Multi-scale Context Intertwining for Semantic Segmentation

By Di Lin, Yuanfeng Ji, Dani Lischinski, Daniel Cohen-Or, Hui Huang. 2018

171 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

1. Jiashi Feng
2. Liang-Chieh Chen
3. Alan L. Yuille
4. Quoc V. Le
5. Hartwig Adam
6. Qibin Hou
7. Yukun Zhu
8. Luc Van Gool

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Ming-Hsuan Yang
3. Dacheng Tao
4. Jiashi Feng
5. Xiaogang Wang
6. Alan L. Yuille
7. Yi Yang
8. Yu Qiao

Citations in the corpus

• Representation Compensation Networks for Continual Semantic Segmentation (2022, methodology): “Currently methods pay more attention to multi-scale feature aggregation [3, 34, 52,53,59,65,68,81].”
• Searching for Efficient Multi-Scale Architectures for Dense Image Prediction (2018, positive): “The DPC architecture outperforms previous state-of-the-art models [95, 93] by more than 1.7%, and is comparable to concurrent works [14, 96, 48].”
• Strip Pooling: Rethinking Spatial Pooling for Scene Parsing (2020, methodology): “For continuous feature space learning, prior work use multi-scale feature aggregation [37, 5, 33, 18, 42, 31, 32, 2, 44, 4, 48, 17] to fuse the contextual information by probing the incoming features with filters or pooling operations at multiple rates and multiple fields-of-view.”
• Image Segmentation Using Deep Learning: A Survey (2020, methodology): “Other models use multiscale analysis for segmentation, among them Dynamic Multiscale Filters Network (DMNet) [56], Context Contrasted Network and gated multiscale aggregation (CCN) [57], Adaptive Pyramid Context Network (APC-Net) [58], MultiScale Context Intertwining (MSCI) [59], and salient object ”
• Visual Attention Methods in Deep Learning: An In-Depth Survey (2022, methodology): “Criss-Cross Attention : The contextual information is still very important for scene understanding [107, 191].”
• Squeeze-and-Attention Networks for Semantic Segmentation (2019, methodology): “Since machine translation and image translation share many similarities, RNN and LSTM have been used for semantic segmentation by connecting semantic labeling to translation [43, 21].”
• Adaptive Pyramid Context Network for Semantic Segmentation (2019, methodology): “Without pre-trained on MS COCO dataset [16], APCNet achieves state-of-the-art performance of 84.”
• Expectation-Maximization Attention Networks for Semantic Segmentation (2019, unknown): “PSPNet [37] ResNet-101 47.8 DANet [11] ResNet-50 50.1 MSCI [20] ResNet-152 50.3”
• Scene Segmentation With Dual Relation-Aware Attention Network (2020, background): “MSCI [23] merges features from adjacent layers via LSTM chains to obtain powerful features.”
• Adaptive Context Network for Scene Parsing (2019, methodology): “Among the approaches, the recent methods[21, 28] use more powerful network(e.g. ResNet-152 and Xception-71) as encoder network and fuse high-and low-level feature in decoder network, our method outperforms them by a relatively large margin.”
• Patch-Based Progressive 3D Point Set Upsampling (2018, methodology): “In neural image processing, skip-connection is a powerful tool to leverage features extracted across different layers of the network [16,20,21,35].”
• Dynamic Multi-Scale Filters for Semantic Segmentation (2019, methodology): “deeper backbone model [26, 25] or utilize additional MS COCO dataset to pre-train their model [5].”
• GFF: Gated Fully Fusion for Semantic Segmentation (2019, background): “In (Lin et al. 2018) and (Ding et al. 2018), they proposed to locally fuse every two adjacent feature maps in the feature pyramid into one feature map until only one feature map is left.”