OCNet: Object Context for Semantic Segmentation

By Yuhui Yuan, Lang Huang, Jianyuan Guo, Chao Zhang, Xilin Chen, Jingdong Wang. 2021

255 citations recorded by the source corpus.

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Masked-attention Mask Transformer for Universal Image Segmentation (2021, methodology): “Follow-up methods find context to play an important role for precise per-pixel classification and focus on designing customized context modules [7,8,63] or self-attention variants [21,26,45,55,61,64].”
Per-Pixel Classification is Not All You Need for Semantic Segmentation (2021, methodology): “Modern semantic segmentation models focus on aggregating long-range context in the final feature map: ASPP [7, 8] uses atrous convolutions with different atrous rates; PPM [52] uses pooling operators with different kernel sizes; DANet [19], OCNet [51], and CCNet [23] use different variants of non-lo”
HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation (2022, unknown): “This concept was further improved in different aspects including increasing the receptive field while preserving spatial details [2, 3, 6, 48, 65, 74, 83], integrating context information [30,75,76,78,91], attention mechanisms [18,32,69,84], refining boundaries [15,36,77], and Transformer-based arch”
LMSeg: Language-guided Multi-dataset Segmentation (2023, methodology): “These methods include atrous convolutions with different atrous rates (Chen et al., 2018; 2017), pooling operations with varying kernel sizes (Zhao et al., 2017), and variants of non-local blocks (Fu et al., 2019; Yuan et al., 2021; Huang et al., 2019; Wang et al., 2018).”
CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation With Transformers (2022, methodology): “Inspired by the non-local block [40], self-attention in transformers [25] has been used to establish long-range dependencies by DANet [26] and OCNet [41].”
P2T: Pyramid Pooling Transformer for Scene Understanding (2021, methodology): “After that, pyramid pooling has been widely applied to various vision tasks such as semantic segmentation [37], [54], [55], [56], [57] and object detection [36], [58], [59], [60].”
DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation (2021, background): “However, there are further interesting architectures that could be explored in the future such as [10, 26].”
A Survey on Vision Transformer (2020, methodology): “PSANet [281], OCNet [262], DANet [69] and CFNet [273] are the pioneering works to propose using the self-attention module in semantic segmentation tasks.”
Deep Dual-Resolution Networks for Real-Time and Accurate Semantic Segmentation of Traffic Scenes (2023, methodology): “There have been many methods to model long-range contextual information such as Atrous Spatial Pyramid Pooling (ASPP) [8], Pyramid Pooling Module (PPM) [10], and kinds of self-attention variants [44], [45], [46].”
Beyond Self-Attention: External Attention Using Two Linear Layers for Visual Tasks (2021, background): “Self-attention is a special case of attention, andmanypapers [3], [4], [11], [17], [22], have considered the self-attention mechanism for vision.”