2018 · 51 citations · 17 references
ComputingComputer ScienceComputer VisionFeature EngineeringMachine VisionDeep LearningFeature DescriptionFeature DetectionFeature-level FusionObject DetectionObject RecognitionConvolutional Neural NetworksDeep Feature ExtractionDeep Feature FusionFeature IntegrationHierarchical Feature FusionMulti-scale Feature DetectionMulti-scale Feature ExtractionMulti-scale Feature Representation
In natural images, the scales (thickness) of object skeletons may dramatically vary among objects and object parts. Thus, robust skeleton detection requires powerful multi-scale feature integration ability. To address this issue, we present a new convolutional neural network (CNN) architecture by introducing a novel hierarchical feature integration mechanism, named Hi-Fi, to address the object skeleton detection problem. The proposed CNN-based approach intrinsically captures high-level semantics from deeper layers, as well as low-level details from shallower layers. By hierarchically integrating different CNN feature levels with bidirectional guidance, our approach (1) enables mutual refinement across features of different levels, and (2) possesses the strong ability to capture both rich object context and high-resolution details. Experimental results show that our method significantly outperforms the state-of-the-art methods in terms of effectively fusing features from very different scales, as evidenced by a considerable performance improvement on several benchmarks.
17
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Caffe: Convolutional Architecture for Fast Feature Embedding
Yangqing Jia, Evan Shelhamer, Jeff Donahue et al. · arXiv (Cornell University) · 2014 · 4.3K citations · Full text
Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detection
Pingping Zhang, Dong Wang, Huchuan Lu et al. · 2017 · 861 citations
Richer Convolutional Features for Edge Detection
Yun Liu, Ming‐Ming Cheng, Xiaowei Hu et al. · 2017 · 768 citations