LatentGNN: Learning Efficient Non-local Relations for Visual Recognition

By Songyang Zhang, Shipeng Yan, Xuming He. 2019

87 citations recorded by the source corpus.

Capturing long-range dependencies in feature representations is crucial for many visual recognition tasks. Despite recent successes of deep convolutional networks, it remains challenging to model non-local context relations between visual features. A promising strategy is to model the feature context by a fully-connected graph neural network (GNN), which augments traditional convolutional features with an estimated non-local context representation. However, most GNN-based approaches require computing a dense graph affinity matrix and hence have difficulty in scaling up to tackle complex real-world visual problems. In this work, we propose an efficient and yet flexible non-local relation representation based on a novel class of graph neural networks. Our key idea is to introduce a latent space to reduce the complexity of graph, which allows us to use a low-rank representation for the graph affinity matrix and to achieve a linear complexity in computation. Extensive experimental evaluations on three major visual recognition tasks show that our method outperforms the prior works with a large margin while maintaining a low computation cost.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Graph Learning

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

1. Kurt Keutzer
2. Péter Vajda
3. Bichen Wu
4. Xiaoliang Dai
5. Masayoshi Tomizuka
6. Chenfeng Xu
7. Peizhao Zhang
8. Peng-Tao Jiang

In Computer Vision and Pattern Recognition

1. Ming-Ming Cheng
2. Kurt Keutzer
3. Luc Van Gool
4. Hongsheng Li
5. Bichen Wu
6. Ming-Hsuan Yang
7. Xiaogang Wang
8. Ling Shao

In Graph Learning

1. Shuai Yi
2. Ming-Ming Cheng
3. Haiyu Zhao

Citations in the corpus

• Visual Transformers: Token-based Image Representation and Processing for Computer Vision (2020, methodology): “Graph convolutions in vision models: Our work is also related to previous efforts such as GloRe [6], LatentGNN [47], and [26] that densely relate concepts in latent space using graph convolutions.”
• Efficient Attention: Attention with Linear Complexities (2018, methodology): “The team obtained these metrics by measuring the official open-source implementations of [29, 27].”
• Attention mechanisms in computer vision: A survey (2021, result): “[8], [9], [15], [21], [31], [32], [34], [35] , [22], [26], [62], [63], [64], [65], [66], [67] , [41], [68], [69], [70], [71], [72], [73], [74] , [8], [34], [42], [43], [75], [76], [77], [78] , [27], [44], [45], [46], [79], [80], [81], [82] , [61], [83], [84], [85], [86], [87], [88], [89] , [47], [90”