AOGNets: Compositional Grammatical Architectures for Deep Learning
By Xilai Li, Xi Song, Tianfu Wu. 2017
26 citations recorded by the source corpus.
Neural architectures are the foundation for improving performance of deep neural networks (DNNs). This paper presents deep compositional grammatical architectures which harness the best of two worlds: grammar models and DNNs. The proposed architectures integrate compositionality and reconfigurability of the former and the capability of learning rich features of the latter in a principled way. We utilize AND-OR Grammar (AOG) as network generator in this paper and call the resulting networks AOGNets. An AOGNet consists of a number of stages each of which is composed of a number of AOG building blocks. An AOG building block splits its input feature map into N groups along feature channels and then treat it as a sentence of N words. It then jointly realizes a phrase structure grammar and a dependency grammar in bottom-up parsing the “sentence” for better feature exploration and reuse. It provides a unified framework for the best practices developed in state-of-the-art DNNs. In experiments, AOGNet is tested in the ImageNet-1K classification benchmark and the MS-COCO object detection and segmentation benchmark. In ImageNet-1K, AOGNet obtains better performance than ResNet and most of its variants, ResNeXt and its attention based variants such as SENet, DenseNet and DualPathNet. AOGNet also obtains the best model interpretability score using network dissection. AOGNet further shows better potential in adversarial defense. In MS-COCO, AOGNet obtains better performance than the ResNet and ResNeXt backbones in Mask R-CNN.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Alan L. Yuille
- Qing Liu
- Adam Kortylewski
- Marcel A. J. van Gerven
- Gabrielle Ras
- Willem F. G. Haselager
- Biswajeet Pradhan
- Manoranjan Paul
In Computer Vision and Pattern Recognition
- Qing Liu
- Adam Kortylewski
- Marcel A. J. van Gerven
- Alan L. Yuille
- Ju He
- Yihong Sun
- Angtian Wang
- Gabrielle Ras
Citations in the corpus
- Explanation Methods in Deep Learning: Users, Values, Concerns and Challenges (2018, background): “Li et al. (2017) introduce an explicit structure to DNNs for visual recognition by building in an AND-OR grammar directly in the network structure.”
- Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition Under Occlusion (2020, background): “A number of works (Li et al. 2019; Tang et al. 2018, 2017) use differentiable graphical models to integrate partwhole compositions intoDCNNs.”
- Compositional Convolutional Neural Networks: A Deep Architecture With Innate Robustness to Partial Occlusion (2020, background): “A number of works [18, 25, 26] use differentiable graphical models to integrate part-whole compositions into DCNNs.”
- COVID-19 Detection Through Transfer Learning Using Multimodal Imaging Data (2020, methodology): “Another path of development combining multiple base models has resulted in a number of hybrid models including AOGNet [87], PNASNet [88], AmoebaNet [89], DPN [90], HCGNet [76], GCNet [91], ThiNet [92], and SKNet [93] etc.”