arXiv subjects

Yandong Guo

Publications and source records attributed to Yandong Guo.

At least 91 records · Page 5Linked to original sources

arXiv2022

Squeezed metallic droplet with tunable Kubo gap and charge injection in transition metal dichalcogenides

Shrinking the size of a bulk metal into nanoscale leads to the discreteness of electronic energy levels, the so-called Kubo gap. Renormalization of the electronic properties with a tunable and size-dependent Kubo gap renders fascinating photon emission and electron tunneling. In contrast with usual three-dimensional (3D) metal clusters, here we demonstrate that Kubo gap can be achieved with a two-dimensional (2D) metallic transition metal dichalcogenide (i.e., 1T'-phase MoTe2) nanocluster embedded in a semiconducting polymorph (i.e., 1H-phase MoTe2). Such a 1T'-1H MoTe2 nanodomain resembles a 3D metallic droplet squeezed in a 2D space which shows a strong polarization catastrophe while simultaneously maintains its bond integrity which is absent in traditional delta-gapped 3D clusters. The weak screening of the host 2D MoTe2 leads to photon emission of such pseudo-metallic systems and a ballistic injection of carriers in the 1T'-1H-1T' homojunctions which may find applications in sensors and 2D reconfigurable devices.

cond-mat.mtrl-sci↗

arXiv2022

Towards Communication-Efficient and Privacy-Preserving Federated Representation Learning

This paper investigates the feasibility of federated representation learning under the constraints of communication cost and privacy protection. Existing works either conduct annotation-guided local training which requires frequent communication or aggregates the client models via weight averaging which has potential risks of privacy exposure. To tackle the above problems, we first identify that self-supervised contrastive local training is robust against the non-identically distributed data, which provides the feasibility of longer local training and thus reduces the communication cost. Then based on the aforementioned robustness, we propose a novel Federated representation Learning framework with Ensemble Similarity Distillation~(FLESD) that utilizes this robustness. At each round of communication, the server first gathers a fraction of the clients' inferred similarity matrices on a public dataset. Then it ensembles the similarity matrices and train the global model via similarity distillation. We verify the effectiveness of FLESD by a series of empirical experiments and show that, despite stricter constraints, it achieves comparable results under multiple settings on multiple datasets.

cs.LG↗

arXiv2021

Simple and Robust Loss Design for Multi-Label Learning with Missing Labels

Multi-label learning in the presence of missing labels (MLML) is a challenging problem. Existing methods mainly focus on the design of network structures or training schemes, which increase the complexity of implementation. This work seeks to fulfill the potential of loss function in MLML without increasing the procedure and complexity. Toward this end, we propose two simple yet effective methods via robust loss design based on an observation that a model can identify missing labels during training with a high precision. The first is a novel robust loss for negatives, namely the Hill loss, which re-weights negatives in the shape of a hill to alleviate the effect of false negatives. The second is a self-paced loss correction (SPLC) method, which uses a loss derived from the maximum likelihood criterion under an approximate distribution of missing labels. Comprehensive experiments on a vast range of multi-label image classification datasets demonstrate that our methods can remarkably boost the performance of MLML and achieve new state-of-the-art loss functions in MLML.

cs.LG↗

arXiv2021

On the Efficacy of Small Self-Supervised Contrastive Models without Distillation Signals

It is a consensus that small models perform quite poorly under the paradigm of self-supervised contrastive learning. Existing methods usually adopt a large off-the-shelf model to transfer knowledge to the small one via distillation. Despite their effectiveness, distillation-based methods may not be suitable for some resource-restricted scenarios due to the huge computational expenses of deploying a large model. In this paper, we study the issue of training self-supervised small models without distillation signals. We first evaluate the representation spaces of the small models and make two non-negligible observations: (i) the small models can complete the pretext task without overfitting despite their limited capacity and (ii) they universally suffer the problem of over clustering. Then we verify multiple assumptions that are considered to alleviate the over-clustering phenomenon. Finally, we combine the validated techniques and improve the baseline performances of five small architectures with considerable margins, which indicates that training small self-supervised contrastive models is feasible even without distillation signals. The code is available at \textit{https://github.com/WOWNICE/ssl-small}.

cs.LG↗

arXiv2021

Virtual Multi-Modality Self-Supervised Foreground Matting for Human-Object Interaction

Most existing human matting algorithms tried to separate pure human-only foreground from the background. In this paper, we propose a Virtual Multi-modality Foreground Matting (VMFM) method to learn human-object interactive foreground (human and objects interacted with him or her) from a raw RGB image. The VMFM method requires no additional inputs, e.g. trimap or known background. We reformulate foreground matting as a self-supervised multi-modality problem: factor each input image into estimated depth map, segmentation mask, and interaction heatmap using three auto-encoders. In order to fully utilize the characteristics of each modality, we first train a dual encoder-to-decoder network to estimate the same alpha matte. Then we introduce a self-supervised method: Complementary Learning(CL) to predict deviation probability map and exchange reliable gradients across modalities without label. We conducted extensive experiments to analyze the effectiveness of each modality and the significance of different components in complementary learning. We demonstrate that our model outperforms the state-of-the-art methods.

cs.CV↗

arXiv2021

Deep Two-Stream Video Inference for Human Body Pose and Shape Estimation

Several video-based 3D pose and shape estimation algorithms have been proposed to resolve the temporal inconsistency of single-image-based methods. However it still remains challenging to have stable and accurate reconstruction. In this paper, we propose a new framework Deep Two-Stream Video Inference for Human Body Pose and Shape Estimation (DTS-VIBE), to generate 3D human pose and mesh from RGB videos. We reformulate the task as a multi-modality problem that fuses RGB and optical flow for more reliable estimation. In order to fully utilize both sensory modalities (RGB or optical flow), we train a two-stream temporal network based on transformer to predict SMPL parameters. The supplementary modality, optical flow, helps to maintain temporal consistency by leveraging motion knowledge between two consecutive frames. The proposed algorithm is extensively evaluated on the Human3.6 and 3DPW datasets. The experimental results show that it outperforms other state-of-the-art methods by a significant margin.

cs.CV↗

arXiv2021

The 2nd Anti-UAV Workshop & Challenge: Methods and Results

The 2nd Anti-UAV Workshop \& Challenge aims to encourage research in developing novel and accurate methods for multi-scale object tracking. The Anti-UAV dataset used for the Anti-UAV Challenge has been publicly released. There are two subsets in the dataset, $i.e.$, the test-dev subset and test-challenge subset. Both subsets consist of 140 thermal infrared video sequences, spanning multiple occurrences of multi-scale UAVs. Around 24 participating teams from the globe competed in the 2nd Anti-UAV Challenge. In this paper, we provide a brief summary of the 2nd Anti-UAV Workshop \& Challenge including brief introductions to the top three methods.The submission leaderboard will be reopened for researchers that are interested in the Anti-UAV challenge. The benchmark dataset and other information can be found at: https://anti-uav.github.io/.

cs.CV↗

arXiv2021

Retrieval and Localization with Observation Constraints

Accurate visual re-localization is very critical to many artificial intelligence applications, such as augmented reality, virtual reality, robotics and autonomous driving. To accomplish this task, we propose an integrated visual re-localization method called RLOCS by combining image retrieval, semantic consistency and geometry verification to achieve accurate estimations. The localization pipeline is designed as a coarse-to-fine paradigm. In the retrieval part, we cascade the architecture of ResNet101-GeM-ArcFace and employ DBSCAN followed by spatial verification to obtain a better initial coarse pose. We design a module called observation constraints, which combines geometry information and semantic consistency for filtering outliers. Comprehensive experiments are conducted on open datasets, including retrieval on R-Oxford5k and R-Paris6k, semantic segmentation on Cityscapes, localization on Aachen Day-Night and InLoc. By creatively modifying separate modules in the total pipeline, our method achieves many performance improvements on the challenging localization benchmarks.

cs.CV↗

arXiv2021

View-Guided Point Cloud Completion

This paper presents a view-guided solution for the task of point cloud completion. Unlike most existing methods directly inferring the missing points using shape priors, we address this task by introducing ViPC (view-guided point cloud completion) that takes the missing crucial global structure information from an extra single-view image. By leveraging a framework that sequentially performs effective cross-modality and cross-level fusions, our method achieves significantly superior results over typical existing solutions on a new large-scale dataset we collect for the view-guided point cloud completion task.

cs.CV↗

arXiv2020

Generator Pyramid for High-Resolution Image Inpainting

Inpainting high-resolution images with large holes challenges existing deep learning based image inpainting methods. We present a novel framework -- PyramidFill for high-resolution image inpainting task, which explicitly disentangles content completion and texture synthesis. PyramidFill attempts to complete the content of unknown regions in a lower-resolution image, and synthesis the textures of unknown regions in a higher-resolution image, progressively. Thus, our model consists of a pyramid of fully convolutional GANs, wherein the content GAN is responsible for completing contents in the lowest-resolution masked image, and each texture GAN is responsible for synthesizing textures in a higher-resolution image. Since completing contents and synthesising textures demand different abilities from generators, we customize different architectures for the content GAN and texture GAN. Experiments on multiple datasets including CelebA-HQ, Places2 and a new natural scenery dataset (NSHQ) with different resolutions demonstrate that PyramidFill generates higher-quality inpainting results than the state-of-the-art methods. To better assess high-resolution image inpainting methods, we will release NSHQ, high-quality natural scenery images with high-resolution 1920$\times$1080.

cs.CV↗

arXiv2020

Perceptual Extreme Super Resolution Network with Receptive Field Block

Perceptual Extreme Super-Resolution for single image is extremely difficult, because the texture details of different images vary greatly. To tackle this difficulty, we develop a super resolution network with receptive field block based on Enhanced SRGAN. We call our network RFB-ESRGAN. The key contributions are listed as follows. First, for the purpose of extracting multi-scale information and enhance the feature discriminability, we applied receptive field block (RFB) to super resolution. RFB has achieved competitive results in object detection and classification. Second, instead of using large convolution kernels in multi-scale receptive field block, several small kernels are used in RFB, which makes us be able to extract detailed features and reduce the computation complexity. Third, we alternately use different upsampling methods in the upsampling stage to reduce the high computation complexity and still remain satisfactory performance. Fourth, we use the ensemble of 10 models of different iteration to improve the robustness of model and reduce the noise introduced by each individual model. Our experimental results show the superior performance of RFB-ESRGAN. According to the preliminary results of NTIRE 2020 Perceptual Extreme Super-Resolution Challenge, our solution ranks first among all the participants.

eess.IV↗

arXiv2020

Visual Localization Using Semantic Segmentation and Depth Prediction

In this paper, we propose a monocular visual localization pipeline leveraging semantic and depth cues. We apply semantic consistency evaluation to rank the image retrieval results and a practical clustering technique to reject estimation outliers. In addition, we demonstrate a substantial performance boost achieved with a combination of multiple feature extractors. Furthermore, by using depth prediction with a deep neural network, we show that a significant amount of falsely matched keypoints are identified and eliminated. The proposed pipeline outperforms most of the existing approaches at the Long-Term Visual Localization benchmark 2020.

cs.CV↗

arXiv2020

Discriminative Multi-modality Speech Recognition

Vision is often used as a complementary modality for audio speech recognition (ASR), especially in the noisy environment where performance of solo audio modality significantly deteriorates. After combining visual modality, ASR is upgraded to the multi-modality speech recognition (MSR). In this paper, we propose a two-stage speech recognition model. In the first stage, the target voice is separated from background noises with help from the corresponding visual information of lip movements, making the model 'listen' clearly. At the second stage, the audio modality combines visual modality again to better understand the speech by a MSR sub-network, further improving the recognition rate. There are some other key contributions: we introduce a pseudo-3D residual convolution (P3D)-based visual front-end to extract more discriminative features; we upgrade the temporal convolution block from 1D ResNet with the temporal convolutional network (TCN), which is more suitable for the temporal tasks; the MSR sub-network is built on the top of Element-wise-Attention Gated Recurrent Unit (EleAtt-GRU), which is more effective than Transformer in long sequences. We conducted extensive experiments on the LRS3-TED and the LRW datasets. Our two-stage model (audio enhanced multi-modality speech recognition, AE-MSR) consistently achieves the state-of-the-art performance by a significant margin, which demonstrates the necessity and effectiveness of AE-MSR.

cs.CV↗

arXiv2020

NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results

This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results. The challenge task was to super-resolve an input image with a magnification factor 16 based on a set of prior examples of low and corresponding high resolution images. The goal is to obtain a network design capable to produce high resolution results with the best perceptual quality and similar to the ground truth. The track had 280 registered participants, and 19 teams submitted the final results. They gauge the state-of-the-art in single image super-resolution.

eess.IV↗

arXiv2020

To See in the Dark: N2DGAN for Background Modeling in Nighttime Scene

Due to the deteriorated conditions of \mbox{illumination} lack and uneven lighting, nighttime images have lower contrast and higher noise than their daytime counterparts of the same scene, which limits seriously the performances of conventional background modeling methods. For such a challenging problem of background modeling under nighttime scene, an innovative and reasonable solution is proposed in this paper, which paves a new way completely different from the existing ones. To make background modeling under nighttime scene performs as well as in daytime condition, we put forward a promising generation-based background modeling framework for foreground surveillance. With a pre-specified daytime reference image as background frame, the {\bfseries GAN} based generation model, called {\bfseries N2DGAN}, is trained to transfer each frame of {\bfseries n}ighttime video {\bfseries to} a virtual {\bfseries d}aytime image with the same scene to the reference image except for the foreground region. Specifically, to balance the preservation of background scene and the foreground object(s) in generating the virtual daytime image, we present a two-pathway generation model, in which the global and local sub-networks are well combined with spatial and temporal consistency constraints. For the sequence of generated virtual daytime images, a multi-scale Bayes model is further proposed to characterize pertinently the temporal variation of background. We evaluate on collected datasets with manually labeled ground truth, which provides a valuable resource for related research community. The impressive results illustrated in both the main paper and supplementary show efficacy of our proposed approach.

cs.CV↗

arXiv2020

Learning to Detect Head Movement in Unconstrained Remote Gaze Estimation in the Wild

Unconstrained remote gaze estimation remains challenging mostly due to its vulnerability to the large variability in head-pose. Prior solutions struggle to maintain reliable accuracy in unconstrained remote gaze tracking. Among them, appearance-based solutions demonstrate tremendous potential in improving gaze accuracy. However, existing works still suffer from head movement and are not robust enough to handle real-world scenarios. Especially most of them study gaze estimation under controlled scenarios where the collected datasets often cover limited ranges of both head-pose and gaze which introduces further bias. In this paper, we propose novel end-to-end appearance-based gaze estimation methods that could more robustly incorporate different levels of head-pose representations into gaze estimation. Our method could generalize to real-world scenarios with low image quality, different lightings and scenarios where direct head-pose information is not available. To better demonstrate the advantage of our methods, we further propose a new benchmark dataset with the most rich distribution of head-gaze combination reflecting real-world scenarios. Extensive evaluations on several public datasets and our own dataset demonstrate that our method consistently outperforms the state-of-the-art by a significant margin.

cs.CV↗

arXiv2019

Dually Supervised Feature Pyramid for Object Detection and Segmentation

Feature pyramid architecture has been broadly adopted in object detection and segmentation to deal with multi-scale problem. However, in this paper we show that the capacity of the architecture has not been fully explored due to the inadequate utilization of the supervision information. Such insufficient utilization is caused by the supervision signal degradation in back propagation. Thus inspired, we propose a dually supervised method, named dually supervised FPN (DSFPN), to enhance the supervision signal when training the feature pyramid network (FPN). In particular, DSFPN is constructed by attaching extra prediction (i.e., detection or segmentation) heads to the bottom-up subnet of FPN. Hence, the features can be optimized by the additional heads before being forwarded to subsequent networks. Further, the auxiliary heads can serve as a regularization term to facilitate the model training. In addition, to strengthen the capability of the detection heads in DSFPN for handling two inhomogeneous tasks, i.e., classification and regression, the originally shared hidden feature space is separated by decoupling classification and regression subnets. To demonstrate the generalizability, effectiveness, and efficiency of the proposed method, DSFPN is integrated into four representative detectors (Faster RCNN, Mask RCNN, Cascade RCNN, and Cascade Mask RCNN) and assessed on the MS COCO dataset. Promising precision improvement, state-of-the-art performance, and negligible additional computational cost are demonstrated through extensive experiments. Code will be provided.

cs.CV↗

arXiv2019

Generative One-Shot Face Recognition

One-shot face recognition measures the ability to identify persons with only seeing them at one glance, and is a hallmark of human visual intelligence. It is challenging for conventional machine learning approaches to mimic this way, since limited data are hard to effectively represent the data variance. The goal of one-shot face recognition is to learn a large-scale face recognizer, which is capable to fight off the data imbalance challenge. In this paper, we propose a novel generative adversarial one-shot face recognizer, attempting to synthesize meaningful data for one-shot classes by adapting the data variances from other normal classes. Specifically, we target at building a more effective general face classifier for both normal persons and one-shot persons. Technically, we design a new loss function by formulating knowledge transfer generator and a general classifier into a unified framework. Such a two-player minimax optimization can guide the generation of more effective data, which effectively promote the underrepresented classes in the learned model and lead to a remarkable improvement in face recognition performance. We evaluate our proposed model on the MS-Celeb-1M one-shot learning benchmark task, where we could recognize 94.98% of the test images at the precision of 99% for the one-shot classes, keeping an overall Top1 accuracy at $99.80\%$ for the normal classes. To the best of our knowledge, this is the best performance among all the published methods using this benchmark task with the same setup, including all the participants in the recent MS-Celeb-1M challenge at ICCV 2017\footnote{http://www.msceleb.org/challenge2/2017}.

cs.CV↗