Very Deep Convolutional Networks for Large-Scale Image Recognition
Citations
611 citations
Cites background or methods from "Very Deep Convolutional Networks fo..."
...But instead of training a CNN, we use a pretrained 16-layer CNN model [46] to extract features from patches....
[...]
...EM-Finetune-CNN-Vote/SMI: Similar to EM-CNNVote/SMI except that instead of training a CNN from scratch, we fine-tune a pretrained 16-layer CNN model [46] by training it on discriminative patches....
[...]
...EM-Finetune-CNN-LR/SVM: Similar to EM-CNNLR/SVM except that instead of training a CNN from scratch, we fine-tune a pretrained 16-layer CNN model [46] by training it on discriminative patches....
[...]
...However, it has been shown that in many applications, learning decision fusion models can significantly improve performance compared to voting [42, 45, 24, 47, 26, 46]....
[...]
...Pretrained CNN-ImageFea-SVM: We apply a pretrained 16-layer network [46] to rail surface images to extract features, and train an SVM on these features....
[...]
610 citations
608 citations
Cites methods from "Very Deep Convolutional Networks fo..."
...The pose network is initialized with VGG [15] and fine-tuned for pose estimation using ground truth annotations from Pascal 3D+....
[...]
608 citations
Cites background or methods from "Very Deep Convolutional Networks fo..."
...loss is used to optimize the model. Li et al. [130] consider joint semantic segmentation and salient object detection. Similar to the FCN work [142], the two original fully connected layers in VGGNet [180] are replaced by convolutional layers.To overcome the fuzzy object boundaries caused by the down-sampling operations of CNNs, they make use of the SLIC [8] superpixels to model the topological relatio...
[...]
...exNet 7 10 DISC [39] TNNLS 2016 9,000 MSRA10K - 7 11 LCNN [120] Neuro 2017 2,900 MSRA-B + PASCALS AlexNet 7 12 DHSNET [137] CVPR 2016 6,000 MSRA10K VGGNet 3 13 DCL [119] CVPR 2016 2,500 MSRA-B VGGNet [180] 3 14 RACDNN [110] CVPR 2016 10,565 DUT+NJU2000+RGBD VGG 3 15 SU [109] CVPR 2016 10,000 MSRA10K VGGNet 3 16 CRPSD [187] ECCV 2016 10,000 MSRA10K VGGNet 3 17 DSRCNN [188] MM 2016 10,000 MSRA10K VGGNet ...
[...]
...ures separately. They first extract a number of features for each superpixel and feed them into a subnetwork composed of a stack of convolutional layers with 1 1 kernel size. Then, the standard VGGNet [180] is used to capture high-level features. Both low- and high12 Salient Object Detection: A Survey 13 # Model Pub Year #Training Images Training Set Pre-trained Model Fully Conv 1 SuperCNN [71] IJCV 201...
[...]
...te high-level features to lower layers allowing effective fusion of multi-level features. Another choice is exploiting stronger baseline models, such as using very deep ResNets [70] instead of VGGNet [180]. 5.2 Dataset Bias Datasets have been consequential in the rapid progress in saliency detection. On the one hand, they supply large scale training data and enable comparing performance of competing al...
[...]
607 citations
References
49,639 citations
21,729 citations
9,803 citations
9,775 citations
6,061 citations