Yuhua Chen

Zihao Chen, Yuhua Chen, Yibin Xie et al.

Non-Cartesian sampling with subspace-constrained image reconstruction is a popular approach to dynamic MRI, but slow iterative reconstruction limits its clinical application. Data-consistent (DC) deep learning can accelerate reconstruction with good image quality, but has not been formulated for non-Cartesian subspace imaging. In this study, we propose a DC non-Cartesian deep subspace learning framework for fast, accurate dynamic MR image reconstruction. Four novel DC formulations are developed and evaluated: two gradient decent approaches, a directly solved approach, and a conjugate gradient approach. We applied a U-Net model with and without DC layers to reconstruct T1-weighted images for cardiac MR Multitasking (an advanced multidimensional imaging method), comparing our results to the iteratively reconstructed reference. Experimental results show that the proposed framework significantly improves reconstruction accuracy over the U-Net model without DC, while significantly accelerating the reconstruction over conventional iterative reconstruction.

Pedro Sarmento, Adarsh Kumar, Yu-Hua Chen et al.

Recently, symbolic music generation with deep learning techniques has witnessed steady improvements. Most works on this topic focus on MIDI representations, but less attention has been paid to symbolic music generation using guitar tablatures (tabs) which can be used to encode multiple instruments. Tabs include information on expressive techniques and fingerings for fretted string instruments in addition to rhythm and pitch. In this work, we use the DadaGP dataset for guitar tab music generation, a corpus of over 26k songs in GuitarPro and token formats. We introduce methods to condition a Transformer-XL deep learning model to generate guitar tabs (GTR-CTRL) based on desired instrumentation (inst-CTRL) and genre (genre-CTRL). Special control tokens are appended at the beginning of each song in the training corpus. We assess the performance of the model with and without conditioning. We propose instrument presence metrics to assess the inst-CTRL model's response to a given instrumentation prompt. We trained a BERT model for downstream genre classification and used it to assess the results obtained with the genre-CTRL model. Statistical analyses evidence significant differences between the conditioned and unconditioned models. Overall, results indicate that the GTR-CTRL methods provide more flexibility and control for guitar-focused symbolic music generation than an unconditioned model.

Lukas Hoyer, Dengxin Dai, Qin Wang et al.

Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we present a framework for semi-supervised and domain-adaptive semantic segmentation, which is enhanced by self-supervised monocular depth estimation (SDE) trained only on unlabeled image sequences. In particular, we utilize SDE as an auxiliary task comprehensively across the entire learning framework: First, we automatically select the most useful samples to be annotated for semantic segmentation based on the correlation of sample diversity and difficulty between SDE and semantic segmentation. Second, we implement a strong data augmentation by mixing images and labels using the geometry of the scene. Third, we transfer knowledge from features learned during SDE to semantic segmentation by means of transfer and multi-task learning. And fourth, we exploit additional labeled synthetic data with Cross-Domain DepthMix and Matching Geometry Sampling to align synthetic and real data. We validate the proposed model on the Cityscapes dataset, where all four contributions demonstrate significant performance gains, and achieve state-of-the-art results for semi-supervised semantic segmentation as well as for semi-supervised domain adaptation. In particular, with only 1/30 of the Cityscapes labels, our method achieves 92% of the fully-supervised baseline performance and even 97% when exploiting additional data from GTA. The source code is available at https://github.com/lhoyer/improving_segmentation_with_selfsupervised_depth.

Lukas Hoyer, Dengxin Dai, Yuhua Chen et al.

Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we present a framework for semi-supervised semantic segmentation, which is enhanced by self-supervised monocular depth estimation from unlabeled image sequences. In particular, we propose three key contributions: (1) We transfer knowledge from features learned during self-supervised depth estimation to semantic segmentation, (2) we implement a strong data augmentation by blending images and labels using the geometry of the scene, and (3) we utilize the depth feature diversity as well as the level of difficulty of learning depth in a student-teacher framework to select the most useful samples to be annotated for semantic segmentation. We validate the proposed model on the Cityscapes dataset, where all three modules demonstrate significant performance gains, and we achieve state-of-the-art results for semi-supervised semantic segmentation. The implementation is available at https://github.com/lhoyer/improving_segmentation_with_selfsupervised_depth.

Jinhong Deng, Wen Li, Yuhua Chen et al.

Cross-domain object detection is challenging, because object detection model is often vulnerable to data variance, especially to the considerable domain shift between two distinctive domains. In this paper, we propose a new Unbiased Mean Teacher (UMT) model for cross-domain object detection. We reveal that there often exists a considerable model bias for the simple mean teacher (MT) model in cross-domain scenarios, and eliminate the model bias with several simple yet highly effective strategies. In particular, for the teacher model, we propose a cross-domain distillation method for MT to maximally exploit the expertise of the teacher model. Moreover, for the student model, we alleviate its bias by augmenting training samples with pixel-level adaptation. Finally, for the teaching process, we employ an out-of-distribution estimation strategy to select samples that most fit the current model to further enhance the cross-domain distillation process. By tackling the model bias issue with these strategies, our UMT model achieves mAPs of 44.1%, 58.1%, 41.7%, and 43.1% on benchmark datasets Clipart1k, Watercolor2k, Foggy Cityscapes, and Cityscapes, respectively, which outperforms the existing state-of-the-art results in notable margins. Our implementation is available at https://github.com/kinredon/umt.

Yu-Hua Chen, Bryan Wang, Yi-Hsuan Yang

We present in this paper PerformacnceNet, a neural network model we proposed recently to achieve score-to-audio music generation. The model learns to convert a music piece from the symbolic domain to the audio domain, assigning performance-level attributes such as changes in velocity automatically to the music and then synthesizing the audio. The model is therefore not just a neural audio synthesizer, but an AI performer that learns to interpret a musical score in its own way. The code and sample outputs of the model can be found online at https://github.com/bwang514/PerformanceNet.

Rui Gong, Dengxin Dai, Yuhua Chen et al.

Image-to-image translation is to map images from a given \emph{style} to another given \emph{style}. While exceptionally successful, current methods assume the availability of training images in both source and target domains, which does not always hold in practice. Inspired by humans' reasoning capability of analogy, we propose analogical image translation (AIT). Given images of two styles in the source domain: $\mathcal{A}$ and $\mathcal{A}^\prime$, along with images $\mathcal{B}$ of the first style in the target domain, learn a model to translate $\mathcal{B}$ to $\mathcal{B}^\prime$ in the target domain, such that $\mathcal{A}:\mathcal{A}^\prime ::\mathcal{B}:\mathcal{B}^\prime$. AIT is especially useful for translation scenarios in which training data of one style is hard to obtain but training data of the same two styles in another domain is available. For instance, in the case from normal conditions to extreme, rare conditions, obtaining real training images for the latter case is challenging but obtaining synthetic data for both cases is relatively easy. In this work, we are interested in adding adverse weather effects, more specifically fog effects, to images taken in clear weather. To circumvent the challenge of collecting real foggy images, AIT learns with synthetic clear-weather images, synthetic foggy images and real clear-weather images to add fog effects onto real clear-weather images without seeing any real foggy images during training. AIT achieves this zero-shot image translation capability by coupling a supervised training scheme in the synthetic domain, a cycle consistency strategy in the real domain, an adversarial training scheme between the two domains, and a novel network design. Experiments show the effectiveness of our method for zero-short image translation and its benefit for downstream tasks such as semantic foggy scene understanding.

Yuhua Chen, Luc Van Gool, Cordelia Schmid et al.

Consistency Guided Scene Flow Estimation (CGSF) is a self-supervised framework for the joint reconstruction of 3D scene structure and motion from stereo video. The model takes two temporal stereo pairs as input, and predicts disparity and scene flow. The model self-adapts at test time by iteratively refining its predictions. The refinement process is guided by a consistency loss, which combines stereo and temporal photo-consistency with a geometric term that couples disparity and 3D motion. To handle inherent modeling error in the consistency loss (e.g. Lambertian assumptions) and for better generalization, we further introduce a learned, output refinement network, which takes the initial predictions, the loss, and the gradient as input, and efficiently predicts a correlated output update. In multiple experiments, including ablation studies, we show that the proposed model can reliably predict disparity and scene flow in challenging imagery, achieves better generalization than the state-of-the-art, and adapts quickly and robustly to unseen domains.

Yuhua Chen, Anthony G. Christodoulou, Zhengwei Zhou et al.

High-resolution (HR) magnetic resonance imaging (MRI) provides detailed anatomical information that is critical for diagnosis in the clinical application. However, HR MRI typically comes at the cost of long scan time, small spatial coverage, and low signal-to-noise ratio (SNR). Recent studies showed that with a deep convolutional neural network (CNN), HR generic images could be recovered from low-resolution (LR) inputs via single image super-resolution (SISR) approaches. Additionally, previous works have shown that a deep 3D CNN can generate high-quality SR MRIs by using learned image priors. However, 3D CNN with deep structures, have a large number of parameters and are computationally expensive. In this paper, we propose a novel 3D CNN architecture, namely a multi-level densely connected super-resolution network (mDCSRN), which is light-weight, fast and accurate. We also show that with the generative adversarial network (GAN)-guided training, the mDCSRN-GAN provides appealing sharp SR images with rich texture details that are highly comparable with the referenced HR images. Our results from experiments on a large public dataset with 1,113 subjects showed that this new architecture outperformed other popular deep learning methods in recovering 4x resolution-downgraded images in both quality and speed.

Yuhua Chen, Dan Ruan, Jiayu Xiao et al.

Segmentation of multiple organs-at-risk (OARs) is essential for radiation therapy treatment planning and other clinical applications. We developed an Automated deep Learning-based Abdominal Multi-Organ segmentation (ALAMO) framework based on 2D U-net and a densely connected network structure with tailored design in data augmentation and training procedures such as deep connection, auxiliary supervision, and multi-view. The model takes in multi-slice MR images and generates the output of segmentation results. Three-Tesla T1 VIBE (Volumetric Interpolated Breath-hold Examination) images of 102 subjects were collected and used in our study. Ten OARs were studied, including the liver, spleen, pancreas, left/right kidneys, stomach, duodenum, small intestine, spinal cord, and vertebral bodies. Two radiologists manually labeled and obtained the consensus contours as the ground-truth. In the complete cohort of 102, 20 samples were held out for independent testing, and the rest were used for training and validation. The performance was measured using volume overlapping and surface distance. The ALAMO framework generated segmentation labels in good agreement with the manual results. Specifically, among the 10 OARs, 9 achieved high Dice Similarity Coefficients (DSCs) in the range of 0.87-0.96, except for the duodenum with a DSC of 0.80. The inference completes within one minute for a 3D volume of 320x288x180. Overall, the ALAMO model matches the state-of-the-art performance. The proposed ALAMO framework allows for fully automated abdominal MR segmentation with high accuracy and low memory and computation time demands.

Suman Saha, Wenhao Xu, Menelaos Kanakis et al.

Nowadays, the increasingly growing number of mobile and computing devices has led to a demand for safer user authentication systems. Face anti-spoofing is a measure towards this direction for bio-metric user authentication, and in particular face recognition, that tries to prevent spoof attacks. The state-of-the-art anti-spoofing techniques leverage the ability of deep neural networks to learn discriminative features, based on cues from the training set images or video samples, in an effort to detect spoof attacks. However, due to the particular nature of the problem, i.e. large variability due to factors like different backgrounds, lighting conditions, camera resolutions, spoof materials, etc., these techniques typically fail to generalize to new samples. In this paper, we explicitly tackle this problem and propose a class-conditional domain discriminator module, that, coupled with a gradient reversal layer, tries to generate live and spoof features that are discriminative, but at the same time robust against the aforementioned variability factors. Extensive experimental analysis shows the effectiveness of the proposed method over existing image- and video-based anti-spoofing techniques, both in terms of numerical improvement as well as when visualizing the learned features.

Yuhua Chen, Jaime L. Shaw, Yibin Xie et al.

High spatiotemporal resolution dynamic magnetic resonance imaging (MRI) is a powerful clinical tool for imaging moving structures as well as to reveal and quantify other physical and physiological dynamics. The low speed of MRI necessitates acceleration methods such as deep learning reconstruction from under-sampled data. However, the massive size of many dynamic MRI problems prevents deep learning networks from directly exploiting global temporal relationships. In this work, we show that by applying deep neural networks inside a priori calculated temporal feature spaces, we enable deep learning reconstruction with global temporal modeling even for image sequences with >40,000 frames. One proposed variation of our approach using dilated multi-level Densely Connected Network (mDCN) speeds up feature space coordinate calculation by 3000x compared to conventional iterative methods, from 20 minutes to 0.39 seconds. Thus, the combination of low-rank tensor and deep learning models not only makes large-scale dynamic MRI feasible but also practical for routine clinical application.

Yuhua Chen, Cordelia Schmid, Cristian Sminchisescu

We present GLNet, a self-supervised framework for learning depth, optical flow, camera pose and intrinsic parameters from monocular video - addressing the difficulty of acquiring realistic ground-truth for such tasks. We propose three contributions: 1) we design new loss functions that capture multiple geometric constraints (eg. epipolar geometry) as well as an adaptive photometric loss that supports multiple moving objects, rigid and non-rigid, 2) we extend the model such that it predicts camera intrinsics, making it applicable to uncalibrated video, and 3) we propose several online refinement strategies that rely on the symmetry of our self-supervised loss in training and testing, in particular optimizing model parameters and/or the output of different tasks, thus leveraging their mutual interactions. The idea of jointly optimizing the system output, under all geometric and photometric constraints can be viewed as a dense generalization of classical bundle adjustment. We demonstrate the effectiveness of our method on KITTI and Cityscapes, where we outperform previous self-supervised approaches on multiple tasks. We also show good generalization for transfer learning in YouTube videos.

Jiancong Wang, Yuhua Chen, Yifan Wu et al.

Single image super-resolution (SISR) reconstruction for magnetic resonance imaging (MRI) has generated significant interest because of its potential to not only speed up imaging but to improve quantitative processing and analysis of available image data. Generative Adversarial Networks (GAN) have proven to perform well in recovering image texture detail, and many variants have therefore been proposed for SISR. In this work, we develop an enhancement to tackle GAN-based 3D SISR by introducing a new residual-in-residual dense block (RRDG) generator that is both memory efficient and achieves state-of-the-art performance in terms of PSNR (Peak Signal to Noise Ratio), SSIM (Structural Similarity) and NRMSE (Normalized Root Mean Squared Error) metrics. We also introduce a patch GAN discriminator with improved convergence behavior to better model brain image texture. We proposed a novel the anatomical fidelity evaluation of the results using a pre-trained brain parcellation network. Finally, these developments are combined through a simple and efficient method to balance etween image and texture quality in the final output.

Chao-Chun Hsu, Yu-Hua Chen, Zi-Yuan Chen et al.

In this paper, we introduce Dixit, an interactive visual storytelling system that the user interacts with iteratively to compose a short story for a photo sequence. The user initiates the process by uploading a sequence of photos. Dixit first extracts text terms from each photo which describe the objects (e.g., boy, bike) or actions (e.g., sleep) in the photo, and then allows the user to add new terms or remove existing terms. Dixit then generates a short story based on these terms. Behind the scenes, Dixit uses an LSTM-based model trained on image caption data and FrameNet to distill terms from each image and utilizes a transformer decoder to compose a context-coherent story. Users change images or terms iteratively with Dixit to create the most ideal story. Dixit also allows users to manually edit and rate stories. The proposed procedure opens up possibilities for interpretable and controllable visual storytelling, allowing users to understand the story formation rationale and to intervene in the generation process.

Yuhua Chen, Jordi Pont-Tuset, Alberto Montes et al.

This paper tackles the problem of video object segmentation, given some user annotation which indicates the object of interest. The problem is formulated as pixel-wise retrieval in a learned embedding space: we embed pixels of the same object instance into the vicinity of each other, using a fully convolutional network trained by a modified triplet loss as the embedding model. Then the annotated pixels are set as reference and the rest of the pixels are classified using a nearest-neighbor approach. The proposed method supports different kinds of user input such as segmentation mask in the first frame (semi-supervised scenario), or a sparse set of clicked points (interactive scenario). In the semi-supervised scenario, we achieve results competitive with the state of the art but at a fraction of computation cost (275 milliseconds per frame). In the interactive scenario where the user is able to refine their input iteratively, the proposed method provides instant response to each input, and reaches comparable quality to competing methods with much less interaction.

Yuhua Chen, Feng Shi, Anthony G. Christodoulou et al.

High-resolution (HR) magnetic resonance images (MRI) provide detailed anatomical information important for clinical application and quantitative image analysis. However, HR MRI conventionally comes at the cost of longer scan time, smaller spatial coverage, and lower signal-to-noise ratio (SNR). Recent studies have shown that single image super-resolution (SISR), a technique to recover HR details from one single low-resolution (LR) input image, could provide high-quality image details with the help of advanced deep convolutional neural networks (CNN). However, deep neural networks consume memory heavily and run slowly, especially in 3D settings. In this paper, we propose a novel 3D neural network design, namely a multi-level densely connected super-resolution network (mDCSRN) with generative adversarial network (GAN)-guided training. The mDCSRN quickly trains and inferences and the GAN promotes realistic output hardly distinguishable from original HR images. Our results from experiments on a dataset with 1,113 subjects show that our new architecture beats other popular deep learning methods in recovering 4x resolution-downgraded im-ages and runs 6x faster.

Sergi Caelles, Alberto Montes, Kevis-Kokitsi Maninis et al.

We present the 2018 DAVIS Challenge on Video Object Segmentation, a public competition specifically designed for the task of video object segmentation. It builds upon the DAVIS 2017 dataset, which was presented in the previous edition of the DAVIS Challenge, and added 100 videos with multiple objects per sequence to the original DAVIS 2016 dataset. Motivated by the analysis of the results of the 2017 edition, the main track of the competition will be the same than in the previous edition (segmentation given the full mask of the objects in the first frame -- semi-supervised scenario). This edition, however, also adds an interactive segmentation teaser track, where the participants will interact with a web service simulating the input of a human that provides scribbles to iteratively improve the result.

Siming Yan, Feng Shi, Yuhua Chen et al.

Coronary calcium causes beam hardening and blooming artifacts on cardiac computed tomography angiography (CTA) images, which lead to overestimation of lumen stenosis and reduction of diagnostic specificity. To properly remove coronary calcification and restore arterial lumen precisely, we propose a machine learning-based method with a multi-step inpainting process. We developed a new network configuration, Dense-Unet, to achieve optimal performance with low computational cost. Results after the calcium removal process were validated by comparing with gold-standard X-ray angiography. Our results demonstrated that removing coronary calcification from images with the proposed approach was feasible, and may potentially improve the diagnostic accuracy of CTA.

Yuhua Chen, Wen Li, Luc Van Gool

Exploiting synthetic data to learn deep models has attracted increasing attention in recent years. However, the intrinsic domain difference between synthetic and real images usually causes a significant performance drop when applying the learned model to real world scenarios. This is mainly due to two reasons: 1) the model overfits to synthetic images, making the convolutional filters incompetent to extract informative representation for real images; 2) there is a distribution difference between synthetic and real data, which is also known as the domain adaptation problem. To this end, we propose a new reality oriented adaptation approach for urban scene semantic segmentation by learning from synthetic data. First, we propose a target guided distillation approach to learn the real image style, which is achieved by training the segmentation model to imitate a pretrained real style model using real images. Second, we further take advantage of the intrinsic spatial structure presented in urban scene images, and propose a spatial-aware adaptation scheme to effectively align the distribution of two domains. These two modules can be readily integrated with existing state-of-the-art semantic segmentation networks to improve their generalizability when adapting from synthetic to real urban scenes. We evaluate the proposed method on Cityscapes dataset by adapting from GTAV and SYNTHIA datasets, where the results demonstrate the effectiveness of our method.

Sergi Caelles, Yuhua Chen, Jordi Pont-Tuset et al.

This paper tackles the problem of semi-supervised video object segmentation, that is, segmenting an object in a sequence given its mask in the first frame. One of the main challenges in this scenario is the change of appearance of the objects of interest. Their semantics, on the other hand, do not vary. This paper investigates how to take advantage of such invariance via the introduction of a semantic prior that guides the appearance model. Specifically, given the segmentation mask of the first frame of a sequence, we estimate the semantics of the object of interest, and propagate that knowledge throughout the sequence to improve the results based on an appearance model. We present Semantically-Guided Video Object Segmentation (SGV), which improves results over previous state of the art on two different datasets using a variety of evaluation metrics, while running in half a second per frame.

Dengxin Dai, Yujian Wang, Yuhua Chen et al.

Despite the great advances made in the field of image super-resolution (ISR) during the last years, the performance has merely been evaluated perceptually. Thus, it is still unclear whether ISR is helpful for other vision tasks. In this paper, we present the first comprehensive study and analysis of the usefulness of ISR for other vision applications. In particular, six ISR methods are evaluated on four popular vision tasks, namely edge detection, semantic image segmentation, digit recognition, and scene recognition. We show that applying ISR to input images of other vision systems does improve their performance when the input images are of low-resolution. We also study the correlation between four standard perceptual evaluation criteria (namely PSNR, SSIM, IFC, and NQM) and the usefulness of ISR to the vision tasks. Experiments show that they correlate well with each other in general, but perceptual criteria are still not accurate enough to be used as full proxies for the usefulness. We hope this work will inspire the community to evaluate ISR methods also in real vision applications, and to adopt ISR as a pre-processing step of other vision tasks if the resolution of their input images is low.