arXiv subjects

Guanghui Wang

Publications and source records attributed to Guanghui Wang.

At least 199 records · Page 11Linked to original sources

arXiv2021

Training Deep Neural Networks via Branch-and-Bound

In this paper, we propose BPGrad, a novel approximate algorithm for deep nueral network training, based on adaptive estimates of feasible region via branch-and-bound. The method is based on the assumption of Lipschitz continuity in objective function, and as a result, it can adaptively determine the step size for the current gradient given the history of previous updates. We prove that, by repeating such a branch-and-pruning procedure, it can achieve the optimal solution within finite iterations. A computationally efficient solver based on BPGrad has been proposed to train the deep neural networks. Empirical results demonstrate that BPGrad solver works well in practice and compares favorably to other stochastic optimization methods in the tasks of object recognition, detection, and segmentation. The code is available at \url{https://github.com/RyanCV/BPGrad}.

cs.CV↗

arXiv2021

A Domain Gap Aware Generative Adversarial Network for Multi-domain Image Translation

Recent image-to-image translation models have shown great success in mapping local textures between two domains. Existing approaches rely on a cycle-consistency constraint that supervises the generators to learn an inverse mapping. However, learning the inverse mapping introduces extra trainable parameters and it is unable to learn the inverse mapping for some domains. As a result, they are ineffective in the scenarios where (i) multiple visual image domains are involved; (ii) both structure and texture transformations are required; and (iii) semantic consistency is preserved. To solve these challenges, the paper proposes a unified model to translate images across multiple domains with significant domain gaps. Unlike previous models that constrain the generators with the ubiquitous cycle-consistency constraint to achieve the content similarity, the proposed model employs a perceptual self-regularization constraint. With a single unified generator, the model can maintain consistency over the global shapes as well as the local texture information across multiple domains. Extensive qualitative and quantitative evaluations demonstrate the effectiveness and superior performance over state-of-the-art models. It is more effective in representing shape deformation in challenging mappings with significant dataset variation across multiple domains.

cs.CV↗

arXiv2021

Large $ Y_{k,b} $-tilings and Hamilton $ \ell $-cycles in $k$-uniform hypergraphs

Let $Y_{3,2}$ be the $3$-uniform hypergraph with two edges intersecting in two vertices. Our main result is that any $n$-vertex 3-uniform hypergraph with at least $\binom{n}{3} - \binom{n-m+1}{3} + o(n^3)$ edges contains a collection of $m$ vertex-disjoint copies of $Y_{3,2}$, for $m\le n/7$. The bound on the number of edges is asymptotically best possible. This problem generalizes the Matching Conjecture of Erdős. We then use this result combined with the absorbing method to determine the asymptotically best possible minimum $(k-3)$-degree threshold for $\ell$-Hamiltonicity in $k$-graphs, where $k\ge 7$ is odd and $\ell=(k-1)/2$. Moreover, we give related results on $ Y_{k,b} $-tilings and Hamilton $ \ell $-cycles with $ d $-degree for some other values of $ k,\ell,d $.

math.CO↗

arXiv2021

DRB-GAN: A Dynamic ResBlock Generative Adversarial Network for Artistic Style Transfer

The paper proposes a Dynamic ResBlock Generative Adversarial Network (DRB-GAN) for artistic style transfer. The style code is modeled as the shared parameters for Dynamic ResBlocks connecting both the style encoding network and the style transfer network. In the style encoding network, a style class-aware attention mechanism is used to attend the style feature representation for generating the style codes. In the style transfer network, multiple Dynamic ResBlocks are designed to integrate the style code and the extracted CNN semantic feature and then feed into the spatial window Layer-Instance Normalization (SW-LIN) decoder, which enables high-quality synthetic images with artistic style transfer. Moreover, the style collection conditional discriminator is designed to equip our DRB-GAN model with abilities for both arbitrary style transfer and collection style transfer during the training stage. No matter for arbitrary style transfer or collection style transfer, extensive experiments strongly demonstrate that our proposed DRB-GAN outperforms state-of-the-art methods and exhibits its superior performance in terms of visual quality and efficiency. Our source code is available at \color{magenta}{\url{https://github.com/xuwenju123/DRB-GAN}}.

cs.CV↗

arXiv2021

Audio-Visual Transformer Based Crowd Counting

Crowd estimation is a very challenging problem. The most recent study tries to exploit auditory information to aid the visual models, however, the performance is limited due to the lack of an effective approach for feature extraction and integration. The paper proposes a new audiovisual multi-task network to address the critical challenges in crowd counting by effectively utilizing both visual and audio inputs for better modalities association and productive feature extraction. The proposed network introduces the notion of auxiliary and explicit image patch-importance ranking (PIR) and patch-wise crowd estimate (PCE) information to produce a third (run-time) modality. These modalities (audio, visual, run-time) undergo a transformer-inspired cross-modality co-attention mechanism to finally output the crowd estimate. To acquire rich visual features, we propose a multi-branch structure with transformer-style fusion in-between. Extensive experimental evaluations show that the proposed scheme outperforms the state-of-the-art networks under all evaluation settings with up to 33.8% improvement. We also analyze and compare the vision-only variant of our network and empirically demonstrate its superiority over previous approaches.

cs.CV↗

arXiv2021

Properly colored short cycles in edge-colored graphs

Properly colored cycles in edge-colored graphs are closely related to directed cycles in oriented graphs. As an analogy of the well-known Caccetta-Häggkvist Conjecture, we study the existence of properly colored cycles of bounded length in an edge-colored graph. We first prove that for all integers $s$ and $t$ with $t\geq s\geq2$, every edge-colored graph $G$ with no properly colored $K_{s,t}$ contains a spanning subgraph $H$ which admits an orientation $D$ such that every directed cycle in $D$ is a properly colored cycle in $G$. Using this result, we show that for $r\geq4$, if the Caccetta-Häggkvist Conjecture holds , then every edge-colored graph of order $n$ with minimum color degree at least $n/r+2\sqrt{n}+1$ contains a properly colored cycle of length at most $r$. In addition, we also obtain an asymptotically tight total color degree condition which ensures a properly colored (or rainbow) $K_{s,t}$.

math.CO↗

arXiv2021

A Fine-Grained Visual Attention Approach for Fingerspelling Recognition in the Wild

Fingerspelling in sign language has been the means of communicating technical terms and proper nouns when they do not have dedicated sign language gestures. Automatic recognition of fingerspelling can help resolve communication barriers when interacting with deaf people. The main challenges prevalent in fingerspelling recognition are the ambiguity in the gestures and strong articulation of the hands. The automatic recognition model should address high inter-class visual similarity and high intra-class variation in the gestures. Most of the existing research in fingerspelling recognition has focused on the dataset collected in a controlled environment. The recent collection of a large-scale annotated fingerspelling dataset in the wild, from social media and online platforms, captures the challenges in a real-world scenario. In this work, we propose a fine-grained visual attention mechanism using the Transformer model for the sequence-to-sequence prediction task in the wild dataset. The fine-grained attention is achieved by utilizing the change in motion of the video frames (optical flow) in sequential context-based attention along with a Transformer encoder model. The unsegmented continuous video dataset is jointly trained by balancing the Connectionist Temporal Classification (CTC) loss and the maximum-entropy loss. The proposed approach can capture better fine-grained attention in a single iteration. Experiment evaluations show that it outperforms the state-of-the-art approaches.

cs.CV↗

arXiv2021

Colonoscopy Polyp Detection and Classification: Dataset Creation and Comparative Evaluations

Colorectal cancer (CRC) is one of the most common types of cancer with a high mortality rate. Colonoscopy is the preferred procedure for CRC screening and has proven to be effective in reducing CRC mortality. Thus, a reliable computer-aided polyp detection and classification system can significantly increase the effectiveness of colonoscopy. In this paper, we create an endoscopic dataset collected from various sources and annotate the ground truth of polyp location and classification results with the help of experienced gastroenterologists. The dataset can serve as a benchmark platform to train and evaluate the machine learning models for polyp classification. We have also compared the performance of eight state-of-the-art deep learning-based object detection models. The results demonstrate that deep CNN models are promising in CRC screening. This work can serve as a baseline for future research in polyp detection and classification.

cs.CV↗

arXiv2021

Few-Shot Learning by Integrating Spatial and Frequency Representation

Human beings can recognize new objects with only a few labeled examples, however, few-shot learning remains a challenging problem for machine learning systems. Most previous algorithms in few-shot learning only utilize spatial information of the images. In this paper, we propose to integrate the frequency information into the learning model to boost the discrimination ability of the system. We employ Discrete Cosine Transformation (DCT) to generate the frequency representation, then, integrate the features from both the spatial domain and frequency domain for classification. The proposed strategy and its effectiveness are validated with different backbones, datasets, and algorithms. Extensive experiments demonstrate that the frequency information is complementary to the spatial representations in few-shot classification. The classification accuracy is boosted significantly by integrating features from both the spatial and frequency domains in different few-shot learning tasks.

cs.CV↗

arXiv2021

Six-channel Image Representation for Cross-domain Object Detection

Most deep learning models are data-driven and the excellent performance is highly dependent on the abundant and diverse datasets. However, it is very hard to obtain and label the datasets of some specific scenes or applications. If we train the detector using the data from one domain, it cannot perform well on the data from another domain due to domain shift, which is one of the big challenges of most object detection models. To address this issue, some image-to-image translation techniques have been employed to generate some fake data of some specific scenes to train the models. With the advent of Generative Adversarial Networks (GANs), we could realize unsupervised image-to-image translation in both directions from a source to a target domain and from the target to the source domain. In this study, we report a new approach to making use of the generated images. We propose to concatenate the original 3-channel images and their corresponding GAN-generated fake images to form 6-channel representations of the dataset, hoping to address the domain shift problem while exploiting the success of available detection models. The idea of augmented data representation may inspire further study on object detection and other applications.

cs.CV↗

arXiv2021

Dual Adaptivity: A Universal Algorithm for Minimizing the Adaptive Regret of Convex Functions

To deal with changing environments, a new performance measure -- adaptive regret, defined as the maximum static regret over any interval, was proposed in online learning. Under the setting of online convex optimization, several algorithms have been successfully developed to minimize the adaptive regret. However, existing algorithms lack universality in the sense that they can only handle one type of convex functions and need apriori knowledge of parameters. By contrast, there exist universal algorithms, such as MetaGrad, that attain optimal static regret for multiple types of convex functions simultaneously. Along this line of research, this paper presents the first universal algorithm for minimizing the adaptive regret of convex functions. Specifically, we borrow the idea of maintaining multiple learning rates in MetaGrad to handle the uncertainty of functions, and utilize the technique of sleeping experts to capture changing environments. In this way, our algorithm automatically adapts to the property of functions (convex, exponentially concave, or strongly convex), as well as the nature of environments (stationary or changing). As a by product, it also allows the type of functions to switch between rounds.

cs.LG↗

arXiv2021

Enhanced U-Net: A Feature Enhancement Network for Polyp Segmentation

Colonoscopy is a procedure to detect colorectal polyps which are the primary cause for developing colorectal cancer. However, polyp segmentation is a challenging task due to the diverse shape, size, color, and texture of polyps, shuttle difference between polyp and its background, as well as low contrast of the colonoscopic images. To address these challenges, we propose a feature enhancement network for accurate polyp segmentation in colonoscopy images. Specifically, the proposed network enhances the semantic information using the novel Semantic Feature Enhance Module (SFEM). Furthermore, instead of directly adding encoder features to the respective decoder layer, we introduce an Adaptive Global Context Module (AGCM), which focuses only on the encoder's significant and hard fine-grained features. The integration of these two modules improves the quality of features layer by layer, which in turn enhances the final feature representation. The proposed approach is evaluated on five colonoscopy datasets and demonstrates superior performance compared to other state-of-the-art models.

eess.IV↗

arXiv2021

SGNet: A Super-class Guided Network for Image Classification and Object Detection

Most classification models treat different object classes in parallel and the misclassifications between any two classes are treated equally. In contrast, human beings can exploit high-level information in making a prediction of an unknown object. Inspired by this observation, the paper proposes a super-class guided network (SGNet) to integrate the high-level semantic information into the network so as to increase its performance in inference. SGNet takes two-level class annotations that contain both super-class and finer class labels. The super-classes are higher-level semantic categories that consist of a certain amount of finer classes. A super-class branch (SCB), trained on super-class labels, is introduced to guide finer class prediction. At the inference time, we adopt two different strategies: Two-step inference (TSI) and direct inference (DI). TSI first predicts the super-class and then makes predictions of the corresponding finer class. On the other hand, DI directly generates predictions from the finer class branch (FCB). Extensive experiments have been performed on CIFAR-100 and MS COCO datasets. The experimental results validate the proposed approach and demonstrate its superior performance on image classification and object detection.

cs.CV↗

arXiv2021

Parallel Scale-wise Attention Network for Effective Scene Text Recognition

The paper proposes a new text recognition network for scene-text images. Many state-of-the-art methods employ the attention mechanism either in the text encoder or decoder for the text alignment. Although the encoder-based attention yields promising results, these schemes inherit noticeable limitations. They perform the feature extraction (FE) and visual attention (VA) sequentially, which bounds the attention mechanism to rely only on the FE final single-scale output. Moreover, the utilization of the attention process is limited by only applying it directly to the single scale feature-maps. To address these issues, we propose a new multi-scale and encoder-based attention network for text recognition that performs the multi-scale FE and VA in parallel. The multi-scale channels also undergo regular fusion with each other to develop the coordinated knowledge together. Quantitative evaluation and robustness analysis on the standard benchmarks demonstrate that the proposed network outperforms the state-of-the-art in most cases.

cs.CV↗

arXiv2021

Efficient Golf Ball Detection and Tracking Based on Convolutional Neural Networks and Kalman Filter

This paper focuses on the problem of online golf ball detection and tracking from image sequences. An efficient real-time approach is proposed by exploiting convolutional neural networks (CNN) based object detection and a Kalman filter based prediction. Five classical deep learning-based object detection networks are implemented and evaluated for ball detection, including YOLO v3 and its tiny version, YOLO v4, Faster R-CNN, SSD, and RefineDet. The detection is performed on small image patches instead of the entire image to increase the performance of small ball detection. At the tracking stage, a discrete Kalman filter is employed to predict the location of the ball and a small image patch is cropped based on the prediction. Then, the object detector is utilized to refine the location of the ball and update the parameters of Kalman filter. In order to train the detection models and test the tracking algorithm, a collection of golf ball dataset is created and annotated. Extensive comparative experiments are performed to demonstrate the effectiveness and superior tracking performance of the proposed scheme.

cs.CV↗

arXiv2021

Online Convex Optimization with Continuous Switching Constraint

In many sequential decision making applications, the change of decision would bring an additional cost, such as the wear-and-tear cost associated with changing server status. To control the switching cost, we introduce the problem of online convex optimization with continuous switching constraint, where the goal is to achieve a small regret given a budget on the \emph{overall} switching cost. We first investigate the hardness of the problem, and provide a lower bound of order $Ω(\sqrt{T})$ when the switching cost budget $S=Ω(\sqrt{T})$, and $Ω(\min\{\frac{T}{S},T\})$ when $S=O(\sqrt{T})$, where $T$ is the time horizon. The essential idea is to carefully design an adaptive adversary, who can adjust the loss function according to the cumulative switching cost of the player incurred so far based on the orthogonal technique. We then develop a simple gradient-based algorithm which enjoys the minimax optimal regret bound. Finally, we show that, for strongly convex functions, the regret bound can be improved to $O(\log T)$ for $S=Ω(\log T)$, and $O(\min\{T/\exp(S)+S,T\})$ for $S=O(\log T)$.

cs.LG↗

arXiv2021

Rainbow Pancyclicity in Graph Systems

Let $G_1,...,G_n$ be graphs on the same vertex set of size $n$, each graph with minimum degree $δ(G_i)\ge n/2$. A recent conjecture of Aharoni asserts that there exists a rainbow Hamiltonian cycle i.e. a cycle with edge set $\{e_1,...,e_n\}$ such that $e_i\in E(G_i)$ for $1\leq i \leq n$. This can be viewed as a rainbow version of the well-known Dirac theorem. In this paper, we prove this conjecture asymptotically by showing that for every $\varepsilon>0$, there exists an integer $N>0$, such that when $n>N$ for any graphs $G_1,...,G_n$ on the same vertex set of size $n$ with $δ(G_i)\ge (\frac{1}{2}+\varepsilon)n$, there exists a rainbow Hamiltonian cycle. Our main tool is the absorption technique. Additionally, we prove that with $δ(G_i)\geq \frac{n+1}{2}$ for each $i$, one can find rainbow cycles of length $3,...,n-1$.

math.CO↗

arXiv2021

Classification of Long Noncoding RNA Elements Using Deep Convolutional Neural Networks and Siamese Networks

In the last decade, the discovery of noncoding RNA(ncRNA) has exploded. Classifying these ncRNA is critical todetermining their function. This thesis proposes a new methodemploying deep convolutional neural networks (CNNs) to classifyncRNA sequences. To this end, this paper first proposes anefficient approach to convert the RNA sequences into imagescharacterizing their base-pairing probability. As a result, clas-sifying RNA sequences is converted to an image classificationproblem that can be efficiently solved by available CNN-basedclassification models. This research also considers the foldingpotential of the ncRNAs in addition to their primary sequence.Based on the proposed approach, a benchmark image classifi-cation dataset is generated from the RFAM database of ncRNAsequences. In addition, three classical CNN models and threeSiamese network models have been implemented and comparedto demonstrate the superior performance and efficiency of theproposed approach. Extensive experimental results show thegreat potential of using deep learning approaches for RNAclassification.

cs.CV↗