In some image classification tasks, similarities among different categories are different and the samples are usually misclassified as highly similar categories. To distinguish highly similar categories, more specific...In some image classification tasks, similarities among different categories are different and the samples are usually misclassified as highly similar categories. To distinguish highly similar categories, more specific features are required so that the classifier can improve the classification performance. In this paper, we propose a novel two-level hierarchical feature learning framework based on the deep convolutional neural network(CNN), which is simple and effective. First, the deep feature extractors of different levels are trained using the transfer learning method that fine-tunes the pre-trained deep CNN model toward the new target dataset. Second, the general feature extracted from all the categories and the specific feature extracted from highly similar categories are fused into a feature vector. Then the final feature representation is fed into a linear classifier. Finally, experiments using the Caltech-256, Oxford Flower-102, and Tasmania Coral Point Count(CPC) datasets demonstrate that the expression ability of the deep features resulting from two-level hierarchical feature learning is powerful. Our proposed method effectively increases the classification accuracy in comparison with flat multiple classification methods.展开更多
Semantic image segmentation is a task to predict a category label for every image pixel. The key challenge of it is to design a strong feature representation. In this paper, we fuse the hierarchical convolutional neur...Semantic image segmentation is a task to predict a category label for every image pixel. The key challenge of it is to design a strong feature representation. In this paper, we fuse the hierarchical convolutional neural network(CNN) features and the region-based features as the feature representation. The hierarchical features contain more global information, while the region-based features contain more local information. The combination of these two kinds of features significantly enhances the feature representation. Then the fused features are used to train a softmax classifier to produce per-pixel label assignment probability. And a fully connected conditional random field(CRF) is used as a post-processing method to improve the labeling consistency. We conduct experiments on SIFT flow dataset. The pixel accuracy and class accuracy are 84.4% and 34.86%, respectively.展开更多
We propose a novel prioritized intra refresh method for the wireless video communication.The proposed method considers the characteristics of the human visual system,the error-sensitivity of the bitstream,and the stat...We propose a novel prioritized intra refresh method for the wireless video communication.The proposed method considers the characteristics of the human visual system,the error-sensitivity of the bitstream,and the state of the time-varying wireless channel jointly.An expected perceptual distortion model was used to adjust the intra refresh rate adaptively.This model consists of the perceptual weight map based on an attention model,the bit error probability map based on bitstream size,and the dynamic channel state information(CSI).Experimental results indicate that,compared with other intra refresh methods that consider only the content of the video or the CSI,the proposed method improves the average peak signal-to-noise ratio(PSNR) of the whole frame by about 0.5 dB,and improves the average PSNR of the attention-area by about 0.8 dB.展开更多
基金Project supported by the National Natural Science Foundation of China(No.61379074)the Zhejiang Provincial Natural Science Foundation of China(Nos.LZ12F02003 and LY15F020035)
文摘In some image classification tasks, similarities among different categories are different and the samples are usually misclassified as highly similar categories. To distinguish highly similar categories, more specific features are required so that the classifier can improve the classification performance. In this paper, we propose a novel two-level hierarchical feature learning framework based on the deep convolutional neural network(CNN), which is simple and effective. First, the deep feature extractors of different levels are trained using the transfer learning method that fine-tunes the pre-trained deep CNN model toward the new target dataset. Second, the general feature extracted from all the categories and the specific feature extracted from highly similar categories are fused into a feature vector. Then the final feature representation is fed into a linear classifier. Finally, experiments using the Caltech-256, Oxford Flower-102, and Tasmania Coral Point Count(CPC) datasets demonstrate that the expression ability of the deep features resulting from two-level hierarchical feature learning is powerful. Our proposed method effectively increases the classification accuracy in comparison with flat multiple classification methods.
基金supported by the National Natural Science Foundation of China(Nos.U1509207,61325019,61472278,61403281 and 61572357)the Key Project of Natural Science Foundation of Tianjin(No.14JCZDJC31700)
文摘Semantic image segmentation is a task to predict a category label for every image pixel. The key challenge of it is to design a strong feature representation. In this paper, we fuse the hierarchical convolutional neural network(CNN) features and the region-based features as the feature representation. The hierarchical features contain more global information, while the region-based features contain more local information. The combination of these two kinds of features significantly enhances the feature representation. Then the fused features are used to train a softmax classifier to produce per-pixel label assignment probability. And a fully connected conditional random field(CRF) is used as a post-processing method to improve the labeling consistency. We conduct experiments on SIFT flow dataset. The pixel accuracy and class accuracy are 84.4% and 34.86%, respectively.
文摘We propose a novel prioritized intra refresh method for the wireless video communication.The proposed method considers the characteristics of the human visual system,the error-sensitivity of the bitstream,and the state of the time-varying wireless channel jointly.An expected perceptual distortion model was used to adjust the intra refresh rate adaptively.This model consists of the perceptual weight map based on an attention model,the bit error probability map based on bitstream size,and the dynamic channel state information(CSI).Experimental results indicate that,compared with other intra refresh methods that consider only the content of the video or the CSI,the proposed method improves the average peak signal-to-noise ratio(PSNR) of the whole frame by about 0.5 dB,and improves the average PSNR of the attention-area by about 0.8 dB.
