Paper Reading AI Learner

Learning to predict crisp boundaries

2018-07-26 12:40:36
Ruoxi Deng, Chunhua Shen, Shengjun Liu, Huibing Wang, Xinru Liu

Abstract

Recent methods for boundary or edge detection built on Deep Convolutional Neural Networks (CNNs) typically suffer from the issue of predicted edges being thick and need post-processing to obtain crisp boundaries. Highly imbalanced categories of boundary versus background in training data is one of main reasons for the above problem. In this work, the aim is to make CNNs produce sharp boundaries without post-processing. We introduce a novel loss for boundary detection, which is very effective for classifying imbalanced data and allows CNNs to produce crisp boundaries. Moreover, we propose an end-to-end network which adopts the bottom-up/top-down architecture to tackle the task. The proposed network effectively leverages hierarchical features and produces pixel-accurate boundary mask, which is critical to reconstruct the edge map. Our experiments illustrate that directly making crisp prediction not only promotes the visual results of CNNs, but also achieves better results against the state-of-the-art on the BSDS500 dataset (ODS F-score of .815) and the NYU Depth dataset (ODS F-score of .762).

Abstract (translated)

最近基于深度卷积神经网络(CNN)的边界或边缘检测方法通常遭受预测边缘厚且需要后处理以获得清晰边界的问题。训练数据中高度不平衡的边界与背景类别是导致上述问题的主要原因之一。在这项工作中,目标是使CNN产生清晰的边界而无需后处理。我们引入了一种新的边界检测损失,这对于分类不平衡数据非常有效,并且允许CNN产生清晰的边界。此外,我们提出了一种端到端网络,它采用自下而上/自上而下的架构来处理任务。所提出的网络有效地利用分层特征并产生像素精确的边界掩模,这对于重建边缘图是至关重要的。我们的实验表明,直接进行清晰预测不仅可以促进CNN的视觉效果,而且可以在BSDS500数据集(ODS F-score为.815)和NYU Depth数据集( ODS F-score为.762)。

URL

https://arxiv.org/abs/1807.10097

PDF

https://arxiv.org/pdf/1807.10097.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot