Active Boundary Loss for Semantic Segmentation

@inproceedings{Wang2021ActiveBL,
  title={Active Boundary Loss for Semantic Segmentation},
  author={Chi Wang and Yunke Zhang and Miaomiao Cui and Jinlin Liu and Peiran Ren and Yin Yang and Xuansong Xie and Xiansheng Hua and Hujun Bao and Weiwei Xu},
  booktitle={AAAI Conference on Artificial Intelligence},
  year={2021}
}
This paper proposes a novel active boundary loss for semantic segmentation. It can progressively encourage the alignment between predicted boundaries and ground-truth boundaries during end-to-end training, which is not explicitly enforced in commonly used cross-entropy loss. Based on the predicted boundaries detected from the segmentation results using current network parameters, we formulate the boundary alignment problem as a differentiable direction vector prediction problem to guide the… 

Figures and Tables from this paper

Improving Image Segmentation with Boundary Patch Refinement

This work proposes a conceptually simple yet effective post-processing refinement framework, termed BPR, to improve the boundary quality of the prediction of any image segmentation model and extracts and refine a series of small boundary patches along the predicted boundaries.

Contour-Aware Equipotential Learning for Semantic Segmentation

The proposed EPL module can benefit the off- the-shelf fully convolutional network models when recognizing semantic boundary areas and is agnostic to network architectures, and thus it can be plugged into most existing segmentation models.

Context and Boundary Guided Multi-Scale Feature Fusion Network for Semantic Segmentation

  • Baotong MiXun Liang
  • Computer Science
    2022 IEEE International Conference on Multimedia and Expo (ICME)
  • 2022
This paper aims to bridge the gap by seamlessly introducing the context or boundary guidance into the multiple feature fusion operations, so that multi-scale features are effectively combined while maintaining context consistency and sharp object boundary, leading to enhanced semantic segment coherence.

TriangleNet: Edge Prior Augmented Network for Semantic Segmentation through Cross-Task Consistency

This work provides a model-agnostic method that improves the accuracy of semantic segmentation models with zero extra inference runtime overhead, based on the cross-task consistency theory, and incorporates edge priors into semantic segmentations tasks to obtain better results.

Zero Pixel Directional Boundary by Vector Transform

This paper re-interpret boundaries as 1-D surfaces and formulate a one-to-one vector transform function that allows for training of boundary prediction completely avoiding the class imbalance issue and shows the excellent performance over other losses and representations on several datasets.

Representation Separation for Semantic Segmentation with Vision Transformers

Ancient framework of representation separation in local-patch level and global-region level for semantic segmentation with ViTs is presented, targeted for the peculiar over-smoothness of ViTs in semantic segmentsation.

Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation

This work proposes a simple yet effective approach that standardizes themax logits in order to align the different distributions and reflect the relative meanings of max logits within each predicted class, and considers the local regions from two different perspectives based on the intuition that neighboring pixels share similar semantic information.

Coarse-to-Fine Feature Mining for Video Semantic Segmentation

A Coarse-to-Fine Feature Mining (CFFM) technique to learn a unified presentation of static contexts and motional contexts that performs favorably against state-of-the-art methods for video semantic segmentation.

Wave Loss: A Topographic Metric for Image Segmentation

This paper shows how the application of a topographic metric, called wave loss, can be applied in neural network training and increase the accuracy of traditional segmentation algorithms.

References

SHOWING 1-10 OF 78 REFERENCES

InverseForm: A Loss Function for Structured Boundary-Aware Segmentation

A novel boundary-aware loss term for semantic segmentation using an inverse-transformation network, which efficiently learns the degree of parametric transformations between estimated and target boundaries, which allows consistent and significant performance improvement on segmentation backbone models without increasing their size and computational complexity.

Joint Semantic Segmentation and Boundary Detection Using Iterative Pyramid Contexts

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.

Semantic Segmentation with Boundary Neural Fields

A Boundary Neural Field (BNF) is introduced, which is a global energy model integrating FCN predictions with boundary cues that is used to enhance semantic segment coherence and to improve object localization.

A Unified Efficient Pyramid Transformer for Semantic Segmentation

This work proposes a unified framework (UN-EPT) to segment objects by considering both context information and boundary artifacts, and demonstrates promising performance on three popular benchmarks for semantic segmentation with low memory footprint.

Improving Semantic Segmentation via Video Propagation and Label Relaxation

This paper presents a video prediction-based methodology to scale up training sets by synthesizing new training samples in order to improve the accuracy of semantic segmentation networks, and introduces a novel boundary label relaxation technique that makes training robust to annotation noise and propagation artifacts along object boundaries.

Improving Semantic Segmentation via Decoupled Body and Edge Supervision

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.

SegFix: Model-Agnostic Boundary Refinement for Segmentation

A model-agnostic post-processing scheme to improve the boundary quality for the segmentation result that is generated by any existing segmentation model and empirically verify that the SegFix consistently reduces the boundary errors for segmentation results generated from various state-of-the-art models.

Supervised Edge Attention Network for Accurate Image Instance Segmentation

A fully convolutional box head and a supervised edge attention module in mask head and one new IoU prediction branch are proposed to achieve impressive and robust improvement compared to baseline models in instance segmentation.

Convolutional Random Walk Networks for Semantic Image Segmentation

This work introduces a simple, yet effective Convolutional Random Walk Network (RWN) that addresses the issues of poor boundary localization and spatially fragmented predictions with very little increase in model complexity.

Fully Convolutional Instance-Aware Semantic Segmentation

The first fully convolutional end-to-end solution for instance-aware semantic segmentation task, which achieves state-of-the-art performance in both accuracy and efficiency, wins the COCO 2016 segmentation competition by a large margin.
...