IEEE Access · 2020 · 26 citations · 16 references
ComputingComputer ScienceComputer VisionMachine LearningMachine VisionDeep LearningImage ClassificationObject DetectionObject RecognitionPattern RecognitionRepresentation LearningContainersConvolutional Neural NetworksDeep Learning On GpusDeep Learning-based ClassificationObjects
The paper focuses on the identification of different objects in a pair of images taken from the same environment, which is challenging and has wide application. We propose a single deep convolutional neural network termed as DiffNet to solve this problem. DiffNet takes a pair of images as the input and directly regresses the bounding boxes of different objects. To train DiffNet, we only need to label the different objects, rather than all objects in input images, which significantly reduces human labeling efforts. Experiments are performed on an image dataset collected from unmanned containers. DiffNet obtains a very high product detection accuracy of 95.56% mAP at the speed of 143 fps measured on an NVIDIA TITAN Xp GPU.
16
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Image quality assessment: from error visibility to structural similarity
Zhou Wang, Alan C. Bovik, Hamid R. Sheikh et al. · IEEE Transactions on Image Processing · 2004 · 56K citations
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Ross Girshick, Jeff Donahue, Trevor Darrell et al. · 2014 · 31.8K citations
Kaiming He, Georgia Gkioxari, Piotr Dollár et al. · 2017 · 28.8K citations