of the original model parameters. Codes are released on: https://github.com/zhechen/Condensing2stageDetection.
