paper-with-me

홈 › Papers

Rethinking Learnable Tree Filter for Generic Feature Transform

2020-12-07 · NeurIPS 2020 12 · Lin Song, Yanwei Li, Zhengkai Jiang, Zeming Li, Xiangyu Zhang, Hongbin Sun, Jian Sun, Nanning Zheng

The Learnable Tree Filter presents a remarkable approach to model structure-preserving relations for semantic segmentation. Nevertheless, the intrinsic geometric constraint forces it to focus on the regions with close spatial distance, hindering the effective long-range interactions. To relax the geometric constraint, we give the analysis by reformulating it as a Markov Random Field and introduce a learnable unary term. Besides, we propose a learnable spanning tree algorithm to replace the original non-differentiable one, which further improves the flexibility and robustness. With the above improvements, our method can better capture long-range dependencies and preserve structural details with linear complexity, which is extended to several vision tasks for more generic feature transform. Extensive experiments on object detection/instance segmentation demonstrate the consistent improvements over the original version. For semantic segmentation, we achieve leading performance (82.1% mIoU) on the Cityscapes benchmark without bells-and-whistles. Code is available at https://github.com/StevenGrove/LearnableTreeFilterV2.

📄 PDF Abstract BibTeX arXiv:2012.03482

Code (1)

StevenGrove/LearnableTreeFilterV2 공식 구현 pytorch

Tasks

Instance Segmentationobject-detectionObject DetectionSegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

Learnable Tree Filter for Structure-preserving Feature Transform

2019-09-27 · NeurIPS 2019 12 · Lin Song, Yanwei Li, Zeming Li, Gang Yu 외

Learning discriminative global features plays a vital role in semantic segmentation. And most of the existing methods adopt stacks of local convolutions or non-local blocks to capture long-range context. However, due to …

Semantic Segmentation

Large-Scale Learnable Graph Convolutional Networks

2018-08-12 · Hongyang Gao, Zhengyang Wang, Shuiwang Ji

Convolutional neural networks (CNNs) have achieved great success on grid-like data such as images, but face tremendous challenges in learning from more generic data such as graphs. In CNNs, the trainable local filters en…

Document ClassificationInductive LearningNode Classification

Combining Progressive Rethinking and Collaborative Learning: A Deep Framework for In-Loop Filtering

2020-01-16 · Dezhao Wang, Sifeng Xia, Wenhan Yang, Jiaying Liu

In this paper, we aim to address issues of (1) joint spatial-temporal modeling and (2) side information injection for deep-learning based in-loop filter. For (1), we design a deep network with both progressive rethinking…

Learning to Prune Dependency Trees with Rethinking for Neural Relation Extraction

2020-12-01 · COLING 2020 8 · Bowen Yu, Xue Mengge, Zhenyu Zhang, Tingwen Liu 외

Dependency trees have been shown to be effective in capturing long-range relations between target entities. Nevertheless, how to selectively emphasize target-relevant information and remove irrelevant content from the tr…

RelationRelation Extraction

Learning Local Receptive Fields and their Weight Sharing Scheme on Graphs

2017-06-08 · Jean-Charles Vialatte, Vincent Gripon, Gilles Coppin

We propose a simple and generic layer formulation that extends the properties of convolutional layers to any domain that can be described by a graph. Namely, we use the support of its adjacency matrix to design learnable…