Holistically-Nested Edge Detection

Xie, Sihong; Tu, Zhuowen

doi:10.1109/iccv.2015.164

Cited by 2,265 publications

(429 citation statements)

References 32 publications

Supporting

Mentioning

332

Contrasting

Unclassified

Order By: Relevance

“…[Liu and Han, 2016] also design a deep hierarchical network to learn a coarse global estimation and then refine the saliency map hierarchically and progressively. Then, [Hou et al, 2017] introduce dense short connections to the skip-layers within the holistically-nested edge detection (HED) architecture [Xie and Tu, 2015] to get rich multi-scale features for SOD. propose a bidirectional learning framework to aggregate multilevel convolutional features for SOD.…”

Section: Related Workmentioning

confidence: 99%

“…However, for a typical natural image, the class distribution of salient/non-salient pixels is heavily imbalanced: most of the pixels in the ground truth are non-salient. To automatically balance the loss between positive/negative classes, we introduce a class-balancing weight β on a per-pixel term basis, following [Xie and Tu, 2015]. Specifically, we define the following weighted cross-entropy loss function,…”

Section: Weighted Structural Lossmentioning

confidence: 99%

See 1 more Smart Citation

Salient Object Detection by Lossless Feature Reflection

Zhang

Liu

et al. 2018

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

Salient object detection, which aims to identify and locate the most salient pixels or regions in images, has been attracting more and more interest due to its various real-world applications. However, this vision task is quite challenging, especially under complex image scenes. Inspired by the intrinsic reflection of natural images, in this paper we propose a novel feature learning framework for large-scale salient object detection. Specifically, we design a symmetrical fully convolutional network (SFCN) to learn complementary saliency features under the guidance of lossless feature reflection. The location information, together with contextual and semantic information, of salient objects are jointly utilized to supervise the proposed network for more accurate saliency predictions. In addition, to overcome the blurry boundary problem, we propose a new structural loss function to learn clear object boundaries and spatially consistent saliency. The coarse prediction results are effectively refined by these structural information for performance improvements. Extensive experiments on seven saliency detection datasets demonstrate that our approach achieves consistently superior performance and outperforms the very recent state-of-the-art methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Weighted Structural Lossmentioning

confidence: 99%

Salient Object Detection by Lossless Feature Reflection

Zhang

Liu

et al. 2018

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…A good idea for CNN-based multi-scale segmentation and detection is using the skip-layer network architecture [29,41]. In this architecture, links are added to incorporate the feature responses from different levels of the primary network stream, and these responses are then combined in a shared output layer [42]. Our multi-scale network architecture is illustrated in Figure 5.…”

Section: Network Architecture For Multi-scale Classificationmentioning

confidence: 99%

Classification for High Resolution Remote Sensing Imagery Using a Fully Convolutional Network

et al. 2017

View full text Add to dashboard Cite

Abstract:As a variant of Convolutional Neural Networks (CNNs) in Deep Learning, the Fully Convolutional Network (FCN) model achieved state-of-the-art performance for natural image semantic segmentation. In this paper, an accurate classification approach for high resolution remote sensing imagery based on the improved FCN model is proposed. Firstly, we improve the density of output class maps by introducing Atrous convolution, and secondly, we design a multi-scale network architecture by adding a skip-layer structure to make it capable for multi-resolution image classification. Finally, we further refine the output class map using Conditional Random Fields (CRFs) post-processing. Our classification model is trained on 70 GF-2 true color images, and tested on the other 4 GF-2 images and 3 IKONOS true color images. We also employ object-oriented classification, patch-based CNN classification, and the FCN-8s approach on the same images for comparison. The experiments show that compared with the existing approaches, our approach has an obvious improvement in accuracy. The average precision, recall, and Kappa coefficient of our approach are 0.81, 0.78, and 0.83, respectively. The experiments also prove that our approach has strong applicability for multi-resolution image classification.

show abstract

“…UN follows an encoder-decoder architecture, with the encoder part being a DN and the decoder part an up-sampling network that gradually restores resolution via 2×2 transposed convolution [9]. We consider three layer aggregation approaches: deep supervision (DS) [10], feature pyramid network (FPN) [11], and iterative deep aggregation (IDA) [12]. As shown in Fig.…”

Section: Methodsmentioning

confidence: 99%

Automatic Lacunae Localization in Placental Ultrasound Images via Layer Aggregation

Collins

Noble

2018

Medical Image Computing and Computer Assisted Intervention – MICCAI 2018

View full text Add to dashboard Cite

Accurate localization of structural abnormalities is a precursor for image-based prenatal assessment of adverse conditions. For clinical screening and diagnosis of abnormally invasive placenta (AIP), a life-threatening obstetric condition, qualitative and quantitative analysis of ultrasonic patterns correlated to placental lesions such as placental lacunae (PL) is challenging and time-consuming to perform even for experienced sonographers. There is a need for automated placental lesion localization that does not rely on expensive human annotations such as detailed manual segmentation of anatomical structures. In this paper, we investigate PL localization in 2D placental ultrasound images. First, we demonstrate the effectiveness of generating confidence maps from weak dot annotations in localizing PL as an alternative to expensive manual segmentation. Then we propose a layer aggregation structure based on iterative deep aggregation (IDA) for PL localization. Models with this structure were evaluated with 10-fold cross-validations on an AIP database (containing 3,440 images with 9,618 labelled PL from 23 AIP and 11 non-AIP participants). Experimental results demonstrate that the model with the proposed structure yielded the highest mean average precision (mAP=35.7%), surpassing all other baseline models (32.6%, 32.2%, 29.7%). We argue that features from shallower stages can contribute to PL localization more effectively using the proposed structure. To our knowledge, this is the first successful application of machine learning to placental lesion analysis and has the potential to be adapted for other clinical scenarios in breast, liver, and prostate cancer imaging.

show abstract

Holistically-Nested Edge Detection

Cited by 2,265 publications

References 32 publications

Salient Object Detection by Lossless Feature Reflection

Salient Object Detection by Lossless Feature Reflection

Classification for High Resolution Remote Sensing Imagery Using a Fully Convolutional Network

Automatic Lacunae Localization in Placental Ultrasound Images via Layer Aggregation

Contact Info

Product

Resources

About