# Global Second-order Pooling Convolutional Networks

arXiv: https://arxiv.org/abs/1811.12006 · HTML: https://mlsanity.com/paper/1811.12006/

## Key facts

- Cited by 66 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Nov 2018.

## Built on by (most cited first, 30 of 66)

- [Coordinate Attention for Efficient Mobile Network Design](https://mlsanity.com/paper/2103.02907/) (2021)
- [Attention Mechanisms in Computer Vision: A Survey](https://mlsanity.com/paper/2111.07624/) (2021)
- [Attention Spiking Neural Networks](https://mlsanity.com/paper/2209.13929/) (2022)
- [3Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognition](https://mlsanity.com/paper/2303.14474/) (2023)
- [Focus U-Net: A novel dual attention-gated CNN for polyp segmentation during colonoscopy](https://mlsanity.com/paper/2105.07467/) (2021)
- [PIDray: A Large-scale X-ray Benchmark for Real-World Prohibited Item Detection](https://mlsanity.com/paper/2211.10763/) (2022)
- [Surpassing the Human Accuracy: Detecting Gallbladder Cancer from USG Images with Curriculum Learning](https://mlsanity.com/paper/2204.11433/) (2022)
- [EPSANet: An Efficient Pyramid Squeeze Attention Block on Convolutional Neural Network](https://mlsanity.com/paper/2105.14447/) (2021)
- [MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation](https://mlsanity.com/paper/2103.13044/) (2021)
- [All the attention you need: Global-local, spatial-channel attention for image retrieval](https://mlsanity.com/paper/2107.08000/) (2021)
- [Temporal-attentive Covariance Pooling Networks for Video Recognition](https://mlsanity.com/paper/2110.14381/) (2021)
- [EEG motor imagery decoding: A framework for comparative analysis with channel attention mechanisms](https://mlsanity.com/paper/2310.11198/) (2023)
- [BA-Net: Bridge Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/2112.04150/) (2021)
- [NAM: Normalization-based Attention Module](https://mlsanity.com/paper/2111.12419/) (2021)
- [ELA: Efficient Local Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/2403.01123/) (2024)
- [DSNet: A Dual-Stream Framework for Weakly-Supervised Gigapixel Pathology Image Analysis](https://mlsanity.com/paper/2109.05788/) (2021)
- [How well does CLIP understand texture?](https://mlsanity.com/paper/2203.11449/) (2022)
- [YOLOv8-AM: YOLOv8 Based on Effective Attention Mechanisms for Pediatric Wrist Fracture Detection](https://mlsanity.com/paper/2402.09329/) (2024)
- [Transformers Meet Visual Learning Understanding: A Comprehensive Review](https://mlsanity.com/paper/2203.12944/) (2022)
- [Booster-SHOT: Boosting Stacked Homography Transformations for Multiview Pedestrian Detection with Attention](https://mlsanity.com/paper/2208.09211/) (2022)
- [DPNet: Dual-Path Network for Real-time Object Detection with Lightweight Attention](https://mlsanity.com/paper/2209.13933/) (2022)
- [A General Framework for Robust G-Invariance in G-Equivariant Networks](https://mlsanity.com/paper/2310.18564/) (2023)
- [YOLOv8-ResCBAM: YOLOv8 Based on An Effective Attention Module for Pediatric Wrist Fracture Detection](https://mlsanity.com/paper/2409.18826/) (2024)
- [TDAM: Top-Down Attention Module for Contextually Guided Feature Selection in CNNs](https://mlsanity.com/paper/2111.13470/) (2021)
- [Switchable Self-attention Module](https://mlsanity.com/paper/2209.05680/) (2022)
- [Meta-learning of Pooling Layers for Character Recognition](https://mlsanity.com/paper/2103.09528/) (2021)
- [On Evolving Attention Towards Domain Adaptation](https://mlsanity.com/paper/2103.13561/) (2021)
- [Ultra-high Resolution Image Segmentation via Locality-aware Context Fusion and Alternating Local Enhancement](https://mlsanity.com/paper/2109.02580/) (2021)
- [Knowledge-enriched Attention Network with Group-wise Semantic for Visual Storytelling](https://mlsanity.com/paper/2203.05346/) (2022)
- [SiamTHN: Siamese Target Highlight Network for Visual Tracking](https://mlsanity.com/paper/2303.12304/) (2023)

## Abstract (arXiv)

Deep Convolutional Networks (ConvNets) are fundamental to, besides large-scale visual recognition, a lot of vision tasks. As the primary goal of the ConvNets is to characterize complex boundaries of thousands of classes in a high-dimensional space, it is critical to learn higher-order representations for enhancing non-linear modeling capability. Recently, Global Second-order Pooling (GSoP), plugged at the end of networks, has attracted increasing attentions, achieving much better performance than classical, first-order networks in a variety of vision tasks. However, how to effectively introduce higher-order representation in earlier layers for improving non-linear capability of ConvNets is still an open problem. In this paper, we propose a novel network model introducing GSoP across from lower to higher layers for exploiting holistic image information throughout a network. Given an input 3D tensor outputted by some previous convolutional layer, we perform GSoP to obtain a covariance matrix which, after nonlinear transformation, is used for tensor scaling along channel dimension. Similarly, we can perform GSoP along spatial dimension for tensor scaling as well. In this way, we can make full use of the second-order statistics of the holistic image throughout a network. The proposed networks are thoroughly evaluated on large-scale ImageNet-1K, and experiments have shown that they outperformed non-trivially the counterparts while achieving state-of-the-art results.