End-to-End Integration of a Convolutional Network, Deformable Parts Model and Non-Maximum Suppression.
IEEE Conference on Computer Vision and Pattern Recognition(2015)
摘要
Deformable Parts Models and Convolutional Networks each have achieved notable performance in object detection. Yet these two approaches find their strengths in complementary areas: DPMs are well-versed in object composition, modeling fine-grained spatial relationships between parts; likewise, ConvNets are adept at producing powerful image features, having been discriminatively trained directly on the pixels. In this paper, we propose a new model that combines these two approaches, obtaining the advantages of each. We train this model using a new structured loss function that considers all bounding boxes within an image, rather than isolated object instances. This enables the non-maximal suppression (NMS) operation, previously treated as a separate post-processing stage, to be integrated into the model. This allows for discriminative training of our combined Convnet + DPM + NMS model in end-to-end fashion. We evaluate our system on PASCAL VOC 2007 and 2011 datasets, achieving competitive results on both benchmarks.
更多查看译文
关键词
feature extraction,learning (artificial intelligence),neural nets,object detection,Convnet-DPM-NMS model,PASCAL VOC dataset,bounding box,convolutional network,deformable parts model,nonmaximum suppression,object composition,structured loss function
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络