arXiv subjects

Han Wu

Publications and source records attributed to Han Wu.

At least 109 records · Page 6Linked to original sources

arXiv2024

Cephalometric Landmark Detection across Ages with Prototypical Network

Automated cephalometric landmark detection is crucial in real-world orthodontic diagnosis. Current studies mainly focus on only adult subjects, neglecting the clinically crucial scenario presented by adolescents whose landmarks often exhibit significantly different appearances compared to adults. Hence, an open question arises about how to develop a unified and effective detection algorithm across various age groups, including adolescents and adults. In this paper, we propose CeLDA, the first work for Cephalometric Landmark Detection across Ages. Our method leverages a prototypical network for landmark detection by comparing image features with landmark prototypes. To tackle the appearance discrepancy of landmarks between age groups, we design new strategies for CeLDA to improve prototype alignment and obtain a holistic estimation of landmark prototypes from a large set of training images. Moreover, a novel prototype relation mining paradigm is introduced to exploit the anatomical relations between the landmark prototypes. Extensive experiments validate the superiority of CeLDA in detecting cephalometric landmarks on both adult and adolescent subjects. To our knowledge, this is the first effort toward developing a unified solution and dataset for cephalometric landmark detection across age groups. Our code and dataset will be made public on https://github.com/ShanghaiTech-IMPACT/Cephalometric-Landmark-Detection-across-Ages-with-Prototypical-Network

cs.CV↗

arXiv2024

GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer

Cross-modal transformers have demonstrated superiority in various vision tasks by effectively integrating different modalities. This paper first critiques prior token exchange methods which replace less informative tokens with inter-modal features, and demonstrate exchange based methods underperform cross-attention mechanisms, while the computational demand of the latter inevitably restricts its use with longer sequences. To surmount the computational challenges, we propose GeminiFusion, a pixel-wise fusion approach that capitalizes on aligned cross-modal representations. GeminiFusion elegantly combines intra-modal and inter-modal attentions, dynamically integrating complementary information across modalities. We employ a layer-adaptive noise to adaptively control their interplay on a per-layer basis, thereby achieving a harmonized fusion process. Notably, GeminiFusion maintains linear complexity with respect to the number of input tokens, ensuring this multimodal framework operates with efficiency comparable to unimodal networks. Comprehensive evaluations across multimodal image-to-image translation, 3D object detection and arbitrary-modal semantic segmentation tasks, including RGB, depth, LiDAR, event data, etc. demonstrate the superior performance of our GeminiFusion against leading-edge techniques. The PyTorch code is available at https://github.com/JiaDingCN/GeminiFusion

cs.CV↗

arXiv2024

NiteDR: Nighttime Image De-Raining with Cross-View Sensor Cooperative Learning for Dynamic Driving Scenes

In real-world environments, outdoor imaging systems are often affected by disturbances such as rain degradation. Especially, in nighttime driving scenes, insufficient and uneven lighting shrouds the scenes in darkness, resulting degradation of both the image quality and visibility. Particularly, in the field of autonomous driving, the visual perception ability of RGB sensors experiences a sharp decline in such harsh scenarios. Additionally, driving assistance systems suffer from reduced capabilities in capturing and discerning the surrounding environment, posing a threat to driving safety. Single-view information captured by single-modal sensors cannot comprehensively depict the entire scene. To address these challenges, we developed an image de-raining framework tailored for rainy nighttime driving scenes. It aims to remove rain artifacts, enrich scene representation, and restore useful information. Specifically, we introduce cooperative learning between visible and infrared images captured by different sensors. By cross-view fusion of these multi-source data, the scene within the images gains richer texture details and enhanced contrast. We constructed an information cleaning module called CleanNet as the first stage of our framework. Moreover, we designed an information fusion module called FusionNet as the second stage to fuse the clean visible images with infrared images. Using this stage-by-stage learning strategy, we obtain de-rained fusion images with higher quality and better visual perception. Extensive experiments demonstrate the effectiveness of our proposed Cross-View Cooperative Learning (CVCL) in adverse driving scenarios in low-light rainy environments. The proposed approach addresses the gap in the utilization of existing rain removal algorithms in specific low-light conditions.

cs.CV↗

arXiv2024

Ultralarge polarization in ferroelectric hafnia-based thin films

Hafnia-based ferroelectrics have become a valuable class of electronic functional materials at the nanoscale, showing great potential for next-generation memory and logic devices. However, more robust ferroelectric properties and better understanding of the polarization mechanisms are currently needed both in technology and science. Herein, we report the properties of oxygen-deficient Hf0.5Zr0.5O2 films with ultralarge remanent polarization (Pr) of 387 uC cm-2 at room temperature (1 kHz). Structure characterizations identify a new ferroelectric monoclinic Pc phase in these Hf0.5Zr0.5O2 films. The in-situ STEM measurements evidence polar displacements of the oxygen atoms, which move up and down in the Pc structure under applied DC bias fields, showing a huge displacement (1.6 A). DFT calculations optimized the Pc structure and also predicted a large polarization. The coexistence of the ferroelectric monoclinic (Pc) phases and orthorhombic (Pca21) is responsible for this superior ferroelectric properties. These findings are promising for hafnia-based ferroelectric applications in integrated ferroelectric devices, energy harvesting and actuators, etc.

cond-mat.mtrl-sci↗

arXiv2024

Mid-infrared computational temporal ghost imaging

Ghost imaging in the time domain allows for reconstructing fast temporal objects using a slow photodetector. The technique involves correlating random or pre-programmed probing temporal intensity patterns with the integrated signal measured after modulation by the temporal object. However, the implementation of temporal ghost imaging necessitates ultrafast detectors or modulators for measuring or pre-programming the probing intensity patterns, which is not universally available in all spectral regions especially in the mid-infrared range. Here, we demonstrate a frequency downconversion temporal ghost imaging scheme that enables to extend the operation regime to arbitrary wavelengths regions where fast modulators and detectors are not available. The approach modulates a signal with temporal intensity patterns in the near-infrared and transfers the patterns to an idler via difference-frequency generation at the wavelength of the temporal object to be retrieved. As a proof-of-concept, we demonstrate temporal ghost imaging in the mid-infrared. The scheme is flexible and introduces new possibilities for scan-free pump-probe imaging and the study of ultrafast dynamics in spectral regions where ultrafast modulation or detection is challenging such as the mid-infrared and THz regions.

physics.optics↗

arXiv2024

Theoretical demonstration of mode transmission in ZGP-based micrometer waveguide platforms

Birefringence phase-matching based \c{hi}(2) ZnGeP2 (ZGP) waveguide platform has been recently reported for excellent mid-infrared laser generation. Here, a detailed theoretical characterization of mode transmission taking waveguide anisotropy and substrate material absorption into account in a micrometer ZGP waveguide platform (ZGP-on-SiO2) is conducted. Benefited from high-index contrast between ZGP and substrate (SiO2/Air), Transverse electric and magnetic (TM and TE) mode transmission loss at interested wavelengths range of 2 - 12 μm is calculated to be less than 4 dB/cm and 1.5 dB/cm, respectively, in the designed ZGP waveguide. Notably, non-obvious oscillation of mode transmission loss versus phase-matching angles is observed, which is different from that in the previously reported weakly guided anisotropic waveguide. A vital phenomenon named mode crossing at some wavelengths in TM polarization is also exhibited in our waveguide platforms, which jeopardizes waveguide performances and could be avoided by changing the phase-matching angle in practice. This work provides a significant indication of ZGP waveguide design optimization in future and also exhibits extendibility to other birefringent crystal waveguide platforms.

physics.optics↗

arXiv2024

SIRST-5K: Exploring Massive Negatives Synthesis with Self-supervised Learning for Robust Infrared Small Target Detection

Single-frame infrared small target (SIRST) detection aims to recognize small targets from clutter backgrounds. Recently, convolutional neural networks have achieved significant advantages in general object detection. With the development of Transformer, the scale of SIRST models is constantly increasing. Due to the limited training samples, performance has not been improved accordingly. The quality, quantity, and diversity of the infrared dataset are critical to the detection of small targets. To highlight this issue, we propose a negative sample augmentation method in this paper. Specifically, a negative augmentation approach is proposed to generate massive negatives for self-supervised learning. Firstly, we perform a sequential noise modeling technology to generate realistic infrared data. Secondly, we fuse the extracted noise with the original data to facilitate diversity and fidelity in the generated data. Lastly, we proposed a negative augmentation strategy to enrich diversity as well as maintain semantic invariance. The proposed algorithm produces a synthetic SIRST-5K dataset, which contains massive pseudo-data and corresponding labels. With a rich diversity of infrared small target data, our algorithm significantly improves the model performance and convergence speed. Compared with other state-of-the-art (SOTA) methods, our method achieves outstanding performance in terms of probability of detection (Pd), false-alarm rate (Fa), and intersection over union (IoU).

cs.CV↗

arXiv2024

Towards Versatile and Efficient Visual Knowledge Integration into Pre-trained Language Models with Cross-Modal Adapters

Humans learn language via multi-modal knowledge. However, due to the text-only pre-training scheme, most existing pre-trained language models (PLMs) are hindered from the multi-modal information. To inject visual knowledge into PLMs, existing methods incorporate either the text or image encoder of vision-language models (VLMs) to encode the visual information and update all the original parameters of PLMs for knowledge fusion. In this paper, we propose a new plug-and-play module, X-adapter, to flexibly leverage the aligned visual and textual knowledge learned in pre-trained VLMs and efficiently inject them into PLMs. Specifically, we insert X-adapters into PLMs, and only the added parameters are updated during adaptation. To fully exploit the potential in VLMs, X-adapters consist of two sub-modules, V-expert and T-expert, to fuse VLMs' image and text representations, respectively. We can opt for activating different sub-modules depending on the downstream tasks. Experimental results show that our method can significantly improve the performance on object-color reasoning and natural language understanding (NLU) tasks compared with PLM baselines.

cs.CL↗

arXiv2024

Data-efficient Large Vision Models through Sequential Autoregression

Training general-purpose vision models on purely sequential visual data, eschewing linguistic inputs, has heralded a new frontier in visual understanding. These models are intended to not only comprehend but also seamlessly transit to out-of-domain tasks. However, current endeavors are hamstrung by an over-reliance on colossal models, exemplified by models with upwards of 3B parameters, and the necessity for an extensive corpus of visual data, often comprising a staggering 400B tokens. In this paper, we delve into the development of an efficient, autoregression-based vision model, innovatively architected to operate on a limited dataset. We meticulously demonstrate how this model achieves proficiency in a spectrum of visual tasks spanning both high-level and low-level semantic understanding during the testing phase. Our empirical evaluations underscore the model's agility in adapting to various tasks, heralding a significant reduction in the parameter footprint, and a marked decrease in training data requirements, thereby paving the way for more sustainable and accessible advancements in the field of generalist vision models. The code is available at https://github.com/ggjy/DeLVM.

cs.CV↗

arXiv2023

Two-Step Electronic Response to Magnetic Ordering in a van der Waals Ferromagnet

The two-dimensional (2D) material Cr$_2$Ge$_2$Te$_6$ is a member of the class of insulating van der Waals magnets. Here, using high resolution angle-resolved photoemission spectroscopy in a detailed temperature dependence study, we identify a clear response of the electronic structure to a dimensional crossover in the form of two distinct temperature scales marking onsets of modifications in the electronic structure. Specifically, we observe Te $p$-orbital-dominated bands to undergo changes at the Curie transition temperature T$_C$ while the Cr $d$-orbital-dominated bands begin evolving at a higher temperature scale. Combined with neutron scattering, density functional theory calculations, and Monte Carlo simulations, we find that the electronic system can be consistently understood to respond sequentially to the distinct temperatures at which in-plane and out-of-plane spin correlations exceed a characteristic length scale. Our findings reveal the sensitivity of the orbital-selective electronic structure for probing the dynamical evolution of local moment correlations in vdW insulating magnets.

cond-mat.str-el↗

arXiv2023

Adversarial Driving: Attacking End-to-End Autonomous Driving

As research in deep neural networks advances, deep convolutional networks become promising for autonomous driving tasks. In particular, there is an emerging trend of employing end-to-end neural network models for autonomous driving. However, previous research has shown that deep neural network classifiers are vulnerable to adversarial attacks. While for regression tasks, the effect of adversarial attacks is not as well understood. In this research, we devise two white-box targeted attacks against end-to-end autonomous driving models. Our attacks manipulate the behavior of the autonomous driving system by perturbing the input image. In an average of 800 attacks with the same attack strength (epsilon=1), the image-specific and image-agnostic attack deviates the steering angle from the original output by 0.478 and 0.111, respectively, which is much stronger than random noises that only perturbs the steering angle by 0.002 (The steering angle ranges from [-1, 1]). Both attacks can be initiated in real-time on CPUs without employing GPUs. Demo video: https://youtu.be/I0i8uN2oOP0.

cs.CV↗

arXiv2023

Adversarial Detection: Attacking Object Detection in Real Time

Intelligent robots rely on object detection models to perceive the environment. Following advances in deep learning security it has been revealed that object detection models are vulnerable to adversarial attacks. However, prior research primarily focuses on attacking static images or offline videos. Therefore, it is still unclear if such attacks could jeopardize real-world robotic applications in dynamic environments. This paper bridges this gap by presenting the first real-time online attack against object detection models. We devise three attacks that fabricate bounding boxes for nonexistent objects at desired locations. The attacks achieve a success rate of about 90% within about 20 iterations. The demo video is available at https://youtu.be/zJZ1aNlXsMU.

cs.AI↗

arXiv2023

Spectral Evidence for Local-Moment Ferromagnetism in van der Waals Metals Fe$_3$GaTe$_2$ and Fe$_3$GeTe$_2$

Magnetism in two-dimensional (2D) materials has attracted considerable attention recently for both fundamental understanding of magnetism and their tunability towards device applications. The isostructural Fe$_3$GeTe$_2$ and Fe$_3$GaTe$_2$ are two members of the Fe-based van der Waals (vdW) ferromagnet family, but exhibit very different Curie temperatures (T$_C$) of 210 K and 360 K, respectively. Here, by using angle-resolved photoemission spectroscopy and density functional theory, we systematically compare the electronic structures of the two compounds. Qualitative similarities in the Fermi surface can be found between the two compounds, with expanded hole pockets in Fe$_3$GaTe$_2$ suggesting additional hole carriers compared to Fe$_3$GeTe$_2$. Interestingly, we observe no band shift in Fe$_3$GaTe$_2$ across its T$_C$ of 360 K, compared to a small shift in Fe$_3$GeTe$_2$ across its T$_C$ of 210 K. The weak temperature-dependent evolution strongly deviates from the expectations of an itinerant Stoner mechanism. Our results suggest that itinerant electrons have minimal contributions to the enhancement of T$_C$ in Fe$_3$GaTe$_2$ compared to Fe$_3$GeTe$_2$, and that the nature of ferromagnetism in these Fe-based vdW ferromagnets must be understood with considerations of the electron correlations.

cond-mat.str-el↗

arXiv2023

Fine-grained Conversational Decoding via Isotropic and Proximal Search

General-purpose text decoding approaches are usually adopted for dialogue response generation. Although the quality of the generated responses can be improved with dialogue-specific encoding methods, conversational decoding methods are still under-explored. Inspired by \citet{wu2023learning} that a good dialogue feature space should follow the rules of locality and isotropy, we present a fine-grained conversational decoding method, termed \textit{isotropic and proximal search (IPS)}. Our method is designed to generate the semantic-concentrated response, while still maintaining informativeness and discrimination against the context. Experiments show that our approach outperforms existing decoding strategies in the dialogue field across both automatic and human evaluation metrics. More in-depth analyses further confirm the effectiveness of our approach.

cs.CL↗

arXiv2023

Qin's Algorithm, Continued Fractions and 2-dimensional Lattices

In his celebrated book "Mathematical Treatise in Nine Sections" of 1247, Qin, Jiushao described the Chinese remainder theorem with great detail and generality. He also gave a method for computing modular inverse under the name of "DaYan deriving one". Historical significance of DaYan deriving one method has been well studied. In this paper, we investigate its modern mathematical nature from the perspectives of number theory and algorithm. One of the remarkable features of Qin's algorithm is that it keeps a state of four variables in a matrix form. Its choice of variables and layout provide natural ways of connecting several important mathematical concepts. An invariant about the state is also observed which provides a convenient yet powerful tool in proving several important mathematical results. The paper first explains Qin's algorithm and proves some of its properties. Then the connection with continued fractions is examined, the results show that the states of Qin's algorithm contain rich information about continued fractions and some classical arguments can be derived easily. The last part of the paper discusses a family of 2-dimensional lattices of number theoretic significance by proving that the shortest vectors of these lattices can be obtained from the states of Qin's algorithm. This result is surprising in that a shortest lattice vector is found in a well-regulated set. A method of computing such shortest vectors is proposed.ed.

math.NT↗

arXiv2023

Reconstruct Before Summarize: An Efficient Two-Step Framework for Condensing and Summarizing Meeting Transcripts

Meetings typically involve multiple participants and lengthy conversations, resulting in redundant and trivial content. To overcome these challenges, we propose a two-step framework, Reconstruct before Summarize (RbS), for effective and efficient meeting summarization. RbS first leverages a self-supervised paradigm to annotate essential contents by reconstructing the meeting transcripts. Secondly, we propose a relative positional bucketing (RPB) algorithm to equip (conventional) summarization models to generate the summary. Despite the additional reconstruction process, our proposed RPB significantly compressed the input, leading to faster processing and reduced memory consumption compared to traditional summarization methods. We validate the effectiveness and efficiency of our method through extensive evaluations and analysis. On two meeting summarization datasets, AMI and ICSI, our approach outperforms previous state-of-the-art approaches without relying on large-scale pre-training or expert-grade annotating tools.

cs.CL↗

arXiv2023

LDRNet: Enabling Real-time Document Localization on Mobile Devices

While Identity Document Verification (IDV) technology on mobile devices becomes ubiquitous in modern business operations, the risk of identity theft and fraud is increasing. The identity document holder is normally required to participate in an online video interview to circumvent impostors. However, the current IDV process depends on an additional human workforce to support online step-by-step guidance which is inefficient and expensive. The performance of existing AI-based approaches cannot meet the real-time and lightweight demands of mobile devices. In this paper, we address those challenges by designing an edge intelligence-assisted approach for real-time IDV. Aiming at improving the responsiveness of the IDV process, we propose a new document localization model for mobile devices, LDRNet, to Localize the identity Document in Real-time. On the basis of a lightweight backbone network, we build three prediction branches for LDRNet, the corner points prediction, the line borders prediction and the document classification. We design novel supplementary targets, the equal-division points, and use a new loss function named Line Loss, to improve the speed and accuracy of our approach. In addition to the IDV process, LDRNet is an efficient and reliable document localization alternative for all kinds of mobile applications. As a matter of proof, we compare the performance of LDRNet with other popular approaches on localizing general document datasets. The experimental results show that LDRNet runs at a speed up to 790 FPS which is 47x faster, while still achieving comparable Jaccard Index(JI) in single-model and single-scale tests.

cs.CV↗

arXiv2023

Multi-View Vertebra Localization and Identification from CT Images

Accurately localizing and identifying vertebrae from CT images is crucial for various clinical applications. However, most existing efforts are performed on 3D with cropping patch operation, suffering from the large computation costs and limited global information. In this paper, we propose a multi-view vertebra localization and identification from CT images, converting the 3D problem into a 2D localization and identification task on different views. Without the limitation of the 3D cropped patch, our method can learn the multi-view global information naturally. Moreover, to better capture the anatomical structure information from different view perspectives, a multi-view contrastive learning strategy is developed to pre-train the backbone. Additionally, we further propose a Sequence Loss to maintain the sequential structure embedded along the vertebrae. Evaluation results demonstrate that, with only two 2D networks, our method can localize and identify vertebrae in CT images accurately, and outperforms the state-of-the-art methods consistently. Our code is available at https://github.com/ShanghaiTech-IMPACT/Multi-View-Vertebra-Localization-and-Identification-from-CT-Images.

eess.IV↗