Multi-scale Hierarchical Residual Network for Dense Captioning

Tian, Yan; Wang, Xun; Wu, Juanjuan; Wang, Ruili; Yang, Bailin

doi:10.1613/jair.1.11338

Cited by 22 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To stabilize the training of deep network, we introduce residual network blocks and skip connections to the network, which can increase training efficiency, and achieve high accuracy as well [19]. The residual networks (also known as ResNet) have been successfully applied to a range of diverse areas of research [17,20].…”

Section: Introductionmentioning

confidence: 99%

DeepF0: End-To-End Fundamental Frequency Estimation for Music and Speech Signals

Singh

Wang

Qiu

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

We propose a novel pitch estimation technique called DeepF0, which leverages the available annotated data to directly learns from the raw audio in a data-driven manner. f0 estimation is important in various speech processing and music information retrieval applications. Existing deep learning models for pitch estimations have relatively limited learning capabilities due to their shallow receptive field. The proposed model addresses this issue by extending the receptive field of a network by introducing the dilated convolutional blocks into the network. The dilation factor increases the network receptive field exponentially without increasing the parameters of the model exponentially. To make the training process more efficient and faster, DeepF0 is augmented with residual blocks with residual connections. Our empirical evaluation demonstrates that the proposed model outperforms the baselines in terms of raw pitch accuracy and raw chroma accuracy even using 77.4% fewer network parameters. We also show that our model can capture reasonably well pitch estimation even under the various levels of accompaniment noise.

show abstract

Section: Introductionmentioning

confidence: 99%

DeepF0: End-To-End Fundamental Frequency Estimation for Music and Speech Signals

Singh

Wang

Qiu

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Hyperparameters are also important in our approach, such as mixture coefficients in Eqs. 3, (4), and (7). The longterm dependency provides a context cue to increase the discriminant capacity for pixel-wise tasks, such as medical image segmentation.…”

Section: Discussionmentioning

confidence: 99%

“…Recently, medical image segmentation has made considerable achievement owing to convolutional neural network with cascade structure 1 and multiscale analysis. [2][3][4] However, accurately classifying each pixel is still challenging in MRI databased brain tumor segmentation. The MRI data have relatively low image contrast, and different types of tumors present ambiguous patterns.…”

Section: Introductionmentioning

confidence: 99%

Spatial‐channel relation learning for brain tumor segmentation

Cheng

Ji²,

Ding

2020

Medical Physics

View full text Add to dashboard Cite

Purpose: Recently, research on brain tumor segmentation has made great progress. However, ambiguous patterns in magnetic resonance imaging data and linear fusion omitting semantic gaps between features in different branches remain challenging. We need to design a mechanism to fully utilize the similarity within the spatial space and channel space and the correlation between these two spaces to improve the result of volumetric segmentation. Methods: We propose a revised cascade structure network. In each subnetwork, a context exploitation module is introduced between the encoder and decoder, in which the dual attention mechanism is adopted to learn the information within the spatial space and channel space, and space interaction learning is employed to model the relation between the spatial and channel spaces. Results: Extensive experiments on the BraTS19 dataset have evaluated that our approach improves the dice coefficient (DC) by a margin of 2.1, 2.0, and 1.4 for whole tumor (WT), tumor core (TC), and enhancing tumor (ET), respectively, obtaining results competitive with the state-of-art approaches working on brain tumor segmentation. Conclusions: Context exploitation in the embedding feature spaces, including intraspace relations and interspace relations, can effectively model dependency in semantic features and alleviate the semantic gap in multimodel data. Our approach is also robust to variations in different modality.

show abstract

“…In recent years, deep learning networks and especially convolutional neural networks (CNNs) have achieved remarkable success in many computer vision areas, including object recognition [1] [2], semantic segmentation [3] [4] [5], depth estimation [6], object detection [7] [8], etc. Instead of crafting features by humans, CNNs use convolutional layers to automatically extract the features from the input images and provide end-to-end solutions to the perceptional task.…”

Section: Introductionmentioning

confidence: 99%

Adversarial Perturbation on MRI Modalities in Brain Tumor Segmentation

Cheng

Ji²

2020

IEEE Access

View full text Add to dashboard Cite

Convolutional neural networks(CNNs) have been widely used by biomedical image segmentation applications. U-net, as a semantic segmentation method, has become a mainstream approach to brain tumor segmentation. However, the intrinsic vulnerability of CNNs also brings potential risks to all CNN-based applications, including semantic segmentation applications. In this paper, we create a universal adversarial perturbation and apply it on every modality in order to investigate how the adversarial perturbation affects each Magnetic Resonance Imaging(MRI) modality and the MRI images overall. We evaluate the performance when all four modalities are attacked and when one modality is attacked. The results show the following: 1) The adversarial perturbation affects the accuracy performance greatly, regardless of the size of the perturbation; 2) When only one modality is attacked, the network structure and the other three modalities provide some resistance to the adversarial perturbation; and 3) There are performance differences in different modalities, which are strongly related to the intensity distribution. T2 is least affected by the adversarial perturbation, while T1 and T1ce are more affected by the adversarial perturbation.

show abstract

Multi-scale Hierarchical Residual Network for Dense Captioning

Cited by 22 publications

References 27 publications

DeepF0: End-To-End Fundamental Frequency Estimation for Music and Speech Signals

DeepF0: End-To-End Fundamental Frequency Estimation for Music and Speech Signals

Spatial‐channel relation learning for brain tumor segmentation

Adversarial Perturbation on MRI Modalities in Brain Tumor Segmentation

Contact Info

Product

Resources

About