Boundary-Aware Feature Propagation for Scene Segmentation

@article{Ding2019BoundaryAwareFP,
  title={Boundary-Aware Feature Propagation for Scene Segmentation},
  author={Henghui Ding and Xudong Jiang and Ai Qun Liu and Nadia Magnenat-Thalmann and G. Wang},
  journal={2019 IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2019},
  pages={6818-6828}
}
In this work, we address the challenging issue of scene segmentation. [...] Key Method Then, we propose unidirectional acyclic graphs (UAGs) to model the function of undirected cyclic graphs (UCGs), which structurize the image via building graphic pixel-by-pixel connections, in an efficient and effective way. Furthermore, we propose a boundary-aware feature propagation (BFP) module to harvest and propagate the local features within their regions isolated by the learned boundaries in the UAG-structured image…Expand
Semantic Segmentation With Context Encoding and Multi-Path Decoding
TLDR
This paper proposes a segmentation network called CGBNet to enhance the segmentation performance by context encoding and multi-path decoding, and proposes a scale-selection scheme to selectively fuse the segmentsation results from different-scales of features at every spatial position. Expand
Global Aggregation Then Local Distribution for Scene Parsing
  • Xiangtai Li, Li Zhang, +4 authors T. Xiang
  • Computer Science, Medicine
  • IEEE Transactions on Image Processing
  • 2021
TLDR
A novel local distribution module is designed which models the affinity map between global and local relationship for each pixel adaptively and can be modularized as an end-to-end trainable block and easily plugged into existing semantic segmentation networks, giving rise to the GALD networks. Expand
RANet: Region Attention Network for Semantic Segmentation
TLDR
This paper introduces the Region Attention Network (RANet), a novel attention network for modeling the relationship between object regions, and extensively evaluates the method on the challenging segmentation benchmarks, demonstrating that RANet effectively helps to achieve the state-of-the-art results. Expand
Joint Semantic Segmentation and Boundary Detection Using Iterative Pyramid Contexts
TLDR
This paper presents a joint multi-task learning framework for semantic segmentation and boundary detection, which couples two tasks and stores the shared latent semantics to interact between the two tasks, and proposes the novel spatial gradient fusion to suppress non-semantic edges. Expand
Contour-Aware Loss: Boundary-Aware Learning for Salient Object Segmentation
TLDR
A novel loss function, i.e., Contour Loss, is come up with, which leverages object contours to guide models to perceive salient object boundaries and which forces the model hierarchically to attend to global contexts, thus captures the global visual saliency. Expand
Boundary Guided Context Aggregation for Semantic Segmentation
  • Haoxiang Ma, Hongyu Yang, Di Huang
  • Computer Science
  • ArXiv
  • 2021
TLDR
This work exploits boundary as a significant guidance for context aggregation to promote the overall semantic understanding of an image and proposes a Boundary guided Context Aggregation Network (BCANet), where a Multi-Scale Boundary extractor borrowing the backbone features at multiple scales is specifically designed for accurate boundary detection. Expand
Scene Segmentation With Dual Relation-Aware Attention Network
TLDR
A Dual Relation-aware Attention Network (DRANet) is proposed to handle the task of scene segmentation and designs two types of compact attention modules, which model the contextual dependencies in spatial and channel dimensions, respectively. Expand
Object-Contextual Representations for Semantic Segmentation
TLDR
This paper addresses the semantic segmentation problem with a focus on the context aggregation strategy, and presents a simple yet effective approach, object-contextual representations, characterizing a pixel by exploiting the representation of the corresponding object class. Expand
Improving Semantic Segmentation via Decoupled Body and Edge Supervision
TLDR
This paper proposes a new paradigm for semantic segmentation that establishes new state of the art while retaining high efficiency in inference and shows that the proposed framework with various baselines or backbone networks leads to better object inner consistency and object boundaries. Expand
Cars Can’t Fly Up in the Sky: Improving Urban-Scene Segmentation via Height-Driven Attention Networks
  • Sungha Choi, J. Kim, J. Choo
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
TLDR
This paper exploits the intrinsic features of urban-scene images and proposes a general add-on module, called height-driven attention networks (HANet), for improving semantic segmentation for urban- scene images, and achieves a new state-of-the-art performance on the Cityscapes benchmark with a large margin among ResNet101 based segmentation models. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 91 REFERENCES
Dual Attention Network for Scene Segmentation
TLDR
New state-of-the-art segmentation performance on three challenging scene segmentation datasets, i.e., Cityscapes, PASCAL Context and COCO Stuff dataset is achieved without using coarse data. Expand
Context Contrasted Feature and Gated Multi-scale Aggregation for Scene Segmentation
TLDR
A novel context contrasted local feature that not only leverages the informative context but also spotlights the local information in contrast to the context is proposed that greatly improves the parsing performance. Expand
Semantic Correlation Promoted Shape-Variant Context for Segmentation
TLDR
This work proposes a novel paired convolution to infer the semantic correlation of the pair and based on that to generate a shape mask, of which the receptive field is controlled by the shape mask that varies with the appearance of input. Expand
Multi-scale Context Intertwining for Semantic Segmentation
TLDR
This work proposes a novel scheme for aggregating features from different scales, which it refers to as Multi-Scale Context Intertwining (MSCI), which merge pairs of feature maps in a bidirectional and recurrent fashion, via connections between two LSTM chains. Expand
Decomposing a scene into geometric and semantically consistent regions
TLDR
A region-based model which combines appearance and scene geometry to automatically decompose a scene into semantically meaningful regions and which achieves state-of-the-art performance on the tasks of both multi-class image segmentation and geometric reasoning. Expand
Efficiently selecting regions for scene understanding
  • M. Kumar, D. Koller
  • Computer Science
  • 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
TLDR
This work designs an efficient approach for obtaining the best set of regions in terms of the energy function itself and demonstrates the usefulness of the algorithm on the task of scene segmentation and shows significant improvements over state of the art methods. Expand
Boundary-Aware Instance Segmentation
TLDR
This paper introduces a novel object segment representation based on the distance transform of the object masks, and designs an object mask network (OMN) with a new residual-deconvolution architecture that infers such a representation and decodes it into the final binary object mask. Expand
Adaptive Context Network for Scene Parsing
TLDR
This paper proposes an Adaptive Context Network (ACNet) to capture the pixel-aware contexts by a competitive fusion of global context and local context according to different per-pixel demands. Expand
Adaptive Pyramid Context Network for Semantic Segmentation
TLDR
This paper introduces three desirable properties of context features in segmentation task and finds that Global-guided Local Affinity (GLA) can play a vital role in constructing effective context features, while this property has been largely ignored in previous works. Expand
The Role of Context for Object Detection and Semantic Segmentation in the Wild
TLDR
A novel deformable part-based model is proposed, which exploits both local context around each candidate detection as well as global context at the level of the scene, which significantly helps in detecting objects at all scales. Expand
...
1
2
3
4
5
...