Dynamic Scene Deblurring With Parameter Selective Sharing and Nested Skip Connections

Gao, Hongyun; Xin, Tao; Shen, Xiaoyong; Jia, Jiaya

doi:10.1109/cvpr.2019.00397

Cited by 295 publications

(258 citation statements)

References 25 publications

Supporting

Mentioning

256

Contrasting

Unclassified

Order By: Relevance

“…The reason is that the characteristics of the residual network are easy to optimize and can improve the accuracy by adding deeper layers. ResNet's internal residual block uses skip connections [38], which alleviates the problem of gradient disappearance caused by increasing the number of layers in deep neural networks. In contrast, Faster RCNN-mobile greatly improved the detection speed, but it decreased by 1.16% on mAP compared to the original Faster RCNN.…”

Section: ) Analysis Of Different Feature Extraction Network Based Omentioning

confidence: 99%

Deep Learning-Based Object Detection Improvement for Tomato Disease

2020

View full text Add to dashboard Cite

To improve the recognition model accuracy of crop disease leaves and locating diseased leaves, this paper proposes an improved Faster RCNN to detect healthy tomato leaves and four diseases: powdery mildew, blight, leaf mold fungus and ToMV. First, we use a depth residual network to replace VGG16 for image feature extraction so we can obtain deeper disease features. Second, the k-means clustering algorithm is used to cluster the bounding boxes. We improve the anchoring according to the clustering results. The improved anchor frame tends toward the real bounding box of the dataset. Finally, we carry out a k-means experiment with three kinds of different feature extraction networks. The experimental results show that the improved method for crop leaf disease detection had 2.71% higher recognition accuracy and a faster detection speed than the original Faster RCNN.

show abstract

Section: ) Analysis Of Different Feature Extraction Network Based Omentioning

confidence: 99%

Deep Learning-Based Object Detection Improvement for Tomato Disease

2020

View full text Add to dashboard Cite

show abstract

“…There are also many excellent papers on deblurring algorithms [ 39 ]. Kupyn, O., et al [ 40 ] proposed a spatiotemporal attention model to integrate information so that adjacent frames in the video can complement with each other. This dataset deblurred on PSS-NSC [ 40 ], which proposes a parameter-selective sharing mechanism to build a larger and higher-quality defuzzification network framework.…”

Section: Methodsmentioning

confidence: 99%

Estimation of the Gender Ratio of Chickens Based on Computer Vision: Dataset and Exploration

Yao

et al. 2020

Entropy

View full text Add to dashboard Cite

The gender ratio of free-range chickens is considered as a major animal welfare problem in commercial broiler farming. Free-range chicken producers need to identify chicken gender to estimate the economic value of their flock. However, it is challenging for farmers to estimate the gender ratio of chickens efficiently and accurately, since the environmental background is complicated and the chicken number is dynamic. Moreover, manual estimation is likely double counts or missed count and thus is inaccurate and time consuming. Hence, automated methods that can lead to results efficiently and accurately replace the identification abilities of a chicken gender expert, working in a farm environment, are beneficial to the industry. The contributions in this paper include: (1) Building the world’s first chicken gender classification database annotated manually, which comprises 800 chicken flock images captured on a farm and 1000 single chicken images separated from the flock images by an object detection network, labelled with gender information. (2) Training a rooster and hen classifier using a deep neural network and cross entropy in information theory to achieve an average accuracy of 96.85%. The evaluation of the algorithm performance indicates that the proposed automated method is practical for the gender classification of chickens on the farm environment and provides a feasible way of thinking for the estimation of the gender ratio.

show abstract

“…CBDnet [26] is a singleframe method that can restore the real degraded image well. Stack(4)-DMPHN [43] is a single-frame method using a deep stacked hierarchical multi-patch network for image deblurring. For a fair comparison, all multi-frame methods used the same training set, validation set and test set as those used by our network.…”

Section: Comparative Experiments and Analysismentioning

confidence: 99%

“…During a long period, researchers used pooling layers to down-sample image features for large receptive field. But the analysis in [43] showed that unlike clean images, the sharp textures in degraded images change along with the scales of features. Furthermore, Visin et al [44] thought that the pooling layers would drop some detailed information which is important for image restoration.…”

Section: Introductionmentioning

confidence: 99%

Multi-Frame Blind Restoration for Image of Space Target With FRC and Branch-Attention

2020

View full text Add to dashboard Cite

The random noise and anisotropic motion of atmospheric turbulence can cause different degradation patterns, which make images of space targets observed from ground-based stations severely disturbed. In recent years, benefit from the development of convolutional neural networks (CNNs), a large number of effective end-to-end methods were proposed to restore images. However, a single-frame method whose input is just a single image can hardly achieve a further improvement for the restoration image due to the diversified degradation patterns of space-target images. In this paper, we proposed a multi-branch network with a multi-frame input to restore space-target images. The multi-frame input contains spacetarget images which own different degradation patterns at different moments. In this way, we can fully use the complementary information between input frames. And in this network, two effective technologies are introduced: one is the full resolution convolution module which extracts features by using convolutional layers with different dilation rates to keep feature information complete; the other is the branch-attention module which is used to pass effective information between different branches of the network. Furthermore, we demonstrated the effectiveness of our method by comparing it with those state-of-the-art methods. INDEX TERMS Multi-frame image restoration, multi-branch network, self-attention, branch-attention, full resolution convolution, images of space targets.

show abstract

Dynamic Scene Deblurring With Parameter Selective Sharing and Nested Skip Connections

Cited by 295 publications

References 25 publications

Deep Learning-Based Object Detection Improvement for Tomato Disease

Deep Learning-Based Object Detection Improvement for Tomato Disease

Estimation of the Gender Ratio of Chickens Based on Computer Vision: Dataset and Exploration

Multi-Frame Blind Restoration for Image of Space Target With FRC and Branch-Attention

Contact Info

Product

Resources

About