arXiv subjects

Chang Chen

Publications and source records attributed to Chang Chen.

At least 55 records · Page 3Linked to original sources

arXiv2023

Computational Spectral Imaging with Unified Encoding Model: A Comparative Study and Beyond

Computational spectral imaging is drawing increasing attention owing to the snapshot advantage, and amplitude, phase, and wavelength encoding systems are three types of representative implementations. Fairly comparing and understanding the performance of these systems is essential, but challenging due to the heterogeneity in encoding design. To overcome this limitation, we propose the unified encoding model (UEM) that covers all physical systems using the three encoding types. Specifically, the UEM comprises physical amplitude, physical phase, and physical wavelength encoding models that can be combined with a digital decoding model in a joint encoder-decoder optimization framework to compare the three systems under a unified experimental setup fairly. Furthermore, we extend the UEMs to ideal versions, namely, ideal amplitude, ideal phase, and ideal wavelength encoding models, which are free from physical constraints, to explore the full potential of the three types of computational spectral imaging systems. Finally, we conduct a holistic comparison of the three types of computational spectral imaging systems and provide valuable insights for designing and exploiting these systems in the future.

eess.IV↗

arXiv2023

A discussion on the anomalous threshold enhancement of $J/ψ$ -- $ψ(3770)$ couplings and $X(6900)$ peak

The attractive interaction between $J/ψ$ and $ψ(3770)$ has to be strong enough to form the molecular resonant structure, i.e., $X(6900)$. We argue that since $ψ(3770)$ decays predominantly into a $D\bar D$ pair, the interactions between $J/ψ$ and $ψ(3770)$ may be significantly enhanced due to the three point $D\bar D$ loop diagram. The enhancement comes from the anomalous threshold located at $t=-1.288$GeV$^2$, which effect propagates into the $s$-channel partial wave amplitude in the vicinity of $\sqrt{s}\simeq 6.9$GeV. This effect may be helpful in forming the $X(6900)$ peak.

hep-ph↗

arXiv2023

An Image is Worth a Thousand Toxic Words: A Metamorphic Testing Framework for Content Moderation Software

The exponential growth of social media platforms has brought about a revolution in communication and content dissemination in human society. Nevertheless, these platforms are being increasingly misused to spread toxic content, including hate speech, malicious advertising, and pornography, leading to severe negative consequences such as harm to teenagers' mental health. Despite tremendous efforts in developing and deploying textual and image content moderation methods, malicious users can evade moderation by embedding texts into images, such as screenshots of the text, usually with some interference. We find that modern content moderation software's performance against such malicious inputs remains underexplored. In this work, we propose OASIS, a metamorphic testing framework for content moderation software. OASIS employs 21 transform rules summarized from our pilot study on 5,000 real-world toxic contents collected from 4 popular social media applications, including Twitter, Instagram, Sina Weibo, and Baidu Tieba. Given toxic textual contents, OASIS can generate image test cases, which preserve the toxicity yet are likely to bypass moderation. In the evaluation, we employ OASIS to test five commercial textual content moderation software from famous companies (i.e., Google Cloud, Microsoft Azure, Baidu Cloud, Alibaba Cloud and Tencent Cloud), as well as a state-of-the-art moderation research model. The results show that OASIS achieves up to 100% error finding rates. Moreover, through retraining the models with the test cases generated by OASIS, the robustness of the moderation model can be improved without performance degradation.

cs.SE↗

arXiv2023

Matching with multiple criteria and its application to health disparities research

Matching is a popular nonparametric covariate adjustment strategy in empirical health services research. Matching helps construct two groups comparable in many baseline covariates but different in some key aspects under investigation. In health disparities research, it is desirable to understand the contributions of various modifiable factors, like income and insurance type, to the observed disparity in access to health services between different groups. To single out the contributions from the factors of interest, we propose a statistical matching methodology that constructs nested matched comparison groups from, for instance, White men, that resemble the target group, for instance, black men, in some selected covariates while remaining identical to the white men population before matching in the remaining covariates. Using the proposed method, we investigated the disparity gaps between white men and black men in the US in prostate-specific antigen (PSA) screening based on the 2020 Behavioral Risk Factor Surveillance System (BFRSS) database. We found a widening PSA screening rate as the white matched comparison group increasingly resembles the black men group and quantified the contribution of modifiable factors like socioeconomic status. Finally, we provide code that replicates the case study and a tutorial that enables users to design customized matched comparison groups satisfying multiple criteria.

stat.AP↗

arXiv2023

Validating Multimedia Content Moderation Software via Semantic Fusion

The exponential growth of social media platforms, such as Facebook and TikTok, has revolutionized communication and content publication in human society. Users on these platforms can publish multimedia content that delivers information via the combination of text, audio, images, and video. Meanwhile, the multimedia content release facility has been increasingly exploited to propagate toxic content, such as hate speech, malicious advertisements, and pornography. To this end, content moderation software has been widely deployed on these platforms to detect and blocks toxic content. However, due to the complexity of content moderation models and the difficulty of understanding information across multiple modalities, existing content moderation software can fail to detect toxic content, which often leads to extremely negative impacts. We introduce Semantic Fusion, a general, effective methodology for validating multimedia content moderation software. Our key idea is to fuse two or more existing single-modal inputs (e.g., a textual sentence and an image) into a new input that combines the semantics of its ancestors in a novel manner and has toxic nature by construction. This fused input is then used for validating multimedia content moderation software. We realized Semantic Fusion as DUO, a practical content moderation software testing tool. In our evaluation, we employ DUO to test five commercial content moderation software and two state-of-the-art models against three kinds of toxic content. The results show that DUO achieves up to 100% error finding rate (EFR) when testing moderation software. In addition, we leverage the test cases generated by DUO to retrain the two models we explored, which largely improves model robustness while maintaining the accuracy on the original test set.

cs.SE↗

arXiv2023

Toward DNN of LUTs: Learning Efficient Image Restoration with Multiple Look-Up Tables

The widespread usage of high-definition screens on edge devices stimulates a strong demand for efficient image restoration algorithms. The way of caching deep learning models in a look-up table (LUT) is recently introduced to respond to this demand. However, the size of a single LUT grows exponentially with the increase of its indexing capacity, which restricts its receptive field and thus the performance. To overcome this intrinsic limitation of the single-LUT solution, we propose a universal method to construct multiple LUTs like a neural network, termed MuLUT. Firstly, we devise novel complementary indexing patterns, as well as a general implementation for arbitrary patterns, to construct multiple LUTs in parallel. Secondly, we propose a re-indexing mechanism to enable hierarchical indexing between cascaded LUTs. Finally, we introduce channel indexing to allow cross-channel interaction, enabling LUTs to process color channels jointly. In these principled ways, the total size of MuLUT is linear to its indexing capacity, yielding a practical solution to obtain superior performance with the enlarged receptive field. We examine the advantage of MuLUT on various image restoration tasks, including super-resolution, demosaicing, denoising, and deblocking. MuLUT achieves a significant improvement over the single-LUT solution, e.g., up to 1.1dB PSNR for super-resolution and up to 2.8dB PSNR for grayscale denoising, while preserving its efficiency, which is 100$\times$ less in energy cost compared with lightweight deep neural networks. Our code and trained models are publicly available at https://github.com/ddlee-cn/MuLUT.

cs.CV↗

arXiv2023

TA-MoE: Topology-Aware Large Scale Mixture-of-Expert Training

Sparsely gated Mixture-of-Expert (MoE) has demonstrated its effectiveness in scaling up deep neural networks to an extreme scale. Despite that numerous efforts have been made to improve the performance of MoE from the model design or system optimization perspective, existing MoE dispatch patterns are still not able to fully exploit the underlying heterogeneous network environments. In this paper, we propose TA-MoE, a topology-aware routing strategy for large-scale MoE trainging, from a model-system co-design perspective, which can dynamically adjust the MoE dispatch pattern according to the network topology. Based on communication modeling, we abstract the dispatch problem into an optimization objective and obtain the approximate dispatch pattern under different topologies. On top of that, we design a topology-aware auxiliary loss, which can adaptively route the data to fit in the underlying topology without sacrificing the model accuracy. Experiments show that TA-MoE can substantially outperform its counterparts on various hardware and model configurations, with roughly 1.01x-1.61x, 1.01x-4.77x, 1.25x-1.54x improvements over the popular DeepSpeed-MoE, FastMoE and FasterMoE.

cs.LG↗

arXiv2023

The $X(6900)$ peak could be a molecular state

The analyses of the LHCb data on $X(6900)$ found in di-$J/ψ$ and $J/ψψ(3686)$ systems are performed using a momentum-dependent {Flatté}-like parameterization. The use of the pole counting rule and spectral density function sum rule give consistent conclusions that $X(6900)$ may not be a molecule of $J/ψψ(3686)$. Nevertheless it is still possible that $X(6900)$ be a molecule of higher states, such as $J/ψψ(3770)$, $χ_{c0}χ_{c2}$, etc.

hep-ph↗

arXiv2023

Identifying Hadronic Molecular States with a Neural Network

Neural networks are trained to judge whether or not an exotic state is a hadronic molecule of a given channel according its line-shapes. This method performs well in both trainings and validation tests. As applications, it is applied to study $X(3872)$, $X(4260)$ and $Z_c(3900)$. The results show that $Z_c(3900)$ should be regarded as a $\bar{D}^* D$ molecular state but $X(3872)$ not. As for $X(4260)$, it can not be a molecular state of $χ_{c0}ω$. Some discussions on $X_1(2900)$ are also provided.

hep-ph↗

arXiv2022

Association between author metadata and acceptance: A feature-rich, matched observational study of a corpus of ICLR submissions between 2017-2022

Many recent studies have probed status bias in the peer-review process of academic journals and conferences. In this article, we investigated the association between author metadata and area chairs' final decisions (Accept/Reject) using our compiled database of 5,313 borderline submissions to the International Conference on Learning Representations (ICLR) from 2017 to 2022. We carefully defined elements in a cause-and-effect analysis, including the treatment and its timing, pre-treatment variables, potential outcomes and causal null hypothesis of interest, all in the context of study units being textual data and under Neyman and Rubin's potential outcomes (PO) framework. We found some weak evidence that author metadata was associated with articles' final decisions. We also found that, under an additional stability assumption, borderline articles from high-ranking institutions (top-30% or top-20%) were less favored by area chairs compared to their matched counterparts. The results were consistent in two different matched designs (odds ratio = 0.82 [95% CI: 0.67 to 1.00] in a first design and 0.83 [95% CI: 0.64 to 1.07] in a strengthened design). We discussed how to interpret these results in the context of multiple interactions between a study unit and different agents (reviewers and area chairs) in the peer-review system.

stat.AP↗

arXiv2022

Towards Real World HDRTV Reconstruction: A Data Synthesis-based Approach

Existing deep learning based HDRTV reconstruction methods assume one kind of tone mapping operators (TMOs) as the degradation procedure to synthesize SDRTV-HDRTV pairs for supervised training. In this paper, we argue that, although traditional TMOs exploit efficient dynamic range compression priors, they have several drawbacks on modeling the realistic degradation: information over-preservation, color bias and possible artifacts, making the trained reconstruction networks hard to generalize well to real-world cases. To solve this problem, we propose a learning-based data synthesis approach to learn the properties of real-world SDRTVs by integrating several tone mapping priors into both network structures and loss functions. In specific, we design a conditioned two-stream network with prior tone mapping results as a guidance to synthesize SDRTVs by both global and local transformations. To train the data synthesis network, we form a novel self-supervised content loss to constraint different aspects of the synthesized SDRTVs at regions with different brightness distributions and an adversarial loss to emphasize the details to be more realistic. To validate the effectiveness of our approach, we synthesize SDRTV-HDRTV pairs with our method and use them to train several HDRTV reconstruction networks. Then we collect two inference datasets containing both labeled and unlabeled real-world SDRTVs, respectively. Experimental results demonstrate that, the networks trained with our synthesized data generalize significantly better to these two real-world datasets than existing solutions.

cs.CV↗

arXiv2022

Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report

Cameras capture sensor RAW images and transform them into pleasant RGB images, suitable for the human eyes, using their integrated Image Signal Processor (ISP). Numerous low-level vision tasks operate in the RAW domain (e.g. image denoising, white balance) due to its linear relationship with the scene irradiance, wide-range of information at 12bits, and sensor designs. Despite this, RAW image datasets are scarce and more expensive to collect than the already large and public RGB datasets. This paper introduces the AIM 2022 Challenge on Reversed Image Signal Processing and RAW Reconstruction. We aim to recover raw sensor images from the corresponding RGBs without metadata and, by doing this, "reverse" the ISP transformation. The proposed methods and benchmark establish the state-of-the-art for this low-level vision inverse problem, and generating realistic raw sensor readings can potentially benefit other tasks such as denoising and super-resolution.

eess.IV↗

arXiv2022

Trans4Map: Revisiting Holistic Bird's-Eye-View Mapping from Egocentric Images to Allocentric Semantics with Vision Transformers

Humans have an innate ability to sense their surroundings, as they can extract the spatial representation from the egocentric perception and form an allocentric semantic map via spatial transformation and memory updating. However, endowing mobile agents with such a spatial sensing ability is still a challenge, due to two difficulties: (1) the previous convolutional models are limited by the local receptive field, thus, struggling to capture holistic long-range dependencies during observation; (2) the excessive computational budgets required for success, often lead to a separation of the mapping pipeline into stages, resulting the entire mapping process inefficient. To address these issues, we propose an end-to-end one-stage Transformer-based framework for Mapping, termed Trans4Map. Our egocentric-to-allocentric mapping process includes three steps: (1) the efficient transformer extracts the contextual features from a batch of egocentric images; (2) the proposed Bidirectional Allocentric Memory (BAM) module projects egocentric features into the allocentric memory; (3) the map decoder parses the accumulated memory and predicts the top-down semantic segmentation map. In contrast, Trans4Map achieves state-of-the-art results, reducing 67.2% parameters, yet gaining a +3.25% mIoU and a +4.09% mBF1 improvements on the Matterport3D dataset. Code at: https://github.com/jamycheung/Trans4Map.

cs.CV↗

arXiv2022

Continuous Spectral Reconstruction from RGB Images via Implicit Neural Representation

Existing methods for spectral reconstruction usually learn a discrete mapping from RGB images to a number of spectral bands. However, this modeling strategy ignores the continuous nature of spectral signature. In this paper, we propose Neural Spectral Reconstruction (NeSR) to lift this limitation, by introducing a novel continuous spectral representation. To this end, we embrace the concept of implicit function and implement a parameterized embodiment with a neural network. Specifically, we first adopt a backbone network to extract spatial features of RGB inputs. Based on it, we devise Spectral Profile Interpolation (SPI) module and Neural Attention Mapping (NAM) module to enrich deep features, where the spatial-spectral correlation is involved for a better representation. Then, we view the number of sampled spectral bands as the coordinate of continuous implicit function, so as to learn the projection from deep features to spectral intensities. Extensive experiments demonstrate the distinct advantage of NeSR in reconstruction accuracy over baseline methods. Moreover, NeSR extends the flexibility of spectral reconstruction by enabling an arbitrary number of spectral bands as the target output.

cs.CV↗

arXiv2022

Advanced Deep Networks for 3D Mitochondria Instance Segmentation

Mitochondria instance segmentation from electron microscopy (EM) images has seen notable progress since the introduction of deep learning methods. In this paper, we propose two advanced deep networks, named Res-UNet-R and Res-UNet-H, for 3D mitochondria instance segmentation from Rat and Human samples. Specifically, we design a simple yet effective anisotropic convolution block and deploy a multi-scale training strategy, which together boost the segmentation performance. Moreover, we enhance the generalizability of the trained models on the test set by adding a denoising operation as pre-processing. In the Large-scale 3D Mitochondria Instance Segmentation Challenge at ISBI 2021, our method ranks the 1st place. Code is available at https://github.com/Limingxing00/MitoEM2021-Challenge.

cs.CV↗

arXiv2022

On Lowest Lying $\frac{1}{2}^-$ Octet Baryons

The recently proposed $N^*(890)$ $1/2^-$ baryon is studied in a flavor $SU(3)$ scheme with $K$ matrix unitarization, by fitting to low energy cross section and phase shift data. It is found that $N^*(890)$ co-exists with low lying poles in other channels, which have been extensively discussed in the literature, though they belong to different octets, in the $SU(3)$ limit. Hence the existence of $N^*(890)$ is further verified.

hep-ph↗

arXiv2022

Retinal Vessel Segmentation with Pixel-wise Adaptive Filters

Accurate retinal vessel segmentation is challenging because of the complex texture of retinal vessels and low imaging contrast. Previous methods generally refine segmentation results by cascading multiple deep networks, which are time-consuming and inefficient. In this paper, we propose two novel methods to address these challenges. First, we devise a light-weight module, named multi-scale residual similarity gathering (MRSG), to generate pixel-wise adaptive filters (PA-Filters). Different from cascading multiple deep networks, only one PA-Filter layer can improve the segmentation results. Second, we introduce a response cue erasing (RCE) strategy to enhance the segmentation accuracy. Experimental results on the DRIVE, CHASE_DB1, and STARE datasets demonstrate that our proposed method outperforms state-of-the-art methods while maintaining a compact structure. Code is available at https://github.com/Limingxing00/Retinal-Vessel-Segmentation-ISBI20222.

eess.IV↗

arXiv2021

Removing Interlopers From Intensity Mapping Probes Of Primordial Non-Gaussianity

Line intensity mapping (LIM) has the potential to produce highly precise measurements of scale-dependence bias from primordial non-Gaussianity (PNG) due to its ability to map much larger volumes than are available from galaxy surveys. PNG parameterized by $f_{NL}$ leads to a scale-dependent correction to the bias, and therefore a correction to the line intensity power spectrum. However, LIM experiences contamination from foreground emission, including interloping emission lines from other redshifts which alter the power spectra of the maps at these scales, potentially biasing measurements of $f_{NL}$. Here we model the effect of line interlopers on upcoming line intensity mapping probes of primordial non-Gaussianity (PNG) from inflation. As an example, we consider the $[\rm CII]$ line at target redshift $z_t = 3.6$ to probe PNG, with the important systematic concern being foreground contamination from CO lines residing at redshifts different from the target redshift. We find interloper lines can lead to a significant bias and an increase in errors for our PNG constraints, leading to a false positive for non-standard inflation models. We model how well the cross-correlation technique could reduce this interloper contamination. We find the uncertainty of $f_{NL}$ reduces by factors of two and six for local and orthogonal shape PNG respectively, and by a factor of five for local shape if we consider seven interloper lines, almost eliminating the effect of interlopers. This work shows that using cross-power and auto-power spectra of line intensity maps jointly could potentially remove the effects of interlopers when measuring non-Gaussianity.

astro-ph.CO↗