arXiv subjects

Jian Wang

Publications and source records attributed to Jian Wang.

At least 505 records · Page 28Linked to original sources

arXiv2024

Sagiri: Low Dynamic Range Image Enhancement with Generative Diffusion Prior

Capturing High Dynamic Range (HDR) scenery using 8-bit cameras often suffers from over-/underexposure, loss of fine details due to low bit-depth compression, skewed color distributions, and strong noise in dark areas. Traditional LDR image enhancement methods primarily focus on color mapping, which enhances the visual representation by expanding the image's color range and adjusting the brightness. However, these approaches fail to effectively restore content in dynamic range extremes, which are regions with pixel values close to 0 or 255. To address the full scope of challenges in HDR imaging and surpass the limitations of current models, we propose a novel two-stage approach. The first stage maps the color and brightness to an appropriate range while keeping the existing details, and the second stage utilizes a diffusion prior to generate content in dynamic range extremes lost during capture. This generative refinement module can also be used as a plug-and-play module to enhance and complement existing LDR enhancement models. The proposed method markedly improves the quality and details of LDR images, demonstrating superior performance through rigorous experimental validation. The project page is at https://sagiri0208.github.io

eess.IV↗

arXiv2024

DSL-FIQA: Assessing Facial Image Quality via Dual-Set Degradation Learning and Landmark-Guided Transformer

Generic Face Image Quality Assessment (GFIQA) evaluates the perceptual quality of facial images, which is crucial in improving image restoration algorithms and selecting high-quality face images for downstream tasks. We present a novel transformer-based method for GFIQA, which is aided by two unique mechanisms. First, a Dual-Set Degradation Representation Learning (DSL) mechanism uses facial images with both synthetic and real degradations to decouple degradation from content, ensuring generalizability to real-world scenarios. This self-supervised method learns degradation features on a global scale, providing a robust alternative to conventional methods that use local patch information in degradation learning. Second, our transformer leverages facial landmarks to emphasize visually salient parts of a face image in evaluating its perceptual quality. We also introduce a balanced and diverse Comprehensive Generic Face IQA (CGFIQA-40k) dataset of 40K images carefully designed to overcome the biases, in particular the imbalances in skin tone and gender representation, in existing datasets. Extensive analysis and evaluation demonstrate the robustness of our method, marking a significant improvement over prior methods.

cs.CV↗

arXiv2024

RobustSAM: Segment Anything Robustly on Degraded Images

Segment Anything Model (SAM) has emerged as a transformative approach in image segmentation, acclaimed for its robust zero-shot segmentation capabilities and flexible prompting system. Nonetheless, its performance is challenged by images with degraded quality. Addressing this limitation, we propose the Robust Segment Anything Model (RobustSAM), which enhances SAM's performance on low-quality images while preserving its promptability and zero-shot generalization. Our method leverages the pre-trained SAM model with only marginal parameter increments and computational requirements. The additional parameters of RobustSAM can be optimized within 30 hours on eight GPUs, demonstrating its feasibility and practicality for typical research laboratories. We also introduce the Robust-Seg dataset, a collection of 688K image-mask pairs with different degradations designed to train and evaluate our model optimally. Extensive experiments across various segmentation tasks and datasets confirm RobustSAM's superior performance, especially under zero-shot conditions, underscoring its potential for extensive real-world application. Additionally, our method has been shown to effectively improve the performance of SAM-based downstream tasks such as single image dehazing and deblurring.

cs.CV↗

arXiv2024

Chiral transport in Compact topological waveguide arrays

Waveguide arrays have a wide range of applications, including optical communication, topological systems, and quantum computing. Chiral transport has broad prospects in optical computing, optical switching, optical isolation, and polarization control. However, the lengths of chiral transmission devices in waveguide arrays are typically very long due to adiabatic limit. We introduce topological protection in encircling exceptional points systems, enabling the larger gap size between the bulk states and topological edge states (TESs). Thus, the restriction from adiabatic limit on the rapid evolution of TESs is eased, thereby significantly reducing the device size. We experimentally demonstrate that the chiral transport has been achieved in a topological waveguide array that is only 75 μm long. Our research fuses the topology with non-Hermitian physics to develop highly-integrated photonic chips for further advance of nano-photonics.

physics.optics↗

arXiv2024

LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection

In this paper, we present a light-weight detection transformer, LW-DETR, which outperforms YOLOs for real-time object detection. The architecture is a simple stack of a ViT encoder, a projector, and a shallow DETR decoder. Our approach leverages recent advanced techniques, such as training-effective techniques, e.g., improved loss and pretraining, and interleaved window and global attentions for reducing the ViT encoder complexity. We improve the ViT encoder by aggregating multi-level feature maps, and the intermediate and final feature maps in the ViT encoder, forming richer feature maps, and introduce window-major feature map organization for improving the efficiency of interleaved attention computation. Experimental results demonstrate that the proposed approach is superior over existing real-time detectors, e.g., YOLO and its variants, on COCO and other benchmark datasets. Code and models are available at (https://github.com/Atten4Vis/LW-DETR).

cs.CV↗

arXiv2024

High-Temperature Anomalous Metal States in Iron-Based Interface Superconductors

The nature of the anomalous metal state has been a major puzzle in condensed matter physics for more than three decades. Here, we report systematic investigation and modulation of the anomalous metal states in high-temperature interface superconductor FeSe films on SrTiO3 substrate. Remarkably, under zero magnetic field, the anomalous metal state persists up to 20 K in pristine FeSe films, an exceptionally high temperature standing out from previous observations. In stark contrast, for the FeSe films with nano-hole arrays, the characteristic temperature of the anomalous metal state is considerably reduced. We demonstrate that the observed anomalous metal states originate from the quantum tunneling of vortices adjusted by the Ohmic dissipation. Our work offers a perspective for understanding the origin and modulation of the anomalous metal states in two-dimensional bosonic systems.

cond-mat.supr-con↗

arXiv2024

Intersecting families with large shadow degree

A $k$-uniform family $\mathcal{F}$ is called intersecting if $F\cap F'\neq \emptyset$ for all $F,F'\in \mathcal{F}$. The shadow family $\partial \mathcal{F}$ is the family of $(k-1)$-element sets that are contained in some members of $\mathcal{F}$. The shadow degree (or minimum positive co-degree) of $\mathcal{F}$ is defined as the maximum integer $r$ such that every $E\in \partial \mathcal{F}$ is contained in at least $r$ members of $\mathcal{F}$. In 2021, Balogh, Lemons and Palmer determined the maximum size of an intersecting $k$-uniform family with shadow degree at least $r$ for $n\geq n_0(k,r)$, where $n_0(k,r)$ is doubly exponential in $k$ for $4\leq r\leq k$. In the present paper, we present a short proof of this result for $n\geq 2(r+1)^rk \frac{\binom{2k-1}{k}}{\binom{2r-1}{r}}$ and $4\leq r\leq k$.

math.CO↗

arXiv2024

Multi-state Chiral Switching Through Adiabaticity Control in Encircling Exceptional Points

Dynamic encircling of exceptional points has attracted significant interest in recent years, as it can facilitate chiral transmission selectivity due to a nontrivial eigenstate evolution. Recently, multi-state systems have been explored, associated with more complex topologies supporting a larger number of exceptional points, but chiral switching among multiple eigenstates has remained elusive in experiments. Here, we overcome this challenge by dividing the eigenstate space into multiple subspaces by controlling the adiabaticity. The eigenstates in different subspaces can evolve without crosstalk, and chiral switching occurs as the eigenstates within each subspace are subject to a non-adiabatic transition while they encircle exceptional points. We experimentally demonstrate this phenomenon by reporting chiral switching for two groups of optical modes at telecom wavelengths in a four-state optical system, and theoretically demonstrate that our approach can be extended to higher-order systems. Our findings pave new avenues for studying chiral dynamics based on exceptional-point physics in multi-state systems, and offer opportunities to develop multiplexed photonic devices.

physics.optics↗

arXiv2024

Instruct Once, Chat Consistently in Multiple Rounds: An Efficient Tuning Framework for Dialogue

Tuning language models for dialogue generation has been a prevalent paradigm for building capable dialogue agents. Yet, traditional tuning narrowly views dialogue generation as resembling other language generation tasks, ignoring the role disparities between two speakers and the multi-round interactive process that dialogues ought to be. Such a manner often leads to unsatisfactory chat consistency for the built agent. In this work, we emphasize the interactive, communicative nature of dialogue and argue that it is more feasible to model the speaker roles of agent and user separately, enabling the agent to adhere to its role consistently. With this in mind, we propose an efficient Multi-round Interactive Dialogue Tuning (Midi-Tuning) framework. It models the agent and user individually with two adapters built upon large language models. The adapters make use of respective utterances round by round in alternating order and they are tuned via a round-level memory caching mechanism. Extensive experiments demonstrate that, our framework performs superior to traditional fine-tuning and harbors the tremendous potential for improving dialogue consistency.

cs.CL↗

arXiv2024

MIPI 2024 Challenge on Nighttime Flare Removal: Methods and Results

The increasing demand for computational photography and imaging on mobile platforms has led to the widespread development and integration of advanced image sensors with novel algorithms in camera systems. However, the scarcity of high-quality data for research and the rare opportunity for in-depth exchange of views from industry and academia constrain the development of mobile intelligent photography and imaging (MIPI). Building on the achievements of the previous MIPI Workshops held at ECCV 2022 and CVPR 2023, we introduce our third MIPI challenge including three tracks focusing on novel image sensors and imaging algorithms. In this paper, we summarize and review the Nighttime Flare Removal track on MIPI 2024. In total, 170 participants were successfully registered, and 14 teams submitted results in the final testing phase. The developed solutions in this challenge achieved state-of-the-art performance on Nighttime Flare Removal. More details of this challenge and the link to the dataset can be found at https://mipi-challenge.org/MIPI2024/.

cs.CV↗

arXiv2024

No Two Devils Alike: Unveiling Distinct Mechanisms of Fine-tuning Attacks

The existing safety alignment of Large Language Models (LLMs) is found fragile and could be easily attacked through different strategies, such as through fine-tuning on a few harmful examples or manipulating the prefix of the generation results. However, the attack mechanisms of these strategies are still underexplored. In this paper, we ask the following question: \textit{while these approaches can all significantly compromise safety, do their attack mechanisms exhibit strong similarities?} To answer this question, we break down the safeguarding process of an LLM when encountered with harmful instructions into three stages: (1) recognizing harmful instructions, (2) generating an initial refusing tone, and (3) completing the refusal response. Accordingly, we investigate whether and how different attack strategies could influence each stage of this safeguarding process. We utilize techniques such as logit lens and activation patching to identify model components that drive specific behavior, and we apply cross-model probing to examine representation shifts after an attack. In particular, we analyze the two most representative types of attack approaches: Explicit Harmful Attack (EHA) and Identity-Shifting Attack (ISA). Surprisingly, we find that their attack mechanisms diverge dramatically. Unlike ISA, EHA tends to aggressively target the harmful recognition stage. While both EHA and ISA disrupt the latter two stages, the extent and mechanisms of their attacks differ significantly. Our findings underscore the importance of understanding LLMs' internal safeguarding process and suggest that diverse defense mechanisms are required to effectively cope with various types of attacks.

cs.CL↗

arXiv2024

Generalized all-optical complex exponential operator

Euler's formula, an extraordinary mathematical formula, establishes a vital link between complex-valued operations and trigonometric functions, finding widespread application in various fields. With the end of Moore's Law, electronic computing methods are encountering developmental bottlenecks. With its enviable potential, optical computing has successfully achieved high-speed operation of designed complex numbers. However, the challenge of processing and manipulating arbitrary complex numbers persists. This study introduces a generalized complex exponential operator (GCEO), utilizing a diffractive optical neural network (DONN) for the computation of the complex exponential through Euler's formula. Experiments validate a series of complex exponential calculations using the GCEO. The GCEO has demonstrated generalizability and can compute inputs of any precision within an appropriate error margin. The proposed operator highlights the immense potential of DONN in optical computation and is poised to significantly contribute to the development of computational methods for optoelectronic integration.

physics.optics↗

arXiv2024

Equivariant Twisted Bismut Laplacian with Torsion and KKW type theorems

This paper aims to provide an explicit computation of the noncommutative residue density associated with equivariant twisted Bismut Laplacian with torsion on compact manifolds with (or without) boundary. We prove the equivariant twisted Kastler-Kalau-Walze type theorems with torsion on compact manifolds with boundary.

math.DG↗

arXiv2024

Spatial asymptotic behaviors of fractional stochastic heat equations driven by additive Lévy white noise

We establish explicit integral tests for spatial asymptotic behaviors of fractional stochastic heat equations driven by additive Lévy white noise. Our results indicate that fractional stochastic heat equations enjoy the so-called additive physical intermittent property in all dimensions when the driven Lévy white noise is sufficiently light-tailed. The proofs are based on heat kernel estimates for the fractional Laplacian and exact tail behaviors for Poissonian functionals associated with the driven Lévy white noise.

math.PR↗

arXiv2024

Quantifying the photocurrent fluctuation in quantum materials by shot noise

The DC photocurrent can detect the topology and geometry of quantum materials without inversion symmetry. Herein, we propose that the DC shot noise (DSN), as the fluctuation of photocurrent operator, can also be a diagnostic of quantum materials. Particularly, we develop the quantum theory for DSNs in gapped systems and identify the shift and injection DSNs by dividing the second-order photocurrent operator into off-diagonal and diagonal contributions, respectively. Remarkably, we find that the DSNs can not be forbidden by inversion symmetry, while the constraint from time-reversal symmetry depends on the polarization of light. Furthermore, we show that the DSNs also encode the geometrical information of Bloch electrons, such as the Berry curvature and the quantum metric. Finally, guided by symmetry, we apply our theory to evaluate the DSNs in monolayer GeS and bilayer MoS$_2$ with and without inversion symmetry and find that the DSNs can be larger in centrosymmetric phase.

cond-mat.mtrl-sci↗

arXiv2024

Gapless superconducting state and mirage gap in altermagnets

The interplay between spin-orbit interaction (SOI) and magnetism produces interesting phenomena in superconductors. When a two-dimensional (2D) system with strong SOI is coupled to an $s$-wave superconductor, an in-plane magnetic field can drive the system into a gapless superconducting state and induce a mirage gap at finite energies for an Ising superconductor. In this work, we demonstrate that when an $s$-wave superconductor is proximitized to an altermagnet, the intrinsic anisotropic spin splitting of the altermagnet can result in a gapless superconducting state and a pair of mirage gaps at finite energy. The gapless superconductivity exhibits spin-polarized segmented Fermi surfaces, with coexisting spin-singlet and spin-triplet pairings that have a $d$-wave character. Importantly, the gapless superconducting and mirage gap features are quantified through quantum transport. Our results suggest that altermagnet is an ideal platform for studying gapless superconducting states and mirage gap physics.

cond-mat.supr-con↗

arXiv2024

3D Human Pose Perception from Egocentric Stereo Videos

While head-mounted devices are becoming more compact, they provide egocentric views with significant self-occlusions of the device user. Hence, existing methods often fail to accurately estimate complex 3D poses from egocentric views. In this work, we propose a new transformer-based framework to improve egocentric stereo 3D human pose estimation, which leverages the scene information and temporal context of egocentric stereo videos. Specifically, we utilize 1) depth features from our 3D scene reconstruction module with uniformly sampled windows of egocentric stereo frames, and 2) human joint queries enhanced by temporal features of the video inputs. Our method is able to accurately estimate human poses even in challenging scenarios, such as crouching and sitting. Furthermore, we introduce two new benchmark datasets, i.e., UnrealEgo2 and UnrealEgo-RW (RealWorld). The proposed datasets offer a much larger number of egocentric stereo views with a wider variety of human motions than the existing datasets, allowing comprehensive evaluation of existing and upcoming methods. Our extensive experiments show that the proposed approach significantly outperforms previous methods. We will release UnrealEgo2, UnrealEgo-RW, and trained models on our project page.

cs.CV↗

arXiv2024

Charge-4e and charge-6e flux quantization and higher charge superconductivity in kagome superconductor ring devices

The flux quantization is a key indication of electron pairing in superconductors. For example, the well-known h/2e flux quantization is considered strong evidence for the existence of the charge-2e, two-electron Cooper pairs. Here we report evidence for multi-charge flux quantization in mesoscopic ring devices fabricated using the transition-metal kagome superconductor CsV3Sb5. We perform systematic magneto-transport measurements and observe unprecedented quantization of magnetic flux in units of h/4e and h/6e in magnetoresistance oscillations. Specifically, at low temperatures, magnetoresistance oscillations with period h/2e are detected, as expected from the flux quantization for charge-2e superconductivity. We find that the h/2e oscillations are suppressed and replaced by resistance oscillations with h/4e periodicity when temperature is increased. Increasing the temperature further suppresses the h/4e oscillations and robust resistance oscillations with h/6e periodicity emerge as evidence for charge-6e flux quantization. Our observations provide the first experimental evidence for the existence of multi-charge flux quanta and emergent quantum matter exhibiting higher-charge superconductivity in the strongly fluctuating region above the charge-2e Cooper pair condensate, revealing new insights into the intertwined and vestigial electronic order in kagome superconductors.

cond-mat.supr-con↗