arXiv subjects

Zhen Liu

Publications and source records attributed to Zhen Liu.

At least 163 records · Page 9Linked to original sources

arXiv2024

Controlling Text-to-Image Diffusion by Orthogonal Finetuning

Large text-to-image diffusion models have impressive capabilities in generating photorealistic images from text prompts. How to effectively guide or control these powerful models to perform different downstream tasks becomes an important open problem. To tackle this challenge, we introduce a principled finetuning method -- Orthogonal Finetuning (OFT), for adapting text-to-image diffusion models to downstream tasks. Unlike existing methods, OFT can provably preserve hyperspherical energy which characterizes the pairwise neuron relationship on the unit hypersphere. We find that this property is crucial for preserving the semantic generation ability of text-to-image diffusion models. To improve finetuning stability, we further propose Constrained Orthogonal Finetuning (COFT) which imposes an additional radius constraint to the hypersphere. Specifically, we consider two important finetuning text-to-image tasks: subject-driven generation where the goal is to generate subject-specific images given a few images of a subject and a text prompt, and controllable generation where the goal is to enable the model to take in additional control signals. We empirically show that our OFT framework outperforms existing methods in generation quality and convergence speed.

cs.CV↗

arXiv2024

Top Yukawa Coupling Determination at High Energy Muon Collider

The Top Yukawa coupling profoundly influences several core mysteries linked to the electroweak scale and the Higgs boson. We study the feasibility of measuring the Top Yukawa coupling at high-energy muon colliders by examining the high-energy dynamics of the weak boson fusion to top quark pair processes. A deviation of the Top Yukawa coupling from the Standard Model would lead modified $V V \rightarrow t\bar{t}$ process, violating unitarity at high energy. Our analysis reveals that utilizing a muon collider with a center-of-mass energy of 10 TeV and an integrated luminosity of 10 ab$^{-1}$ allows us to investigate the Top Yukawa coupling with a precision surpassing 1.5\%, more than one order of magnitude better than the precision from $t\bar t h$ channel at muon colliders. This precision represents a notable enhancement compared to the anticipated sensitivities of the High-Luminosity LHC (3.4\%) and those at muon colliders derived from the $t\bar{t} H$ process.

hep-ph↗

arXiv2024

Lightweight Pixel Difference Networks for Efficient Visual Representation Learning

Recently, there have been tremendous efforts in developing lightweight Deep Neural Networks (DNNs) with satisfactory accuracy, which can enable the ubiquitous deployment of DNNs in edge devices. The core challenge of developing compact and efficient DNNs lies in how to balance the competing goals of achieving high accuracy and high efficiency. In this paper we propose two novel types of convolutions, dubbed \emph{Pixel Difference Convolution (PDC) and Binary PDC (Bi-PDC)} which enjoy the following benefits: capturing higher-order local differential information, computationally efficient, and able to be integrated with existing DNNs. With PDC and Bi-PDC, we further present two lightweight deep networks named \emph{Pixel Difference Networks (PiDiNet)} and \emph{Binary PiDiNet (Bi-PiDiNet)} respectively to learn highly efficient yet more accurate representations for visual tasks including edge detection and object recognition. Extensive experiments on popular datasets (BSDS500, ImageNet, LFW, YTF, \emph{etc.}) show that PiDiNet and Bi-PiDiNet achieve the best accuracy-efficiency trade-off. For edge detection, PiDiNet is the first network that can be trained without ImageNet, and can achieve the human-level performance on BSDS500 at 100 FPS and with $<$1M parameters. For object recognition, among existing Binary DNNs, Bi-PiDiNet achieves the best accuracy and a nearly $2\times$ reduction of computational cost on ResNet18. Code available at \href{https://github.com/hellozhuo/pidinet}{https://github.com/hellozhuo/pidinet}.

cs.CV↗

arXiv2024

Higgs Width and Couplings at High Energy Muon Colliders with Forward Muon Detection

We propose a novel method using the $ZZ$-fusion channel and forward muon detection at high-energy muon colliders to address the challenge of the Higgs coupling-width degeneracy. Our approach enables inclusive Higgs rate measurement to 0.75% at 10~TeV muon collider, breaking the coupling-width degeneracy. Results indicate the potential to refine Higgs coupling to sub-percent levels and estimate its total width within (-0.41%, +2.1%). Key insights include the effectiveness of forward muon tagging in signal-background separation despite broad recoil mass distribution due to muon energy reconstruction and beam energy spread. The study emphasizes the significance of muon rapidity coverage up to $|η(μ)|<6$, enhancing measurement precision. Our findings highlight the unique capabilities of high-energy lepton colliders for model-independent Higgs coupling determination and lay the groundwork for future advancements in muon collider technology and Higgs physics research.

hep-ph↗

arXiv2023

Cognitive Visual Commonsense Reasoning Using Dynamic Working Memory

Visual Commonsense Reasoning (VCR) predicts an answer with corresponding rationale, given a question-image input. VCR is a recently introduced visual scene understanding task with a wide range of applications, including visual question answering, automated vehicle systems, and clinical decision support. Previous approaches to solving the VCR task generally rely on pre-training or exploiting memory with long dependency relationship encoded models. However, these approaches suffer from a lack of generalizability and prior knowledge. In this paper we propose a dynamic working memory based cognitive VCR network, which stores accumulated commonsense between sentences to provide prior knowledge for inference. Extensive experiments show that the proposed model yields significant improvements over existing methods on the benchmark VCR dataset. Moreover, the proposed model provides intuitive interpretation into visual commonsense reasoning. A Python implementation of our mechanism is publicly available at https://github.com/tanjatang/DMVCR

cs.CV↗

arXiv2023

FINER: Flexible spectral-bias tuning in Implicit NEural Representation by Variable-periodic Activation Functions

Implicit Neural Representation (INR), which utilizes a neural network to map coordinate inputs to corresponding attributes, is causing a revolution in the field of signal processing. However, current INR techniques suffer from a restricted capability to tune their supported frequency set, resulting in imperfect performance when representing complex signals with multiple frequencies. We have identified that this frequency-related problem can be greatly alleviated by introducing variable-periodic activation functions, for which we propose FINER. By initializing the bias of the neural network within different ranges, sub-functions with various frequencies in the variable-periodic function are selected for activation. Consequently, the supported frequency set of FINER can be flexibly tuned, leading to improved performance in signal representation. We demonstrate the capabilities of FINER in the contexts of 2D image fitting, 3D signed distance field representation, and 5D neural radiance fields optimization, and we show that it outperforms existing INRs.

cs.CV↗

arXiv2023

Searching for millicharged particles with 1 kg of Skipper-CCDs using the NuMI beam at Fermilab

Oscura is a planned light-dark matter search experiment using Skipper-CCDs with a total active mass of 10 kg. As part of the detector development, the collaboration plans to build the Oscura Integration Test (OIT), an engineering test with 10% of the total mass. Here we discuss the early science opportunities with the OIT to search for millicharged particles (mCPs) using the NuMI beam at Fermilab. mCPs would be produced at low energies through photon-mediated processes from decays of scalar, pseudoscalar, and vector mesons, or direct Drell-Yan productions. Estimates show that the OIT would be a world-leading probe for mCPs in the MeV mass range.

hep-ex↗

arXiv2023

Using Representation Expressiveness and Learnability to Evaluate Self-Supervised Learning Methods

We address the problem of evaluating the quality of self-supervised learning (SSL) models without access to supervised labels, while being agnostic to the architecture, learning algorithm or data manipulation used during training. We argue that representations can be evaluated through the lens of expressiveness and learnability. We propose to use the Intrinsic Dimension (ID) to assess expressiveness and introduce Cluster Learnability (CL) to assess learnability. CL is measured in terms of the performance of a KNN classifier trained to predict labels obtained by clustering the representations with K-means. We thus combine CL and ID into a single predictor -- CLID. Through a large-scale empirical study with a diverse family of SSL algorithms, we find that CLID better correlates with in-distribution model performance than other competing recent evaluation schemes. We also benchmark CLID on out-of-domain generalization, where CLID serves as a predictor of the transfer performance of SSL models on several visual classification tasks, yielding improvements with respect to the competing baselines.

cs.LG↗

arXiv2023

Embeddings of generalised Morrey smoothness spaces

We study embeddings between generalised Triebel-Lizorkin-Morrey spaces ${\mathcal E}^{s}_{φ,p,q}({\mathbb R}^d)$ and within the scales of further generalised Morrey smoothness spaces like ${\mathcal N}^{s}_{φ,p,q}({\mathbb R}^d)$, ${B}_{p,q}^{s,φ}({\mathbb R}^d)$ and ${F}_{p,q}^{s,φ}({\mathbb R}^d)$. The latter have been investigated in a recent paper by the first two authors (2023), while the embeddings of the scale ${\mathcal N}^{s}_{φ,p,q}({\mathbb R}^d)$ were mainly obtained in a paper of the first and last two authors (2022). Now we concentrate on the characterisation of the spaces ${\mathcal E}^{s}_{φ,p,q}({\mathbb R}^d)$. Our approach requires a wavelet characterisation of those spaces which we establish for the system of Daubechies' wavelets. Then we prove necessary and sufficient conditions for the embedding ${\mathcal E}^{s_1}_{φ_1,p_1,q_1}({\mathbb R}^d)\hookrightarrow {\mathcal E}^{s_2}_{φ_2,p_2,q_2}({\mathbb R}^d)$. We can also provide some almost final answer to the question when ${\mathcal E}^{s}_{φ,p,q}({\mathbb R}^d)$ is embedded into $C({\mathbb R}^d)$, complementing our recent findings in case of ${\mathcal N}^{s}_{φ,p,q}({\mathbb R}^d)$.

math.FA↗

arXiv2023

Heterogenous Memory Augmented Neural Networks

It has been shown that semi-parametric methods, which combine standard neural networks with non-parametric components such as external memory modules and data retrieval, are particularly helpful in data scarcity and out-of-distribution (OOD) scenarios. However, existing semi-parametric methods mostly depend on independent raw data points - this strategy is difficult to scale up due to both high computational costs and the incapacity of current attention mechanisms with a large number of tokens. In this paper, we introduce a novel heterogeneous memory augmentation approach for neural networks which, by introducing learnable memory tokens with attention mechanism, can effectively boost performance without huge computational overhead. Our general-purpose method can be seamlessly combined with various backbones (MLP, CNN, GNN, and Transformer) in a plug-and-play manner. We extensively evaluate our approach on various image and graph-based tasks under both in-distribution (ID) and OOD conditions and show its competitive performance against task-specific state-of-the-art methods. Code is available at \url{https://github.com/qiuzh20/HMA}.

cs.LG↗

arXiv2023

Adversarial Driving Behavior Generation Incorporating Human Risk Cognition for Autonomous Vehicle Evaluation

Autonomous vehicle (AV) evaluation has been the subject of increased interest in recent years both in industry and in academia. This paper focuses on the development of a novel framework for generating adversarial driving behavior of background vehicle interfering against the AV to expose effective and rational risky events. Specifically, the adversarial behavior is learned by a reinforcement learning (RL) approach incorporated with the cumulative prospect theory (CPT) which allows representation of human risk cognition. Then, the extended version of deep deterministic policy gradient (DDPG) technique is proposed for training the adversarial policy while ensuring training stability as the CPT action-value function is leveraged. A comparative case study regarding the cut-in scenario is conducted on a high fidelity Hardware-in-the-Loop (HiL) platform and the results demonstrate the adversarial effectiveness to infer the weakness of the tested AV.

cs.AI↗

arXiv2023

First attempt of directionality reconstruction for atmospheric neutrinos in a large homogeneous liquid scintillator detector

The directionality information of incoming neutrinos is essential to atmospheric neutrino oscillation analysis since it is directly related to the oscillation baseline length. Large homogeneous liquid scintillator detectors, while offering excellent energy resolution, are traditionally very limited in their capabilities of measuring event directionality. In this paper, we present a novel directionality reconstruction method for atmospheric neutrino events in large homogeneous liquid scintillator detectors based on waveform analysis and machine learning techniques. We demonstrate for the first time that such detectors can achieve good direction resolution and potentially play an important role in future atmospheric neutrino oscillation measurements.

hep-ex↗

arXiv2023

Magnetic properties of the quasi-one-dimensional S = 1 spin chain antiferromagnet BaNiTe2O7

We report a quasi-one-dimensional S = 1 spin chain compound BaNiTe2O7. This magnetic system has been investigated by magnetic susceptibility, specific heat, and neutron powder diffraction. These results indicate that BaNiTe2O7 develops a short-range magnetic correlation around T ~ 22 K. With further cooling, an antiferromagnetic phase transition is observed at TN ~ 5.4 K. Neutron powder diffraction revealed antiferromagnetic noncollinear order with a commensurate propagation vector k = (1/2, 1, 0). The refined magnetic moment size of Ni2+ at 1.5 K is 1.84μB, and its noncollinear spin texture is confirmed by first-principles calculations. Inelastic neutron-scattering results and density functional theory calculations confirmed the quasi-one-dimensional nature of the spin systems.

cond-mat.str-el↗

arXiv2023

Meta-Stock: Task-Difficulty-Adaptive Meta-learning for Sub-new Stock Price Prediction

Sub-new stock price prediction, forecasting the price trends of stocks listed less than one year, is crucial for effective quantitative trading. While deep learning methods have demonstrated effectiveness in predicting old stock prices, they require large training datasets unavailable for sub-new stocks. In this paper, we propose Meta-Stock: a task-difficulty-adaptive meta-learning approach for sub-new stock price prediction. Leveraging prediction tasks formulated by old stocks, our meta-learning method aims to acquire the fast generalization ability that can be further adapted to sub-new stock price prediction tasks, thereby solving the data scarcity of sub-new stocks. Moreover, we enhance the meta-learning process by incorporating an adaptive learning strategy sensitive to varying task difficulties. Through wavelet transform, we extract high-frequency coefficients to manifest stock price volatility. This allows the meta-learning model to assign gradient weights based on volatility-quantified task difficulty. Extensive experiments on datasets collected from three stock markets spanning twenty-two years prove that our Meta-Stock significantly outperforms previous methods and manifests strong applicability in real-world stock trading. Besides, we evaluate the reasonability of the task difficulty quantification and the effectiveness of the adaptive learning strategy.

cs.CE↗

arXiv2023

Low-Light Image Enhancement with Illumination-Aware Gamma Correction and Complete Image Modelling Network

This paper presents a novel network structure with illumination-aware gamma correction and complete image modelling to solve the low-light image enhancement problem. Low-light environments usually lead to less informative large-scale dark areas, directly learning deep representations from low-light images is insensitive to recovering normal illumination. We propose to integrate the effectiveness of gamma correction with the strong modelling capacities of deep networks, which enables the correction factor gamma to be learned in a coarse to elaborate manner via adaptively perceiving the deviated illumination. Because exponential operation introduces high computational complexity, we propose to use Taylor Series to approximate gamma correction, accelerating the training and inference speed. Dark areas usually occupy large scales in low-light images, common local modelling structures, e.g., CNN, SwinIR, are thus insufficient to recover accurate illumination across whole low-light images. We propose a novel Transformer block to completely simulate the dependencies of all pixels across images via a local-to-global hierarchical attention mechanism, so that dark areas could be inferred by borrowing the information from far informative regions in a highly effective manner. Extensive experiments on several benchmark datasets demonstrate that our approach outperforms state-of-the-art methods.

cs.CV↗

arXiv2023

Minimum Latency Deep Online Video Stabilization

We present a novel camera path optimization framework for the task of online video stabilization. Typically, a stabilization pipeline consists of three steps: motion estimating, path smoothing, and novel view rendering. Most previous methods concentrate on motion estimation, proposing various global or local motion models. In contrast, path optimization receives relatively less attention, especially in the important online setting, where no future frames are available. In this work, we adopt recent off-the-shelf high-quality deep motion models for motion estimation to recover the camera trajectory and focus on the latter two steps. Our network takes a short 2D camera path in a sliding window as input and outputs the stabilizing warp field of the last frame in the window, which warps the coming frame to its stabilized position. A hybrid loss is well-defined to constrain the spatial and temporal consistency. In addition, we build a motion dataset that contains stable and unstable motion pairs for the training. Extensive experiments demonstrate that our approach significantly outperforms state-of-the-art online methods both qualitatively and quantitatively and achieves comparable performance to offline methods. Our code and dataset are available at https://github.com/liuzhen03/NNDVS

cs.CV↗

arXiv2023

Self-supervised Learning and Graph Classification under Heterophily

Self-supervised learning has shown its promising capability in graph representation learning in recent work. Most existing pre-training strategies usually choose the popular Graph neural networks (GNNs), which can be seen as a special form of low-pass filter, fail to effectively capture heterophily. In this paper, we first present an experimental investigation exploring the performance of low-pass and high-pass filters in heterophily graph classification, where the results clearly show that high-frequency signal is important for learning heterophily graph representation. On the other hand, it is still unclear how to effectively capture the structural pattern of graphs and how to measure the capability of the self-supervised pre-training strategy in capturing graph structure. To address the problem, we first design a quantitative metric to Measure Graph Structure (MGS), which analyzes correlation between structural similarity and embedding similarity of graph pairs. Then, to enhance the graph structural information captured by self-supervised learning, we propose a novel self-supervised strategy for Pre-training GNNs based on the Metric (PGM). Extensive experiments validate our pre-training strategy achieves state-of-the-art performance for molecular property prediction and protein function prediction. In addition, we find choosing the suitable filter sometimes may be better than designing good pre-training strategies for heterophily graph classification.

cs.LG↗

arXiv2023

Heavy Neutral Leptons from Stopped Muons and Pions

Stopped muons, which are generic in pion-at-rest experiments, can shed light on heavy neutral leptons (HNLs) in unexplored parameter spaces. If the HNL is lighter than the muon, the HNL can be produced from decays of muons and pions.The HNL will travel from the production location and decay into visible Standard Model (SM) modes, leaving signals inside downstream detectors. We find that in the case that the HNL dominantly mixes with muon neutrinos, the LSND constraint on the mixing angle squared is stronger than all the previous constraints by more than an order of magnitude. In this study, we recast the LSND measurement of the $ν-e$ scattering. Future experiments such as PIP2-BD could further improve the sensitivity, provided they can distinguish the HNL events from backgrounds induced by the SM neutrinos.

hep-ph↗