arXiv subjects

Zhen Cheng

Publications and source records attributed to Zhen Cheng.

30 records · Page 2Linked to original sources

arXiv2023

OpenMix: Exploring Outlier Samples for Misclassification Detection

Reliable confidence estimation for deep neural classifiers is a challenging yet fundamental requirement in high-stakes applications. Unfortunately, modern deep neural networks are often overconfident for their erroneous predictions. In this work, we exploit the easily available outlier samples, i.e., unlabeled samples coming from non-target classes, for helping detect misclassification errors. Particularly, we find that the well-known Outlier Exposure, which is powerful in detecting out-of-distribution (OOD) samples from unknown classes, does not provide any gain in identifying misclassification errors. Based on these observations, we propose a novel method called OpenMix, which incorporates open-world knowledge by learning to reject uncertain pseudo-samples generated via outlier transformation. OpenMix significantly improves confidence reliability under various scenarios, establishing a strong and unified framework for detecting both misclassified samples from known classes and OOD samples from unknown classes. The code is publicly available at https://github.com/Impression2805/OpenMix.

cs.LG↗

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

Rethinking Confidence Calibration for Failure Prediction

Reliable confidence estimation for the predictions is important in many safety-critical applications. However, modern deep neural networks are often overconfident for their incorrect predictions. Recently, many calibration methods have been proposed to alleviate the overconfidence problem. With calibrated confidence, a primary and practical purpose is to detect misclassification errors by filtering out low-confidence predictions (known as failure prediction). In this paper, we find a general, widely-existed but actually-neglected phenomenon that most confidence calibration methods are useless or harmful for failure prediction. We investigate this problem and reveal that popular confidence calibration methods often lead to worse confidence separation between correct and incorrect samples, making it more difficult to decide whether to trust a prediction or not. Finally, inspired by the natural connection between flat minima and confidence separation, we propose a simple hypothesis: flat minima is beneficial for failure prediction. We verify this hypothesis via extensive experiments and further boost the performance by combining two different flat minima techniques. Our code is available at https://github.com/Impression2805/FMFP

cs.LG↗

arXiv2023

Average of Pruning: Improving Performance and Stability of Out-of-Distribution Detection

Detecting Out-of-distribution (OOD) inputs have been a critical issue for neural networks in the open world. However, the unstable behavior of OOD detection along the optimization trajectory during training has not been explored clearly. In this paper, we first find the performance of OOD detection suffers from overfitting and instability during training: 1) the performance could decrease when the training error is near zero, and 2) the performance would vary sharply in the final stage of training. Based on our findings, we propose Average of Pruning (AoP), consisting of model averaging and pruning, to mitigate the unstable behaviors. Specifically, model averaging can help achieve a stable performance by smoothing the landscape, and pruning is certified to eliminate the overfitting by eliminating redundant features. Comprehensive experiments on various datasets and architectures are conducted to verify the effectiveness of our method.

cs.LG↗

arXiv2022

Infinitely many sign-changing solutions for the nonlinear Schrödinger-Poisson system with $p$-Laplacian

In this paper, we consider the following Schrödinger-Poisson system with $p$-laplacian \begin{equation} \begin{cases} -Δ_{p}u+V(x)|u|^{p-2}u+ϕ|u|^{p-2}u=f(u)\qquad&x\in\mathbb{R}^{3},\newline -Δϕ=|u|^{p}&x\in\mathbb{R}^{3}. \end{cases}\notag \end{equation} We investigate the existence of multiple sign-changing solutions. By using the method of invariant sets of descending flow, we prove that this system has infinitely many sign-changing solutions. This system is new one coupled by Schrödinger equation of $p$-laplacian with a Poisson equation. Our results complement the study made by Zhaoli Liu, Zhiqiang Wang, Jianjun Zhang (Annali di Matematica Pura ed Applicata, 195(3):775-794(2016)).

math.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

Degradation-agnostic Correspondence from Resolution-asymmetric Stereo

In this paper, we study the problem of stereo matching from a pair of images with different resolutions, e.g., those acquired with a tele-wide camera system. Due to the difficulty of obtaining ground-truth disparity labels in diverse real-world systems, we start from an unsupervised learning perspective. However, resolution asymmetry caused by unknown degradations between two views hinders the effectiveness of the generally assumed photometric consistency. To overcome this challenge, we propose to impose the consistency between two views in a feature space instead of the image space, named feature-metric consistency. Interestingly, we find that, although a stereo matching network trained with the photometric loss is not optimal, its feature extractor can produce degradation-agnostic and matching-specific features. These features can then be utilized to formulate a feature-metric loss to avoid the photometric inconsistency. Moreover, we introduce a self-boosting strategy to optimize the feature extractor progressively, which further strengthens the feature-metric consistency. Experiments on both simulated datasets with various degradations and a self-collected real-world dataset validate the superior performance of the proposed method over existing solutions.

cs.CV↗

arXiv2021

On the physical origin of enhanced turbulent-dispersion of inertial particles in boundary layer flows

One of the most enigmatic science question concerning inertial particle transport by a turbulent boundary layer flow is the value of the turbulent Schmidt number as the ratio of particle diffusivity and turbulent eddy viscosity. Using direct acoustic measurement of turbulent particle flux profile, and two-phase flow turbulence-resolving numerical simulation, it is demonstrated that turbulent dispersion of particles is reduced rather than enhanced when predicted with existing literature model. The explanation lies in the misleading assumption of settling velocity in quiescent water to estimate the turbulent particle diffusivity while direct measurements and simulations of turbulent particle flux support the occurrence of settling retardation.

physics.flu-dyn↗

arXiv2021

The dependence of overlap topological charge density on Wilson mass parameter

In this paper, we analyze the dependence of the topological charge density from the overlap operator on the Wilson mass parameter in the overlap kernel by the symmetric multi-probing source (SMP) method. We observe that the non-trivial topological objects are removed as the Wilson mass is increased. A comparison of topological charge density calculated by the SMP method using fermionic definition with that of gluonic definition by the Wilson flow method is shown. A matching procedure for these two methods is used. We find that there is a best match for topological charge density between gluonic definition with varied Wilson flow time and fermionic definition with different Wilson mass. By using the matching procedure, the proper flow time of Wilson flow in the calculation of topological charge density can be estimated. As the lattice spacing $a$ decreases, the proper flow time also decreases, as expected.

hep-lat↗

arXiv2019

Multi-Perspective Inferrer: Reasoning Sentences Relationship from Holistic Perspective

Natural Language Inference (NLI) aims to determine the logic relationships (i.e., entailment, neutral and contradiction) between a pair of premise and hypothesis. Recently, the alignment mechanism effectively helps NLI by capturing the aligned parts (i.e., the similar segments) in the sentence pairs, which imply the perspective of entailment and contradiction. However, these aligned parts will sometimes mislead the judgment of neutral relations. Intuitively, NLI should rely more on multiple perspectives to form a holistic view to eliminate bias. In this paper, we propose the Multi-Perspective Inferrer (MPI), a novel NLI model that reasons relationships from multiple perspectives associated with the three relationships. The MPI determines the perspectives of different parts of the sentences via a routing-by-agreement policy and makes the final decision from a holistic view. Additionally, we introduce an auxiliary supervised signal to ensure the MPI to learn the expected perspectives. Experiments on SNLI and MultiNLI show that 1) the MPI achieves substantial improvements on the base model, which verifies the motivation of multi-perspective inference; 2) visualized evidence verifies that the MPI learns highly interpretable perspectives as expected; 3) more importantly, the MPI is architecture-free and compatible with the powerful BERT.

cs.CL↗

arXiv2019

Towards a First Step to Understand the Cryptocurrency Stealing Attack on Ethereum

We performed the first systematic study of a new attack on Ethereum that steals cryptocurrencies. The attack is due to the unprotected JSON-RPC endpoints existed in Ethereum nodes that could be exploited by attackers to transfer the Ether and ERC20 tokens to attackers-controlled accounts. This study aims to shed light on the attack, including malicious behaviors and profits of attackers. Specifically, we first designed and implemented a honeypot that could capture real attacks in the wild. We then deployed the honeypot and reported results of the collected data in a period of six months. In total, our system captured more than 308 million requests from 1,072 distinct IP addresses. We further grouped attackers into 36 groups with 59 distinct Ethereum accounts. Among them, attackers of 34 groups were stealing the Ether, while other 2 groups were targeting ERC20 tokens. The further behavior analysis showed that attackers were following a three-steps pattern to steal the Ether. Moreover, we observed an interesting type of transaction called zero gas transaction, which has been leveraged by attackers to steal ERC20 tokens. At last, we estimated the overall profits of attackers. To engage the whole community, the dataset of captured attacks is released on https://github.com/zjuicsr/eth-honey.

cs.CR↗

arXiv2012

A photonic crystal cavity-optical fiber tip nanoparticle sensor for biomedical applications

We present a sensor capable of detecting solution-based nanoparticles using an optical fiber tip functionalized with a photonic crystal cavity. When sensor tips are retracted from a nanoparticle solution after being submerged, we find that a combination of convective fluid forces and optically-induced trapping cause an aggregation of nanoparticles to form directly on cavity surfaces. A simple readout of quantum dot photoluminescence coupled to the optical fiber shows that nanoparticle presence and concentration can be detected through modified cavity properties. Our sensor can detect both gold and iron oxide nanoparticles and can be utilized for molecular sensing applications in biomedicine.

physics.optics↗