arXiv subjects

Chen Li

Publications and source records attributed to Chen Li.

At least 361 records · Page 20Linked to original sources

arXiv2023

ScarceNet: Animal Pose Estimation with Scarce Annotations

Animal pose estimation is an important but under-explored task due to the lack of labeled data. In this paper, we tackle the task of animal pose estimation with scarce annotations, where only a small set of labeled data and unlabeled images are available. At the core of the solution to this problem setting is the use of the unlabeled data to compensate for the lack of well-labeled animal pose data. To this end, we propose the ScarceNet, a pseudo label-based approach to generate artificial labels for the unlabeled images. The pseudo labels, which are generated with a model trained with the small set of labeled images, are generally noisy and can hurt the performance when directly used for training. To solve this problem, we first use a small-loss trick to select reliable pseudo labels. Although effective, the selection process is improvident since numerous high-loss samples are left unused. We further propose to identify reusable samples from the high-loss samples based on an agreement check. Pseudo labels are re-generated to provide supervision for those reusable samples. Lastly, we introduce a student-teacher framework to enforce a consistency constraint since there are still samples that are neither reliable nor reusable. By combining the reliable pseudo label selection with the reusable sample re-labeling and the consistency constraint, we can make full use of the unlabeled data. We evaluate our approach on the challenging AP-10K dataset, where our approach outperforms existing semi-supervised approaches by a large margin. We also test on the TigDog dataset, where our approach can achieve better performance than domain adaptation based approaches when only very few annotations are available. Our code is available at the project website.

cs.CV↗

arXiv2023

NeRF-DS: Neural Radiance Fields for Dynamic Specular Objects

Dynamic Neural Radiance Field (NeRF) is a powerful algorithm capable of rendering photo-realistic novel view images from a monocular RGB video of a dynamic scene. Although it warps moving points across frames from the observation spaces to a common canonical space for rendering, dynamic NeRF does not model the change of the reflected color during the warping. As a result, this approach often fails drastically on challenging specular objects in motion. We address this limitation by reformulating the neural radiance field function to be conditioned on surface position and orientation in the observation space. This allows the specular surface at different poses to keep the different reflected colors when mapped to the common canonical space. Additionally, we add the mask of moving objects to guide the deformation field. As the specular surface changes color during motion, the mask mitigates the problem of failure to find temporal correspondences with only RGB supervision. We evaluate our model based on the novel view synthesis quality with a self-collected dataset of different moving specular objects in realistic environments. The experimental results demonstrate that our method significantly improves the reconstruction quality of moving specular objects from monocular RGB videos compared to the existing NeRF models. Our code and data are available at the project website https://github.com/JokerYan/NeRF-DS.

cs.CV↗

arXiv2023

Distribution-restrained Softmax Loss for the Model Robustness

Recently, the robustness of deep learning models has received widespread attention, and various methods for improving model robustness have been proposed, including adversarial training, model architecture modification, design of loss functions, certified defenses, and so on. However, the principle of the robustness to attacks is still not fully understood, also the related research is still not sufficient. Here, we have identified a significant factor that affects the robustness of models: the distribution characteristics of softmax values for non-real label samples. We found that the results after an attack are highly correlated with the distribution characteristics, and thus we proposed a loss function to suppress the distribution diversity of softmax. A large number of experiments have shown that our method can improve robustness without significant time consumption.

cs.LG↗

arXiv2023

A novel fast response and radiation-resistant scintillator detector for beam loss monitor

At high luminosity areas, beam loss monitor with fast response and high radiation resistance is crucial for accelerator operation. In this article, we report the design and test results of a fast response and radiation-resistant scintillator detector as the beam loss monitor for high luminosity colliders, especially at low energy regions such as RFQ. The detector consists of a 2 cm*2 cm 0.5 cm LYSO crystal readout by a 6 mm*6 mm Silicon photomultiplier. Test results from various radioactive sources show that the detector has good sensitivity to photons from tens of keV to several MeV with good linearity and energy resolution (23% for 60 keV γ-ray). For the field test, two such detectors are installed outside of the vacuum chamber shell of an 800 MeV electron storage ring. The details of the test and results are introduced.

physics.ins-det↗

arXiv2023

Thermal Conductivity of BAs under Pressure

The thermal conductivity of boron arsenide (BAs) is believed to be influenced by phonon scattering selection rules due to its special phonon dispersion. Compression of BAs leads to significant changes in phonon dispersion, which allows for a test of first principles theories for how phonon dispersion affects three- and four-phonon scattering rates. This study reports the thermal conductivity of BAs from 0 to 30 GPa. Thermal conductivity vs. pressure of BAs is measured by time-domain thermoreflectance with a diamond anvil cell. In stark contrast to what is typical for nonmetallic crystals, BAs is observed to have a pressure independent thermal conductivity below 30 GPa. The thermal conductivity of nonmetallic crystals typically increases upon compression. The unusual pressure independence of thermal conductivity of BAs shows the important relationship between phonon dispersion properties and three- and four-phonon scattering rates.

cond-mat.mtrl-sci↗

arXiv2023

All in Tokens: Unifying Output Space of Visual Tasks via Soft Token

Unlike language tasks, where the output space is usually limited to a set of tokens, the output space of visual tasks is more complicated, making it difficult to build a unified visual model for various visual tasks. In this paper, we seek to unify the output space of visual tasks, so that we can also build a unified model for visual tasks. To this end, we demonstrate a single unified model that simultaneously handles two typical visual tasks of instance segmentation and depth estimation, which have discrete/fixed-length and continuous/varied-length outputs, respectively. We propose several new techniques that take into account the particularity of visual tasks: 1) Soft token. We employ soft token to represent the task output. Unlike hard tokens in the common VQ-VAE which are assigned one-hot to discrete codebooks/vocabularies, the soft token is assigned softly to the codebook embeddings. Soft token can improve the accuracy of both the next token inference and decoding of the task output; 2) Mask augmentation. Many visual tasks have corruption, undefined or invalid values in label annotations, i.e., occluded area of depth maps. We show that a mask augmentation technique can greatly benefit these tasks. With these new techniques and other designs, we show that the proposed general-purpose task-solver can perform both instance segmentation and depth estimation well. Particularly, we achieve 0.279 RMSE on the specific task of NYUv2 depth estimation, setting a new record on this benchmark. The general-purpose task-solver, dubbed AiT, is available at \url{https://github.com/SwinTransformer/AiT}.

cs.CV↗

arXiv2023

QS-ADN: Quasi-Supervised Artifact Disentanglement Network for Low-Dose CT Image Denoising by Local Similarity Among Unpaired Data

Deep learning has been successfully applied to low-dose CT (LDCT) image denoising for reducing potential radiation risk. However, the widely reported supervised LDCT denoising networks require a training set of paired images, which is expensive to obtain and cannot be perfectly simulated. Unsupervised learning utilizes unpaired data and is highly desirable for LDCT denoising. As an example, an artifact disentanglement network (ADN) relies on unparied images and obviates the need for supervision but the results of artifact reduction are not as good as those through supervised learning.An important observation is that there is often hidden similarity among unpaired data that can be utilized. This paper introduces a new learning mode, called quasi-supervised learning, to empower the ADN for LDCT image denoising.For every LDCT image, the best matched image is first found from an unpaired normal-dose CT (NDCT) dataset. Then, the matched pairs and the corresponding matching degree as prior information are used to construct and train our ADN-type network for LDCT denoising.The proposed method is different from (but compatible with) supervised and semi-supervised learning modes and can be easily implemented by modifying existing networks. The experimental results show that the method is competitive with state-of-the-art methods in terms of noise suppression and contextual fidelity. The code and working dataset are publicly available at https://github.com/ruanyuhui/ADN-QSDL.git.

cs.LG↗

arXiv2023

ACTIVE: A Deep Model for Sperm and Impurity Detection in Microscopic Videos

The accurate detection of sperms and impurities is a very challenging task, facing problems such as the small size of targets, indefinite target morphologies, low contrast and resolution of the video, and similarity of sperms and impurities. So far, the detection of sperms and impurities still largely relies on the traditional image processing and detection techniques which only yield limited performance and often require manual intervention in the detection process, therefore unfavorably escalating the time cost and injecting the subjective bias into the analysis. Encouraged by the successes of deep learning methods in numerous object detection tasks, here we report a deep learning model based on Double Branch Feature Extraction Network (DBFEN) and Cross-conjugate Feature Pyramid Networks (CCFPN).DBFEN is designed to extract visual features from tiny objects with a double branch structure, and CCFPN is further introduced to fuse the features extracted by DBFEN to enhance the description of position and high-level semantic information. Our work is the pioneer of introducing deep learning approaches to the detection of sperms and impurities. Experiments show that the highest AP50 of the sperm and impurity detection is 91.13% and 59.64%, which lead its competitors by a substantial margin and establish new state-of-the-art results in this problem.

cs.CV↗

arXiv2023

A Knowledge-based Learning Framework for Self-supervised Pre-training Towards Enhanced Recognition of Biomedical Microscopy Images

Self-supervised pre-training has become the priory choice to establish reliable neural networks for automated recognition of massive biomedical microscopy images, which are routinely annotation-free, without semantics, and without guarantee of quality. Note that this paradigm is still at its infancy and limited by closely related open issues: 1) how to learn robust representations in an unsupervised manner from unlabelled biomedical microscopy images of low diversity in samples? and 2) how to obtain the most significant representations demanded by a high-quality segmentation? Aiming at these issues, this study proposes a knowledge-based learning framework (TOWER) towards enhanced recognition of biomedical microscopy images, which works in three phases by synergizing contrastive learning and generative learning methods: 1) Sample Space Diversification: Reconstructive proxy tasks have been enabled to embed a priori knowledge with context highlighted to diversify the expanded sample space; 2) Enhanced Representation Learning: Informative noise-contrastive estimation loss regularizes the encoder to enhance representation learning of annotation-free images; 3) Correlated Optimization: Optimization operations in pre-training the encoder and the decoder have been correlated via image restoration from proxy tasks, targeting the need for semantic segmentation. Experiments have been conducted on public datasets of biomedical microscopy images against the state-of-the-art counterparts (e.g., SimCLR and BYOL), and results demonstrate that: TOWER statistically excels in all self-supervised methods, achieving a Dice improvement of 1.38 percentage points over SimCLR. TOWER also has potential in multi-modality medical image analysis and enables label-efficient semi-supervised learning, e.g., reducing the annotation cost by up to 99% in pathological classification.

cs.CV↗

arXiv2023

Matching Using Sufficient Dimension Reduction for Heterogeneity Causal Effect Estimation

Causal inference plays an important role in under standing the underlying mechanisation of the data generation process across various domains. It is challenging to estimate the average causal effect and individual causal effects from observational data with high-dimensional covariates due to the curse of dimension and the problem of data sufficiency. The existing matching methods can not effectively estimate individual causal effect or solve the problem of dimension curse in causal inference. To address this challenge, in this work, we prove that the reduced set by sufficient dimension reduction (SDR) is a balance score for confounding adjustment. Under the theorem, we propose to use an SDR method to obtain a reduced representation set of the original covariates and then the reduced set is used for the matching method. In detail, a non-parametric model is used to learn such a reduced set and to avoid model specification errors. The experimental results on real-world datasets show that the proposed method outperforms the compared matching methods. Moreover, we conduct an experiment analysis and the results demonstrate that the reduced representation is enough to balance the imbalance between the treatment group and control group individuals.

cs.DS↗

arXiv2022

EBHI-Seg: A Novel Enteroscope Biopsy Histopathological Haematoxylin and Eosin Image Dataset for Image Segmentation Tasks

Background and Purpose: Colorectal cancer is a common fatal malignancy, the fourth most common cancer in men, and the third most common cancer in women worldwide. Timely detection of cancer in its early stages is essential for treating the disease. Currently, there is a lack of datasets for histopathological image segmentation of rectal cancer, which often hampers the assessment accuracy when computer technology is used to aid in diagnosis. Methods: This present study provided a new publicly available Enteroscope Biopsy Histopathological Hematoxylin and Eosin Image Dataset for Image Segmentation Tasks (EBHI-Seg). To demonstrate the validity and extensiveness of EBHI-Seg, the experimental results for EBHI-Seg are evaluated using classical machine learning methods and deep learning methods. Results: The experimental results showed that deep learning methods had a better image segmentation performance when utilizing EBHI-Seg. The maximum accuracy of the Dice evaluation metric for the classical machine learning method is 0.948, while the Dice evaluation metric for the deep learning method is 0.965. Conclusion: This publicly available dataset contained 5,170 images of six types of tumor differentiation stages and the corresponding ground truth images. The dataset can provide researchers with new segmentation algorithms for medical diagnosis of colorectal cancer, which can be used in the clinical setting to help doctors and patients.

eess.IV↗

arXiv2022

Electronic properties of Janus black arsenic-phosphorus (b-AsP) nanoribbons under transverse electric field

The electronic transport properties of Janus monolayer black arsenic phosphorus (b-AsP) nanoribbons have been investigated utilizing the tight-binding approach. The dependence of electronic structure on edge structures is systematically investigated. (1,3)nb and (3,1)nb b-AsP nanoribbons exhibit flatter edge bands than zigzag and armchair counterparts. The edge band of the armchair ones show double degeneracy. Further, the calculated results show the band gap of the zigzag ribbon with different boundary morphology is widely tunable by transverse electric field. A critical electric field can fully close the gap and induce a phase transition from a semiconductor into a conductor. Our work suggests dynamically tunable bandgap in Janus b-AsP nanoribbons and reveals the potential of Janus b-AsP for transmission devices.

cond-mat.mes-hall↗

arXiv2022

Electronic and optical properties of b-AsP quantum dots and quantum rings under the electric and magnetic fields

In this work, we investigate the electronic and optical properties of the b-AsP quantum dots(QDs) and quantum rings(QRs) with different edge types in the presence of an in-plane electric field and a perpendicular magnetic field utilizing the tight-binding method. Our calculations show that the electronic and optical properties of edge states largely depend on the edge types. By adjusting the intensity of the electric field or magnetic field, the probability density can be effectively tuned. In particular, under an in-plane electric field, novel edge states emerge in rhombus QDs and QRs with δ atoms, and transitions happen between these novel edge states and bulk states in the conduction band region, which is illustrated by distinct and evenly separated peaks in the optical absorption spectra. This work might exploit a potential system to implement quantum state transfer among two-dimensional material quantum dots.

cond-mat.mes-hall↗

arXiv2022

Robust and Fast Measure of Information via Low-rank Representation

The matrix-based Rényi's entropy allows us to directly quantify information measures from given data, without explicit estimation of the underlying probability distribution. This intriguing property makes it widely applied in statistical inference and machine learning tasks. However, this information theoretical quantity is not robust against noise in the data, and is computationally prohibitive in large-scale applications. To address these issues, we propose a novel measure of information, termed low-rank matrix-based Rényi's entropy, based on low-rank representations of infinitely divisible kernel matrices. The proposed entropy functional inherits the specialty of of the original definition to directly quantify information from data, but enjoys additional advantages including robustness and effective calculation. Specifically, our low-rank variant is more sensitive to informative perturbations induced by changes in underlying distributions, while being insensitive to uninformative ones caused by noises. Moreover, low-rank Rényi's entropy can be efficiently approximated by random projection and Lanczos iteration techniques, reducing the overall complexity from $\mathcal{O}(n^3)$ to $\mathcal{O}(n^2 s)$ or even $\mathcal{O}(ns^2)$, where $n$ is the number of data samples and $s \ll n$. We conduct large-scale experiments to evaluate the effectiveness of this new information measure, demonstrating superior results compared to matrix-based Rényi's entropy in terms of both performance and computational efficiency.

cs.LG↗

arXiv2022

An Energy Activity Dataset for Smart Homes

A smart home energy dataset that records miscellaneous energy consumption data is publicly offered. The proposed energy activity dataset (EAD) has a high data type diversity in contrast to existing load monitoring datasets. In EAD, a simple data point is labeled with the appliance, brand, and event information, whereas a complex data point has an extra application label. Several discoveries have been made on the energy consumption patterns of many appliances. Load curves of the appliances are measured when different events and applications are triggered and utilized. A revised longest-common-subsequence (LCS) similarity measurement algorithm is proposed to calculate energy dataset similarities. Thus, the data quality prior information becomes available before training machine learning models. In addition, a subsample convolutional neural network (SCNN) is put forward. It serves as a non-intrusive optical character recognition (OCR) approach to obtain energy data directly from monitors of power meters. The link for the EAD dataset is: https://drive.google.com/drive/folders/1zn0V6Q8eXXSKxKgcs8ZRValL5VEn3anD

eess.SP↗

arXiv2022

SynGEC: Syntax-Enhanced Grammatical Error Correction with a Tailored GEC-Oriented Parser

This work proposes a syntax-enhanced grammatical error correction (GEC) approach named SynGEC that effectively incorporates dependency syntactic information into the encoder part of GEC models. The key challenge for this idea is that off-the-shelf parsers are unreliable when processing ungrammatical sentences. To confront this challenge, we propose to build a tailored GEC-oriented parser (GOPar) using parallel GEC training data as a pivot. First, we design an extended syntax representation scheme that allows us to represent both grammatical errors and syntax in a unified tree structure. Then, we obtain parse trees of the source incorrect sentences by projecting trees of the target correct sentences. Finally, we train GOPar with such projected trees. For GEC, we employ the graph convolution network to encode source-side syntactic information produced by GOPar, and fuse them with the outputs of the Transformer encoder. Experiments on mainstream English and Chinese GEC datasets show that our proposed SynGEC approach consistently and substantially outperforms strong baselines and achieves competitive performance. Our code and data are all publicly available at https://github.com/HillZhang1999/SynGEC.

cs.CL↗

arXiv2022

Few-cycle pulse generation by double-stage hybrid multi-pass multi-plate nonlinear pulse compression

Few-cycle pulses present an essential tool to track ultrafast dynamics in matter and drive strong field effects. To address photon-hungry applications, high average power lasers are used which, however, cannot directly provide sub-100 fs pulse durations. Post-compression of laser pulses by spectral broadening and dispersion compensation is the most efficient method to overcome this limitation. Here, we demonstrate a notably compact setup which turns a 0.1 GW peak power, picosecond laser into a 2.9 GW peak power, 8.2 fs source. The 120-fold pulse duration shortening is accomplished in a two-stage hybrid multi-pass, multi-plate compression setup. To our knowledge, neither shorter pulses, nor higher peak powers have been reported to-date from bulk multi-pass cells alone, manifesting the power of the hybrid approach. It puts, for instance, compact, cost-efficient and high repetition rate attosecond sources within reach.

physics.optics↗

arXiv2022

Fries: Fast and Consistent Runtime Reconfiguration in Dataflow Systems with Transactional Guarantees (Extended Version)

A computing job in a big data system can take a long time to run, especially for pipelined executions on data streams. Developers often need to change the computing logic of the job such as fixing a loophole in an operator or changing the machine learning model in an operator with a cheaper model to handle a sudden increase of the data-ingestion rate. Recently many systems have started supporting runtime reconfigurations to allow this type of change on the fly without killing and restarting the execution. While the delay in reconfiguration is critical to performance, existing systems use epochs to do runtime reconfigurations, which can cause a long delay. In this paper we develop a new technique called Fries that leverages the emerging availability of fast control messages in many systems, since these messages can be sent without being blocked by data messages. We formally define consistency in runtime reconfigurations, and develop a Fries scheduler with consistency guarantees. The technique not only works for different classes of dataflows, but also works for parallel executions and supports fault tolerance. Our extensive experimental evaluation on clusters show the advantages of this technique compared to epoch-based schedulers.

cs.DB↗