InverseForm: A Loss Function for Structured Boundary-Aware Segmentation

  title={InverseForm: A Loss Function for Structured Boundary-Aware Segmentation},
  author={Shubhankar Borse and Ying Wang and Yizhe Zhang and Fatih Murat Porikli},
  journal={2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
We present 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. This plug-in loss term complements the cross-entropy loss in capturing boundary transformations and allows consistent and significant performance improvement on segmentation backbone models without increasing their size and computational complexity. We analyze the quantitative and… 

Figures and Tables from this paper

JUPITER – ROS based Vehicle Platform for Autonomous Driving Research

A Robot Operating System (ROS) based prototype vehicle that is built on a Porsche Cayenne, which provides a dedicated test environment for autonomous research and the approach for data recording and long-term persistence is described.

Scene Aware Semantic Crack Segmentation from Oblique Drone Imagery

The M-CrackNet decomposes the task of building crack detection into crack related scene activation and semantic crack segmentation so that the method can be transferred to other scenes with cracks, and by parallelly processing images with two decomposed modules, the computational cost has been largely reduced.

X-Align: Cross-Modal Cross-View Alignment for Bird's-Eye-View Segmentation

This paper proposes X-Align, a novel end-to-end cross-modal and cross-view learning framework for BEV segmentation consisting of a novel Cross-Modal Feature Alignment (X-FA) loss, and provides extensive ablation studies to demonstrate the effectiveness of the individual components.

DCANet: Differential Convolution Attention Network for RGB-D Semantic Segmentation

It is shown that depth maps are suitable to provide intrinsic intrinsic patterns of objects due to their local depth continuity, while RGB images effectively provide a global view, and that a pixel differential convolution attention (DCA) module is proposed to consider geometric information and local-range correlations for depth data.

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.

Boosting Night-time Scene Parsing with Learnable Frequency

This paper proposes to exploit the image frequency distributions for night-time scene parsing by proposing a Learnable Frequency Encoder (LFE) to model the relationship between different frequency coefficients and a Spatial Frequency Fusion module (SFF) that fuses both spatial and frequency information to guide the extraction of spatial context features.

BANet: Boundary-Assistant Encoder-Decoder Network for Semantic Segmentation

Results show that, with the aid of boundary information, BANet is able to produce more consistent segmentation predictions with accurately delineated object shapes and boundaries, leading to the state-of-the-art performance on Cityscapes, and competitive results on PASCAL Context and ADE20K with respect to recent semantic segmentation networks.

BA-GCA Net: Boundary-Aware Grid Contextual Attention Net in Osteosarcoma MRI Image Segmentation

A novel boundary-aware grid contextual attention net (BA-GCA Net) is proposed to solve the problem of insufficient accuracy in osteosarcoma MRI image segmentation and achieves higher segmentation accuracy than existing methods with only a slight increase in the number of parameters and computational complexity.

SeeThroughNet: Resurrection of Auxiliary Loss by Preserving Class Probability Information

This paper introduces Class Probability Preserving pooling to alleviate information loss in down-sampling the ground truth in semantic segmentation tasks and proposes See-Through Network that adopts an improved multi-scale attention-coupled decoder structure to maximize the effect of CPP pooling.

From Intuition to Reasoning: Analyzing Correlative Attributes of Walkability in Urban Environments with Machine Learning

The results demonstrate the usefulness of the approach to predict the walkability of an urban location based on an ML analysis of street image content and a novel feature extraction method based on semantic segmentation techniques.



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.

Large Kernel Matters — Improve Semantic Segmentation by Global Convolutional Network

This work proposes a Global Convolutional Network to address both the classification and localization issues for the semantic segmentation and suggests a residual-based boundary refinement to further refine the object boundaries.

RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation

RefineNet is presented, a generic multi-path refinement network that explicitly exploits all the information available along the down-sampling process to enable high-resolution prediction using long-range residual connections and introduces chained residual pooling, which captures rich background context in an efficient manner.

Boundary-Aware Feature Propagation for Scene Segmentation

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 and achieves new state-of-the-art segmentation performance on three challenging semantic segmentation datasets, i.e., PASCAL-Context, CamVid, and Cityscapes.

Pushing the Boundaries of Boundary Detection using Deep Learning

This work shows that adapting Deep Convolutional Neural Network training to the task of boundary detection can result in substantial improvements over the current state-of-the-art in boundary detection, and examines the potential of the boundary detector in conjunction with thetask of semantic segmentation.

Semantic Correlation Promoted Shape-Variant Context for Segmentation

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.

Hierarchical Multi-Scale Attention for Semantic Segmentation

This work presents an attention-based approach to combining multi-scale predictions, and shows that predictions at certain scales are better at resolving particular failures modes, and that the network learns to favor those scales for such cases in order to generate better predictions.

CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement

This paper presents quantitative and qualitative studies on different datasets to show that CascadePSP can reveal pixel-accurate segmentation boundaries using the novel refinement module without any finetuning.

Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transform

This work proposes replacing the fully-connected CRF with domain transform (DT), a modern edge-preserving filtering method in which the amount of smoothing is controlled by a reference edge map, and shows that it yields comparable semantic segmentation results, accurately capturing object boundaries.

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

This work addresses the task of semantic image segmentation with Deep Learning and proposes atrous spatial pyramid pooling (ASPP), which is proposed to robustly segment objects at multiple scales, and improves the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models.