arXiv subjects

Yi Yang

Publications and source records attributed to Yi Yang.

At least 811 records · Page 45Linked to original sources

arXiv2022

Bridging the Source-to-target Gap for Cross-domain Person Re-Identification with Intermediate Domains

Cross-domain person re-identification (re-ID), such as unsupervised domain adaptive (UDA) re-ID, aims to transfer the identity-discriminative knowledge from the source to the target domain. Existing methods commonly consider the source and target domains are isolated from each other, i.e., no intermediate status is modeled between both domains. Directly transferring the knowledge between two isolated domains can be very difficult, especially when the domain gap is large. From a novel perspective, we assume these two domains are not completely isolated, but can be connected through intermediate domains. Instead of directly aligning the source and target domains against each other, we propose to align the source and target domains against their intermediate domains for a smooth knowledge transfer. To discover and utilize these intermediate domains, we propose an Intermediate Domain Module (IDM) and a Mirrors Generation Module (MGM). IDM has two functions: 1) it generates multiple intermediate domains by mixing the hidden-layer features from source and target domains and 2) it dynamically reduces the domain gap between the source / target domain features and the intermediate domain features. While IDM achieves good domain alignment, it introduces a side effect, i.e., the mix-up operation may mix the identities into a new identity and lose the original identities. To compensate this, MGM is introduced by mapping the features into the IDM-generated intermediate domains without changing their original identity. It allows to focus on minimizing domain variations to promote the alignment between the source / target domain and intermediate domains, which reinforces IDM into IDM++. We extensively evaluate our method under both the UDA and domain generalization (DG) scenarios and observe that IDM++ yields consistent performance improvement for cross-domain re-ID, achieving new state of the art.

cs.CV↗

arXiv2022

Filter Pruning by Switching to Neighboring CNNs with Good Attributes

Filter pruning is effective to reduce the computational costs of neural networks. Existing methods show that updating the previous pruned filter would enable large model capacity and achieve better performance. However, during the iterative pruning process, even if the network weights are updated to new values, the pruning criterion remains the same. In addition, when evaluating the filter importance, only the magnitude information of the filters is considered. However, in neural networks, filters do not work individually, but they would affect other filters. As a result, the magnitude information of each filter, which merely reflects the information of an individual filter itself, is not enough to judge the filter importance. To solve the above problems, we propose Meta-attribute-based Filter Pruning (MFP). First, to expand the existing magnitude information based pruning criteria, we introduce a new set of criteria to consider the geometric distance of filters. Additionally, to explicitly assess the current state of the network, we adaptively select the most suitable criteria for pruning via a meta-attribute, a property of the neural network at the current state. Experiments on two image classification benchmarks validate our method. For ResNet-50 on ILSVRC-2012, we could reduce more than 50% FLOPs with only 0.44% top-5 accuracy loss.

cs.CV↗

arXiv2022

Compact Scintillator Array Detector (ComSAD) for sounding rocket and CubeSat missions

The development of CubeSat and more frequent launch chances of sounding rockets are a total game changer to the space program, and it allows us to build space instruments to be more achievable and affordable. Therefore, it gives us a good opportunity to build a small cosmic ray detector which has capabilities to measure the flux, direction, and even energy of cosmic rays at the height above the limitation of balloon experiments, and it may open a new door for building a constellation of detectors to study cosmic ray physics. Compact Scintillator Array Detector (ComSAD) is dedicated for the sounding rocket mission of Taiwan's National Space Organization. In paper, we present the idea, design, and performance of ComSAD which is also suitable for CubeSat missions in the future.

physics.ins-det↗

arXiv2022

Results and findings of the 2021 Image Similarity Challenge

The 2021 Image Similarity Challenge introduced a dataset to serve as a new benchmark to evaluate recent image copy detection methods. There were 200 participants to the competition. This paper presents a quantitative and qualitative analysis of the top submissions. It appears that the most difficult image transformations involve either severe image crops or hiding into unrelated images, combined with local pixel perturbations. The key algorithmic elements in the winning submissions are: training on strong augmentations, self-supervised learning, score normalization, explicit overlay detection, and global descriptor matching followed by pairwise image comparison.

cs.CV↗

arXiv2022

Single-stream CNN with Learnable Architecture for Multi-source Remote Sensing Data

In this paper, we propose an efficient and generalizable framework based on deep convolutional neural network (CNN) for multi-source remote sensing data joint classification. While recent methods are mostly based on multi-stream architectures, we use group convolution to construct equivalent network architectures efficiently within a single-stream network. We further adopt and improve dynamic grouping convolution (DGConv) to make group convolution hyperparameters, and thus the overall network architecture, learnable during network training. The proposed method therefore can theoretically adjust any modern CNN models to any multi-source remote sensing data set, and can potentially avoid sub-optimal solutions caused by manually decided architecture hyperparameters. In the experiments, the proposed method is applied to ResNet and UNet, and the adjusted networks are verified on three very diverse benchmark data sets (i.e., Houston2018 data, Berlin data, and MUUFL data). Experimental results demonstrate the effectiveness of the proposed single-stream CNNs, and in particular ResNet18-DGConv improves the state-of-the-art classification overall accuracy (OA) on HS-SAR Berlin data set from $62.23\%$ to $68.21\%$. In the experiments we have two interesting findings. First, using DGConv generally reduces test OA variance. Second, multi-stream is harmful to model performance if imposed to the first few layers, but becomes beneficial if applied to deeper layers. Altogether, the findings imply that multi-stream architecture, instead of being a strictly necessary component in deep learning models for multi-source remote sensing data, essentially plays the role of model regularizer. Our code is publicly available at https://github.com/yyyyangyi/Multi-source-RS-DGConv. We hope our work can inspire novel research in the future.

cs.CV↗

arXiv2022

COVID-19 Detection Using CT Image Based On YOLOv5 Network

Computer aided diagnosis (CAD) increases diagnosis efficiency, helping doctors providing a quick and confident diagnosis, it has played an important role in the treatment of COVID19. In our task, we solve the problem about abnormality detection and classification. The dataset provided by Kaggle platform and we choose YOLOv5 as our model. We introduce some methods on objective detection in the related work section, the objection detection can be divided into two streams: onestage and two stage. The representational model are Faster RCNN and YOLO series. Then we describe the YOLOv5 model in the detail. Compared Experiments and results are shown in section IV. We choose mean average precision (mAP) as our experiments' metrics, and the higher (mean) mAP is, the better result the model will gain. mAP@0.5 of our YOLOv5s is 0.623 which is 0.157 and 0.101 higher than Faster RCNN and EfficientDet respectively.

eess.IV↗

arXiv2022

Action Keypoint Network for Efficient Video Recognition

Reducing redundancy is crucial for improving the efficiency of video recognition models. An effective approach is to select informative content from the holistic video, yielding a popular family of dynamic video recognition methods. However, existing dynamic methods focus on either temporal or spatial selection independently while neglecting a reality that the redundancies are usually spatial and temporal, simultaneously. Moreover, their selected content is usually cropped with fixed shapes, while the realistic distribution of informative content can be much more diverse. With these two insights, this paper proposes to integrate temporal and spatial selection into an Action Keypoint Network (AK-Net). From different frames and positions, AK-Net selects some informative points scattered in arbitrary-shaped regions as a set of action keypoints and then transforms the video recognition into point cloud classification. AK-Net has two steps, i.e., the keypoint selection and the point cloud classification. First, it inputs the video into a baseline network and outputs a feature map from an intermediate layer. We view each pixel on this feature map as a spatial-temporal point and select some informative keypoints using self-attention. Second, AK-Net devises a ranking criterion to arrange the keypoints into an ordered 1D sequence. Consequentially, AK-Net brings two-fold benefits for efficiency: The keypoint selection step collects informative content within arbitrary shapes and increases the efficiency for modeling spatial-temporal dependencies, while the point cloud classification step further reduces the computational cost by compacting the convolutional kernels. Experimental results show that AK-Net can consistently improve the efficiency and performance of baseline methods on several video recognition benchmarks.

cs.CV↗

arXiv2022

Active Learning for Deep Visual Tracking

Convolutional neural networks (CNNs) have been successfully applied to the single target tracking task in recent years. Generally, training a deep CNN model requires numerous labeled training samples, and the number and quality of these samples directly affect the representational capability of the trained model. However, this approach is restrictive in practice, because manually labeling such a large number of training samples is time-consuming and prohibitively expensive. In this paper, we propose an active learning method for deep visual tracking, which selects and annotates the unlabeled samples to train the deep CNNs model. Under the guidance of active learning, the tracker based on the trained deep CNNs model can achieve competitive tracking performance while reducing the labeling cost. More specifically, to ensure the diversity of selected samples, we propose an active learning method based on multi-frame collaboration to select those training samples that should be and need to be annotated. Meanwhile, considering the representativeness of these selected samples, we adopt a nearest neighbor discrimination method based on the average nearest neighbor distance to screen isolated samples and low-quality samples. Therefore, the training samples subset selected based on our method requires only a given budget to maintain the diversity and representativeness of the entire sample set. Furthermore, we adopt a Tversky loss to improve the bounding box estimation of our tracker, which can ensure that the tracker achieves more accurate target states. Extensive experimental results confirm that our active learning-based tracker (ALT) achieves competitive tracking accuracy and speed compared with state-of-the-art trackers on the seven most challenging evaluation benchmarks.

cs.CV↗

arXiv2022

Computational discovery of spin-polarized semimetals in spinel materials

The materials with spin-polarized electronic states have attracted a huge amount of interest due to their potential applications in spintronics. Based on first-principles calculations, we study the electronic characteristics of a series of AB2X4 chalcogeniden spinel structures and propose two promising candidates, VZn2O4 and VCd2S4, are spin-polarized semimetal materials. Both of them have ferromagnetic ground states. Their bands near the Fermi level are completely spin-polarized and form two types of nodal rings in the spin-up channel, and the large gaps in the spin-down channel prevent the spin-flip. Further symmetry analysis reveals that the nodal rings are protected by the glide mirror or mirror symmetries. Significantly, these nodal rings connect with each other and form a nodal chain structure, which can be well described by a simple four-band tight-binding (TB) model. The two ternary chalcogeniden spinel materials with a fully spin polarized nodal chain can serve as a prominent platform in the future applications of spintronic.

cond-mat.mtrl-sci↗

arXiv2022

The Type Icn SN 2021csp: Implications for the Origins of the Fastest Supernovae and the Fates of Wolf-Rayet Stars

We present observations of SN 2021csp, the second example of a newly-identified type of supernova (Type Icn) hallmarked by strong, narrow, P Cygni carbon features at early times. The SN appears as a fast and luminous blue transient at early times, reaching a peak absolute magnitude of -20 within 3 days due to strong interaction between fast SN ejecta (v ~ 30000 km/s) and a massive, dense, fast-moving C/O wind shed by the WC-like progenitor months before explosion. The narrow line features disappear from the spectrum 10-20 days after explosion and are replaced by a blue continuum dominated by broad Fe features, reminiscent of Type Ibn and IIn supernovae and indicative of weaker interaction with more extended H/He-poor material. The transient then abruptly fades ~60 days post-explosion when interaction ceases. Deep limits at later phases suggest minimal heavy-element nucleosynthesis, a low ejecta mass, or both, and imply an origin distinct from that of classical Type Ic supernovae. We place SN 2021csp in context with other fast-evolving interacting transients, and discuss various progenitor scenarios: an ultrastripped progenitor star, a pulsational pair-instability eruption, or a jet-driven fallback supernova from a Wolf-Rayet star. The fallback scenario would naturally explain the similarity between these events and radio-loud fast transients, and suggests a picture in which most stars massive enough to undergo a WR phase collapse directly to black holes at the end of their lives.

astro-ph.HE↗

arXiv2022

Boosting RGB-D Saliency Detection by Leveraging Unlabeled RGB Images

Training deep models for RGB-D salient object detection (SOD) often requires a large number of labeled RGB-D images. However, RGB-D data is not easily acquired, which limits the development of RGB-D SOD techniques. To alleviate this issue, we present a Dual-Semi RGB-D Salient Object Detection Network (DS-Net) to leverage unlabeled RGB images for boosting RGB-D saliency detection. We first devise a depth decoupling convolutional neural network (DDCNN), which contains a depth estimation branch and a saliency detection branch. The depth estimation branch is trained with RGB-D images and then used to estimate the pseudo depth maps for all unlabeled RGB images to form the paired data. The saliency detection branch is used to fuse the RGB feature and depth feature to predict the RGB-D saliency. Then, the whole DDCNN is assigned as the backbone in a teacher-student framework for semi-supervised learning. Moreover, we also introduce a consistency loss on the intermediate attention and saliency maps for the unlabeled data, as well as a supervised depth and saliency loss for labeled data. Experimental results on seven widely-used benchmark datasets demonstrate that our DDCNN outperforms state-of-the-art methods both quantitatively and qualitatively. We also demonstrate that our semi-supervised DS-Net can further improve the performance, even when using an RGB image with the pseudo depth map.

eess.IV↗

arXiv2021

Doubly Robust Adaptive LASSO for Effect Modifier Discovery

Effect modification occurs when the effect of the treatment on an outcome differs according to the level of a third variable (the effect modifier, EM). A natural way to assess effect modification is by subgroup analysis or include the interaction terms between the treatment and the covariates in an outcome regression. The latter, however, does not target a parameter of a marginal structural model (MSM) unless a correctly specified outcome model is specified. Our aim is to develop a data-adaptive method to select effect modifying variables in an MSM with a single time point exposure. A two-stage procedure is proposed. First, we estimate the conditional outcome expectation and propensity score and plug these into a doubly robust loss function. Second, we use the adaptive LASSO to select the EMs and estimate MSM coefficients. Post-selection inference is then used to obtain coverage on the selected EMs. Simulations studies are performed in order to verify the performance of the proposed methods.

stat.ME↗

arXiv2021

Omni-supervised Facial Expression Recognition via Distilled Data

Facial expression plays an important role in understanding human emotions. Most recently, deep learning based methods have shown promising for facial expression recognition. However, the performance of the current state-of-the-art facial expression recognition (FER) approaches is directly related to the labeled data for training. To solve this issue, prior works employ the pretrain-and-finetune strategy, i.e., utilize a large amount of unlabeled data to pretrain the network and then finetune it by the labeled data. As the labeled data is in a small amount, the final network performance is still restricted. From a different perspective, we propose to perform omni-supervised learning to directly exploit reliable samples in a large amount of unlabeled data for network training. Particularly, a new dataset is firstly constructed using a primitive model trained on a small number of labeled samples to select samples with high confidence scores from a face dataset, i.e., MS-Celeb-1M, based on feature-wise similarity. We experimentally verify that the new dataset created in such an omni-supervised manner can significantly improve the generalization ability of the learned FER model. However, as the number of training samples grows, computational cost and training time increase dramatically. To tackle this, we propose to apply a dataset distillation strategy to compress the created dataset into several informative class-wise images, significantly improving the training efficiency. We have conducted extensive experiments on widely used benchmarks, where consistent performance gains can be achieved under various settings using the proposed framework. More importantly, the distilled dataset has shown its capabilities of boosting the performance of FER with negligible additional computational costs.

cs.CV↗

arXiv2021

D$^2$LV: A Data-Driven and Local-Verification Approach for Image Copy Detection

Image copy detection is of great importance in real-life social media. In this paper, a data-driven and local-verification (D$^2$LV) approach is proposed to compete for Image Similarity Challenge: Matching Track at NeurIPS'21. In D$^2$LV, unsupervised pre-training substitutes the commonly-used supervised one. When training, we design a set of basic and six advanced transformations, and a simple but effective baseline learns robust representation. During testing, a global-local and local-global matching strategy is proposed. The strategy performs local-verification between reference and query images. Experiments demonstrate that the proposed method is effective. The proposed approach ranks first out of 1,103 participants on the Facebook AI Image Similarity Challenge: Matching Track. The code and trained models are available at https://github.com/WangWenhao0716/ISC-Track1-Submission.

cs.CV↗

arXiv2021

Bag of Tricks and A Strong baseline for Image Copy Detection

Image copy detection is of great importance in real-life social media. In this paper, a bag of tricks and a strong baseline are proposed for image copy detection. Unsupervised pre-training substitutes the commonly-used supervised one. Beyond that, we design a descriptor stretching strategy to stabilize the scores of different queries. Experiments demonstrate that the proposed method is effective. The proposed baseline ranks third out of 526 participants on the Facebook AI Image Similarity Challenge: Descriptor Track. The code and trained models are available at https://github.com/WangWenhao0716/ISC-Track2-Submission.

cs.CV↗

arXiv2021

SemGloVe: Semantic Co-occurrences for GloVe from BERT

GloVe learns word embeddings by leveraging statistical information from word co-occurrence matrices. However, word pairs in the matrices are extracted from a predefined local context window, which might lead to limited word pairs and potentially semantic irrelevant word pairs. In this paper, we propose SemGloVe, which distills semantic co-occurrences from BERT into static GloVe word embeddings. Particularly, we propose two models to extract co-occurrence statistics based on either the masked language model or the multi-head attention weights of BERT. Our methods can extract word pairs without limiting by the local window assumption and can define the co-occurrence weights by directly considering the semantic distance between word pairs. Experiments on several word similarity datasets and four external tasks show that SemGloVe can outperform GloVe.

cs.CL↗

arXiv2021

An imaging polarimetry survey of Type Ia supernovae: are peculiar extinction and polarization properties produced by circumstellar or interstellar matter?

Some highly reddened Type Ia supernovae (SNe Ia) display low total-to-selective extinction ratios ($R_V \lesssim 2$) in comparison to that of typical Milky Way dust ($R_V \approx 3.3$), and polarization curves that rise steeply to blue wavelengths, with peak polarization values at short wavelengths ($λ_{\rm max} < 0.4$ $μ$m) in comparison to the typical Galactic values ($λ_{\rm max} \approx 0.55$ $μ$m). Understanding the source of these properties could provide insight into the progenitor systems of SNe Ia. We aim to determine whether they are the result of the host galaxy's interstellar dust or circumstellar dust. This is accomplished by analysing the continuum polarization of 66 SNe Ia in dust-rich spiral galaxies and 13 SNe Ia in dust-poor elliptical galaxies as a function of normalised galactocentric distance. We find that there is a general trend of SNe Ia in spiral galaxies displaying increased polarization values when located closer to the host galaxies' centre, while SNe Ia in elliptical host galaxies display low polarization. Furthermore, all highly polarized SNe Ia in spiral host galaxies display polarization curves rising toward blue wavelengths, while no evidence of such polarization properties is shown in elliptical host galaxies. This indicates that the source of the peculiar polarization curves is likely the result of interstellar material as opposed to circumstellar material. The peculiar polarization and extinction properties observed toward some SNe Ia may be explained by the radiative torque disruption mechanism induced by the SN or the interstellar radiation field.

astro-ph.GA↗

arXiv2021

Ringing of a black hole in a dark matter halo

Recently, we obtained the simple metrics of a spherically symmetric black hole in a dark matter halo, and extended to the case of rotation. As the characteristic sound of black holes, quasinormal modes (QNMs) are one of the important means to understand black holes currently. Based on these two metrics of a spherically symmetric black hole, we study the QNMs of cold dark matter (CDM) and scalar field dark matter (SFDM) models using the methods of the material field perturbations and the gravitational perturbation, and make comparisons with the Schwarzschild black hole. Our results show that black hole QNMs of CDM and SFDM in a dark matter halo are different from the Schwarzschild black hole, unlike a Schwarzschild black hole with a prominent power-law tail. The different kinds models of dark matter can be distinguished by their QNMs. The time of QNMs ringing and frequencies increase with increasing parameter $l$. The overall QNMs of CDM are stronger than that of SFDM in the same condition, which is easier to be detected. In addition, QNMs frequencies using the sixth-order WKB method and the Prony method are in good agreement.

gr-qc↗