Learning to Refine Object Contours with a Top-Down Fully Convolutional Encoder-Decoder Network
نویسندگان
چکیده
We develop a novel deep contour detection algorithm with a top-down fully convolutional encoder-decoder network. Our proposed method, named TD-CEDN, solves two important issues in this low-level vision problem: (1) learning multi-scale and multi-level features; and (2) applying an effective top-down refined approach in the networks. TD-CEDN performs the pixel-wise prediction by means of leveraging features at all layers of the net. Unlike skip connections and previous encoder-decoder methods, we first learn a coarse feature map after the encoder stage in a feedforward pass, and then refine this feature map in a top-down strategy during the decoder stage utilizing features at successively lower layers. Therefore, the deconvolutional process is conducted stepwise, which is guided by Deeply-Supervision Net providing the integrated direct supervision. The above proposed technologies lead to a more precise and clearer prediction. Our proposed algorithm achieved the state-of-the-art on the BSDS500 dataset (ODS F-score of 0.788), the PASCAL VOC2012 dataset (ODS F-score of 0.588), and and the NYU Depth dataset (ODS F-score of 0.735).
منابع مشابه
Squeeze-SegNet: A new fast Deep Convolutional Neural Network for Semantic Segmentation
The recent researches in Deep Convolutional Neural Network have focused their attention on improving accuracy that provide significant advances. However, if they were limited to classification tasks, nowadays with contributions from Scientific Communities who are embarking in this field, they have become very useful in higher level tasks such as object detection and pixel-wise semantic segmenta...
متن کاملAn efficient method for cloud detection based on the feature-level fusion of Landsat-8 OLI spectral bands in deep convolutional neural network
Cloud segmentation is a critical pre-processing step for any multi-spectral satellite image application. In particular, disaster-related applications e.g., flood monitoring or rapid damage mapping, which are highly time and data-critical, require methods that produce accurate cloud masks in a short time while being able to adapt to large variations in the target domain (induced by atmospheric c...
متن کاملA Fully Convolutional Neural Network for Speech Enhancement
In hearing aids, the presence of babble noise degrades hearing intelligibility of human speech greatly. However, removing the babble without creating artifacts in human speech is a challenging task in a low SNR environment. Here, we sought to solve the problem by finding a ‘mapping’ between noisy speech spectra and clean speech spectra via supervised learning. Specifically, we propose using ful...
متن کاملProvide a Deep Convolutional Neural Network Optimized with Morphological Filters to Map Trees in Urban Environments Using Aerial Imagery
Today, we cannot ignore the role of trees in the quality of human life, so that the earth is inconceivable for humans without the presence of trees. In addition to their natural role, urban trees are also very important in terms of visual beauty. Aerial imagery using unmanned platforms with very high spatial resolution is available today. Convolutional neural networks based deep learning method...
متن کاملFoldingNet: Interpretable Unsupervised Learning on 3D Point Clouds
Recent deep networks that directly handle points in a point set, e.g., PointNet, have been state-of-the-art for supervised learning tasks on point clouds such as classification and segmentation. In this work, a novel end-toend deep auto-encoder is proposed to address unsupervised learning challenges on point clouds. On the encoder side, a graph-based enhancement is enforced to promote local str...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- CoRR
دوره abs/1705.04456 شماره
صفحات -
تاریخ انتشار 2017