arXiv subjects

Guanghui Wang

Publications and source records attributed to Guanghui Wang.

At least 235 records · Page 13Linked to original sources

arXiv2019

Object Detection with Convolutional Neural Networks

In this chapter, we present a brief overview of the recent development in object detection using convolutional neural networks (CNN). Several classical CNN-based detectors are presented. Some developments are based on the detector architectures, while others are focused on solving certain problems, like model degradation and small-scale object detection. The chapter also presents some performance comparison results of different models on several benchmark datasets. Through the discussion of these models, we hope to give readers a general idea about the developments of CNN-based object detection.

cs.CV↗

arXiv2019

Unsupervised Deep Feature Transfer for Low Resolution Image Classification

In this paper, we propose a simple while effective unsupervised deep feature transfer algorithm for low resolution image classification. No fine-tuning on convenet filters is required in our method. We use pre-trained convenet to extract features for both high- and low-resolution images, and then feed them into a two-layer feature transfer network for knowledge transfer. A SVM classifier is learned directly using these transferred low resolution features. Our network can be embedded into the state-of-the-art deep neural networks as a plug-in feature enhancement module. It preserves data structures in feature space for high resolution images, and transfers the distinguishing features from a well-structured source domain (high resolution features space) to a not well-organized target domain (low resolution features space). Extensive experiments on VOC2007 test set show that the proposed method achieves significant improvements over the baseline of using feature extraction.

cs.CV↗

arXiv2019

Adaptively Denoising Proposal Collection for Weakly Supervised Object Localization

In this paper, we address the problem of weakly supervised object localization (WSL), which trains a detection network on the dataset with only image-level annotations. The proposed approach is built on the observation that the proposal set from the training dataset is a collection of background, object parts, and objects. Several strategies are taken to adaptively eliminate the noisy proposals and generate pseudo object-level annotations for the weakly labeled dataset. A multiple instance learning (MIL) algorithm enhanced by mask-out strategy is adopted to collect the class-specific object proposals, which are then utilized to adapt a pre-trained classification network to a detection network. In addition, the detection results from the detection network are re-weighted by jointly considering the detection scores and the overlap ratio of proposals in a proposal subset optimization framework. The optimal proposals work as object-level labels that enable a pseudo-strongly supervised dataset for training the detection network. Consequently, we establish a fully adaptive detection network. Extensive evaluations on the PASCAL VOC 2007 and 2012 datasets demonstrate a significant improvement compared with the state-of-the-art methods.

cs.CV↗

arXiv2019

Direct Visual-Inertial Odometry with Semi-Dense Mapping

The paper presents a direct visual-inertial odometry system. In particular, a tightly coupled nonlinear optimization based method is proposed by integrating the recent advances in direct dense tracking and Inertial Measurement Unit (IMU) pre-integration, and a factor graph optimization is adapted to estimate the pose of the camera and rebuild a semi-dense map. Two sliding windows are maintained in the proposed approach. The first one, based on Direct Sparse Odometry (DSO), is to estimate the depths of candidate points for mapping and dense visual tracking. In the second one, measurements from the IMU pre-integration and dense visual tracking are fused probabilistically using a tightly-coupled, optimization-based sensor fusion framework. As a result, the IMU pre-integration provides additional constraints to suppress the scale drift induced by the visual odometry. Evaluations on real-world benchmark datasets show that the proposed method achieves competitive results in indoor scenes.

cs.RO↗

arXiv2019

Stacked Wasserstein Autoencoder

Approximating distributions over complicated manifolds, such as natural images, are conceptually attractive. The deep latent variable model, trained using variational autoencoders and generative adversarial networks, is now a key technique for representation learning. However, it is difficult to unify these two models for exact latent-variable inference and parallelize both reconstruction and sampling, partly due to the regularization under the latent variables, to match a simple explicit prior distribution. These approaches are prone to be oversimplified, and can only characterize a few modes of the true distribution. Based on the recently proposed Wasserstein autoencoder (WAE) with a new regularization as an optimal transport. The paper proposes a stacked Wasserstein autoencoder (SWAE) to learn a deep latent variable model. SWAE is a hierarchical model, which relaxes the optimal transport constraints at two stages. At the first stage, the SWAE flexibly learns a representation distribution, i.e., the encoded prior; and at the second stage, the encoded representation distribution is approximated with a latent variable model under the regularization encouraging the latent distribution to match the explicit prior. This model allows us to generate natural textual outputs as well as perform manipulations in the latent space to induce changes in the output space. Both quantitative and qualitative results demonstrate the superior performance of SWAE compared with the state-of-the-art approaches in terms of faithful reconstruction and generation quality.

cs.CV↗

arXiv2019

Towards Learning Affine-Invariant Representations via Data-Efficient CNNs

In this paper we propose integrating a priori knowledge into both design and training of convolutional neural networks (CNNs) to learn object representations that are invariant to affine transformations (i.e., translation, scale, rotation). Accordingly we propose a novel multi-scale maxout CNN and train it end-to-end with a novel rotation-invariant regularizer. This regularizer aims to enforce the weights in each 2D spatial filter to approximate circular patterns. In this way, we manage to handle affine transformations in training using convolution, multi-scale maxout, and circular filters. Empirically we demonstrate that such knowledge can significantly improve the data-efficiency as well as generalization and robustness of learned models. For instance, on the Traffic Sign data set and trained with only 10 images per class, our method can achieve 84.15% that outperforms the state-of-the-art by 29.80% in terms of test accuracy.

cs.CV↗

arXiv2019

Multi-Objective Generalized Linear Bandits

In this paper, we study the multi-objective bandits (MOB) problem, where a learner repeatedly selects one arm to play and then receives a reward vector consisting of multiple objectives. MOB has found many real-world applications as varied as online recommendation and network routing. On the other hand, these applications typically contain contextual information that can guide the learning process which, however, is ignored by most of existing work. To utilize this information, we associate each arm with a context vector and assume the reward follows the generalized linear model (GLM). We adopt the notion of Pareto regret to evaluate the learner's performance and develop a novel algorithm for minimizing it. The essential idea is to apply a variant of the online Newton step to estimate model parameters, based on which we utilize the upper confidence bound (UCB) policy to construct an approximation of the Pareto front, and then uniformly at random choose one arm from the approximate Pareto front. Theoretical analysis shows that the proposed algorithm achieves an $\tilde O(d\sqrt{T})$ Pareto regret, where $T$ is the time horizon and $d$ is the dimension of contexts, which matches the optimal result for single objective contextual bandits problem. Numerical experiments demonstrate the effectiveness of our method.

cs.LG↗

arXiv2019

Toward Learning a Unified Many-to-Many Mapping for Diverse Image Translation

Image-to-image translation, which translates input images to a different domain with a learned one-to-one mapping, has achieved impressive success in recent years. The success of translation mainly relies on the network architecture to reserve the structural information while modify the appearance slightly at the pixel level through adversarial training. Although these networks are able to learn the mapping, the translated images are predictable without exclusion. It is more desirable to diversify them using image-to-image translation by introducing uncertainties, i.e., the generated images hold potential for variations in colors and textures in addition to the general similarity to the input images, and this happens in both the target and source domains. To this end, we propose a novel generative adversarial network (GAN) based model, InjectionGAN, to learn a many-to-many mapping. In this model, the input image is combined with latent variables, which comprise of domain-specific attribute and unspecific random variations. The domain-specific attribute indicates the target domain of the translation, while the unspecific random variations introduce uncertainty into the model. A unified framework is proposed to regroup these two parts and obtain diverse generations in each domain. Extensive experiments demonstrate that the diverse generations have high quality for the challenging image-to-image translation tasks where no pairing information of the training dataset exits. Both quantitative and qualitative results prove the superior performance of InjectionGAN over the state-of-the-art approaches.

cs.CV↗

arXiv2019

Adaptivity and Optimality: A Universal Algorithm for Online Convex Optimization

In this paper, we study adaptive online convex optimization, and aim to design a universal algorithm that achieves optimal regret bounds for multiple common types of loss functions. Existing universal methods are limited in the sense that they are optimal for only a subclass of loss functions. To address this limitation, we propose a novel online method, namely Maler, which enjoys the optimal $O(\sqrt{T})$, $O(d\log T)$ and $O(\log T)$ regret bounds for general convex, exponentially concave, and strongly convex functions respectively. The essential idea is to run multiple types of learning algorithms with different learning rates in parallel, and utilize a meta algorithm to track the best one on the fly. Empirical results demonstrate the effectiveness of our method.

cs.LG↗

arXiv2019

SAdam: A Variant of Adam for Strongly Convex Functions

The Adam algorithm has become extremely popular for large-scale machine learning. Under convexity condition, it has been proved to enjoy a data-dependant $O(\sqrt{T})$ regret bound where $T$ is the time horizon. However, whether strong convexity can be utilized to further improve the performance remains an open problem. In this paper, we give an affirmative answer by developing a variant of Adam (referred to as SAdam) which achieves a data-dependant $O(\log T)$ regret bound for strongly convex functions. The essential idea is to maintain a faster decaying yet under controlled step size for exploiting strong convexity. In addition, under a special configuration of hyperparameters, our SAdam reduces to SC-RMSprop, a recently proposed variant of RMSprop for strongly convex functions, for which we provide the first data-dependent logarithmic regret bound. Empirical results on optimizing strongly convex functions and training deep networks demonstrate the effectiveness of our method.

cs.LG↗

arXiv2019

Adversarially Approximated Autoencoder for Image Generation and Manipulation

Regularized autoencoders learn the latent codes, a structure with the regularization under the distribution, which enables them the capability to infer the latent codes given observations and generate new samples given the codes. However, they are sometimes ambiguous as they tend to produce reconstructions that are not necessarily faithful reproduction of the inputs. The main reason is to enforce the learned latent code distribution to match a prior distribution while the true distribution remains unknown. To improve the reconstruction quality and learn the latent space a manifold structure, this work present a novel approach using the adversarially approximated autoencoder (AAAE) to investigate the latent codes with adversarial approximation. Instead of regularizing the latent codes by penalizing on the distance between the distributions of the model and the target, AAAE learns the autoencoder flexibly and approximates the latent space with a simpler generator. The ratio is estimated using generative adversarial network (GAN) to enforce the similarity of the distributions. Additionally, the image space is regularized with an additional adversarial regularizer. The proposed approach unifies two deep generative models for both latent space inference and diverse generation. The learning scheme is realized without regularization on the latent codes, which also encourages faithful reconstruction. Extensive validation experiments on four real-world datasets demonstrate the superior performance of AAAE. In comparison to the state-of-the-art approaches, AAAE generates samples with better quality and shares the properties of regularized autoencoder with a nice latent manifold structure.

cs.LG↗

arXiv2018

Density of monochromatic infinite paths

For any subset $A \subseteq \mathbb{N}$, we define its upper density to be $\limsup_{ n \rightarrow \infty } |A \cap \{ 1, \dotsc, n \}| / n$. We prove that every $2$-edge-colouring of the complete graph on $\mathbb{N}$ contains a monochromatic infinite path, whose vertex set has upper density at least $(9 + \sqrt{17})/16 \approx 0.82019$. This improves on results of Erdős and Galvin, and of DeBiasio and McKenney.

math.CO↗

arXiv2018

Strong list-chromatic index of subcubic graphs

A strong $k$-edge-coloring of a graph G is an edge-coloring with $k$ colors in which every color class is an induced matching. The strong chromatic index of $G$, denoted by $χ'_{s}(G)$, is the minimum $k$ for which $G$ has a strong $k$-edge-coloring. In 1985, Erdős and Nešetřil conjectured that $χ'_{s}(G)\leq\frac{5}{4}Δ(G)^2$, where $Δ(G)$ is the maximum degree of $G$. When $G$ is a graph with maximum degree at most 3, the conjecture was verified independently by Andersen and Horák, Qing, and Trotter. In this paper, we consider the list version of strong edge-coloring. In particular, we show that every subcubic graph has strong list-chromatic index at most 11 and every planar subcubic graph has strong list-chromatic index at most 10.

math.CO↗

arXiv2018

MDCN: Multi-Scale, Deep Inception Convolutional Neural Networks for Efficient Object Detection

Object detection in challenging situations such as scale variation, occlusion, and truncation depends not only on feature details but also on contextual information. Most previous networks emphasize too much on detailed feature extraction through deeper and wider networks, which may enhance the accuracy of object detection to certain extent. However, the feature details are easily being changed or washed out after passing through complicated filtering structures. To better handle these challenges, the paper proposes a novel framework, multi-scale, deep inception convolutional neural network (MDCN), which focuses on wider and broader object regions by activating feature maps produced in the deep part of the network. Instead of incepting inner layers in the shallow part of the network, multi-scale inceptions are introduced in the deep layers. The proposed framework integrates the contextual information into the learning process through a single-shot network structure. It is computational efficient and avoids the hard training problem of previous macro feature extraction network designed for shallow layers. Extensive experiments demonstrate the effectiveness and superior performance of MDCN over the state-of-the-art models.

cs.CV↗

arXiv2018

An Efficient Approach for Polyps Detection in Endoscopic Videos Based on Faster R-CNN

Polyp has long been considered as one of the major etiologies to colorectal cancer which is a fatal disease around the world, thus early detection and recognition of polyps plays a crucial role in clinical routines. Accurate diagnoses of polyps through endoscopes operated by physicians becomes a challenging task not only due to the varying expertise of physicians, but also the inherent nature of endoscopic inspections. To facilitate this process, computer-aid techniques that emphasize fully-conventional image processing and novel machine learning enhanced approaches have been dedicatedly designed for polyp detection in endoscopic videos or images. Among all proposed algorithms, deep learning based methods take the lead in terms of multiple metrics in evolutions for algorithmic performance. In this work, a highly effective model, namely the faster region-based convolutional neural network (Faster R-CNN) is implemented for polyp detection. In comparison with the reported results of the state-of-the-art approaches on polyps detection, extensive experiments demonstrate that the Faster R-CNN achieves very competing results, and it is an efficient approach for clinical practice.

q-bio.TO↗

arXiv2018

Rainbow matchings in properly-colored hypergraphs

A hypergraph $H$ is properly colored if for every vertex $v\in V(H)$, all the edges incident to $v$ have distinct colors. In this paper, we show that if $H_{1}$, \cdots, $H_{s}$ are properly-colored $k$-uniform hypergraphs on $n$ vertices, where $n\geq3k^{2}s$, and $e(H_{i})>{{n}\choose {k}}-{{n-s+1}\choose {k}}$, then there exists a rainbow matching of size $s$, containing one edge from each $H_i$. This generalizes some previous results on the Erdős Matching Conjecture.

math.CO↗

arXiv2018

On splitting digraphs

In 1995, Stiebitz asked the following question: For any positive integers $s,t$, is there a finite integer $f(s,t)$ such that every digraph $D$ with minimum out-degree at least $f(s,t)$ admits a bipartition $(A, B)$ such that $A$ induces a subdigraph with minimum out-degree at least $s$ and $B$ induces a subdigraph with minimum out-degree at least $t$? We give an affirmative answer for tournaments, multipartite tournaments, and digraphs with bounded maximum in-degrees. In particular, we show that for every $ε$ with $0<ε<1/2$, there exists an integer $δ_0$ such that every tournament with minimum out-degree at least $δ_0$ admits a bisection $(A, B)$, so that each vertex has at least $(1/2-ε)$ of its out-neighbors in $A$, and in $B$ as well.

math.CO↗

arXiv2018

Learning Depth from Single Images with Deep Neural Network Embedding Focal Length

Learning depth from a single image, as an important issue in scene understanding, has attracted a lot of attention in the past decade. The accuracy of the depth estimation has been improved from conditional Markov random fields, non-parametric methods, to deep convolutional neural networks most recently. However, there exist inherent ambiguities in recovering 3D from a single 2D image. In this paper, we first prove the ambiguity between the focal length and monocular depth learning, and verify the result using experiments, showing that the focal length has a great influence on accurate depth recovery. In order to learn monocular depth by embedding the focal length, we propose a method to generate synthetic varying-focal-length dataset from fixed-focal-length datasets, and a simple and effective method is implemented to fill the holes in the newly generated images. For the sake of accurate depth recovery, we propose a novel deep neural network to infer depth through effectively fusing the middle-level information on the fixed-focal-length dataset, which outperforms the state-of-the-art methods built on pre-trained VGG. Furthermore, the newly generated varying-focal-length dataset is taken as input to the proposed network in both learning and inference phases. Extensive experiments on the fixed- and varying-focal-length datasets demonstrate that the learned monocular depth with embedded focal length is significantly improved compared to that without embedding the focal length information.

cs.CV↗