Rethinking Learnable Tree Filter for Generic Feature Transform
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.
Code (1)
Tasks
Instance Segmentationobject-detectionObject DetectionSegmentationSemantic SegmentationSimilar Papers 제목 키워드 기반
Learnable Tree Filter for Structure-preserving Feature Transform
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 SegmentationLarge-Scale Learnable Graph Convolutional Networks
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 ClassificationCombining Progressive Rethinking and Collaborative Learning: A Deep Framework for In-Loop Filtering
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
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 ExtractionLearning Local Receptive Fields and their Weight Sharing Scheme on Graphs
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…