Searcharxiv⌕ Search

arXiv subjects

Hang Zhang

Publications and source records attributed to Hang Zhang.

At least 163 records · Page 9Linked to original sources
arXiv2024

Slicer Networks

In medical imaging, scans often reveal objects with varied contrasts but consistent internal intensities or textures. This characteristic enables the use of low-frequency approximations for tasks such as segmentation and deformation field estimation. Yet, integrating this concept into neural network architectures for medical image analysis remains underexplored. In this paper, we propose the Slicer Network, a novel architecture designed to leverage these traits. Comprising an encoder utilizing models like vision transformers for feature extraction and a slicer employing a learnable bilateral grid, the Slicer Network strategically refines and upsamples feature maps via a splatting-blurring-slicing process. This introduces an edge-preserving low-frequency approximation for the network outcome, effectively enlarging the effective receptive field. The enhancement not only reduces computational complexity but also boosts overall performance. Experiments across different medical imaging applications, including unsupervised and keypoints-based image registration and lesion segmentation, have verified the Slicer Network's improved accuracy and efficiency.

eess.IV↗
arXiv2023

Thermodynamic driving forces in contact electrification between polymeric materials

Contact electrification, or contact charging, refers to the process of static charge accumulation after rubbing, or even simple touching, of two materials. Despite its relevance in static electricity, various natural phenomena, and numerous technologies, contact charging remains poorly understood. For insulating materials, even the species of charge carrier may be unknown, and the direction of charge-transfer lacks firm molecular-level explanation. We use all-atom molecular dynamics simulations to investigate whether thermodynamics can explain contact charging between insulating polymers. Building on prior work implicating water-ions (e.g., hydronium and hydroxide) as potential charge carriers, we predict preferred directions of charge-transfer between polymer surfaces according to the free energy of water-ions within water droplets on such surfaces. Broad agreement between our predictions and experimental triboelectric series indicate that thermodynamically driven ion-transfer likely influences contact charging of polymers. Importantly, simulation analyses reveal how specific interactions of water and water-ions proximate to the polymer-water interface explains observed trends. This study establishes relevance of thermodynamic driving forces in contact charging of insulators with new evidence informed by molecular-level interactions. These insights have direct implications for future mechanistic studies and applications of contact charging involving polymeric materials.

cond-mat.soft↗
arXiv2023

Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decoding

Large Vision-Language Models (LVLMs) have advanced considerably, intertwining visual recognition and language understanding to generate content that is not only coherent but also contextually attuned. Despite their success, LVLMs still suffer from the issue of object hallucinations, where models generate plausible yet incorrect outputs that include objects that do not exist in the images. To mitigate this issue, we introduce Visual Contrastive Decoding (VCD), a simple and training-free method that contrasts output distributions derived from original and distorted visual inputs. The proposed VCD effectively reduces the over-reliance on statistical bias and unimodal priors, two essential causes of object hallucinations. This adjustment ensures the generated content is closely grounded to visual inputs, resulting in contextually accurate outputs. Our experiments show that VCD, without either additional training or the usage of external tools, significantly mitigates the object hallucination issue across different LVLM families. Beyond mitigating object hallucinations, VCD also excels in general LVLM benchmarks, highlighting its wide-ranging applicability.

cs.CV↗
arXiv2023

Noisy Pair Corrector for Dense Retrieval

Most dense retrieval models contain an implicit assumption: the training query-document pairs are exactly matched. Since it is expensive to annotate the corpus manually, training pairs in real-world applications are usually collected automatically, which inevitably introduces mismatched-pair noise. In this paper, we explore an interesting and challenging problem in dense retrieval, how to train an effective model with mismatched-pair noise. To solve this problem, we propose a novel approach called Noisy Pair Corrector (NPC), which consists of a detection module and a correction module. The detection module estimates noise pairs by calculating the perplexity between annotated positive and easy negative documents. The correction module utilizes an exponential moving average (EMA) model to provide a soft supervised signal, aiding in mitigating the effects of noise. We conduct experiments on text-retrieval benchmarks Natural Question and TriviaQA, code-search benchmarks StaQC and SO-DS. Experimental results show that NPC achieves excellent performance in handling both synthetic and realistic noise.

cs.CL↗
arXiv2023

M&M3D: Multi-Dataset Training and Efficient Network for Multi-view 3D Object Detection

In this research, I proposed a network structure for multi-view 3D object detection using camera-only data and a Bird's-Eye-View map. My work is based on a current key challenge domain adaptation and visual data transfer. Although many excellent camera-only 3D object detection has been continuously proposed, many research work risk dramatic performance drop when the networks are trained on the source domain but tested on a different target domain. Then I found it is very surprising that predictions on bounding boxes and classes are still replied to on 2D networks. Based on the domain gap assumption on various 3D datasets, I found they still shared a similar data extraction on the same BEV map size and camera data transfer. Therefore, to analyze the domain gap influence on the current method and to make good use of 3D space information among the dataset and the real world, I proposed a transfer learning method and Transformer construction to study the 3D object detection on NuScenes-mini and Lyft. Through multi-dataset training and a detection head from the Transformer, the network demonstrated good data migration performance and efficient detection performance by using 3D anchor query and 3D positional information. Relying on only a small amount of source data and the existing large model pre-training weights, the efficient network manages to achieve competitive results on the new target domain. Moreover, my study utilizes 3D information as available semantic information and 2D multi-view image features blending into the visual-language transfer design. In the final 3D anchor box prediction and object classification, my network achieved good results on standard metrics of 3D object detection, which differs from dataset-specific models on each training domain without any fine-tuning.

cs.CV↗
arXiv2023

The Phase Transition Phenomenon of Shuffled Regression

We study the phase transition phenomenon inherent in the shuffled (permuted) regression problem, which has found numerous applications in databases, privacy, data analysis, etc. In this study, we aim to precisely identify the locations of the phase transition points by leveraging techniques from message passing (MP). In our analysis, we first transform the permutation recovery problem into a probabilistic graphical model. We then leverage the analytical tools rooted in the message passing (MP) algorithm and derive an equation to track the convergence of the MP algorithm. By linking this equation to the branching random walk process, we are able to characterize the impact of the signal-to-noise-ratio ($\snr$) on the permutation recovery. Depending on whether the signal is given or not, we separately investigate the oracle case and the non-oracle case. The bottleneck in identifying the phase transition regimes lies in deriving closed-form formulas for the corresponding critical points, but only in rare scenarios can one obtain such precise expressions. To tackle this technical challenge, this study proposes the Gaussian approximation method, which allows us to obtain the closed-form formulas in almost all scenarios. In the oracle case, our method can fairly accurately predict the phase transition $\snr$. In the non-oracle case, our algorithm can predict the maximum allowed number of permuted rows and uncover its dependency on the sample number.

stat.ML↗
arXiv2023

CAPSTONE: Curriculum Sampling for Dense Retrieval with Document Expansion

The dual-encoder has become the de facto architecture for dense retrieval. Typically, it computes the latent representations of the query and document independently, thus failing to fully capture the interactions between the query and document. To alleviate this, recent research has focused on obtaining query-informed document representations. During training, it expands the document with a real query, but during inference, it replaces the real query with a generated one. This inconsistency between training and inference causes the dense retrieval model to prioritize query information while disregarding the document when computing the document representation. Consequently, it performs even worse than the vanilla dense retrieval model because its performance heavily relies on the relevance between the generated queries and the real query.In this paper, we propose a curriculum sampling strategy that utilizes pseudo queries during training and progressively enhances the relevance between the generated query and the real query. By doing so, the retrieval model learns to extend its attention from the document alone to both the document and query, resulting in high-quality query-informed document representations. Experimental results on both in-domain and out-of-domain datasets demonstrate that our approach outperforms previous dense retrieval models.

cs.CL↗
arXiv2023

Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding

We present Video-LLaMA a multi-modal framework that empowers Large Language Models (LLMs) with the capability of understanding both visual and auditory content in the video. Video-LLaMA bootstraps cross-modal training from the frozen pre-trained visual and audio encoders and the frozen LLMs. Unlike previous works that complement LLMs to process the visual or audio signals only, Video-LLaMA enables video comprehension by tackling two challenges: (1) capturing the temporal changes in visual scenes, (2) integrating audio-visual signals. To counter the first challenge, we propose a Video Q-former to assemble a pre-trained image encoder into our video encoder and introduce a video-to-text generation task to learn video-language correspondence. For the second challenge, we leverage ImageBind, a universal embedding model aligning multiple modalities, as the pre-trained audio encoder and introduce an Audio Q-former on top of ImageBind to learn reasonable auditory query embeddings for the LLM module. To align the output of both visual and audio encoders with LLM's embedding space, we first train Video-LLaMA on massive video/image-caption pairs and then tune our model with visual-instruction datasets of moderate amount but higher quality. We found Video-LLaMA shows the ability to perceive and comprehend video content and generate meaningful responses grounded in the visual and auditory information presented in the videos.

cs.CL↗
arXiv2023

Optimal Estimator for Linear Regression with Shuffled Labels

This paper considers the task of linear regression with shuffled labels, i.e., $\mathbf Y = \mathbf Π\mathbf X \mathbf B + \mathbf W$, where $\mathbf Y \in \mathbb R^{n\times m}, \mathbf Pi \in \mathbb R^{n\times n}, \mathbf X\in \mathbb R^{n\times p}, \mathbf B \in \mathbb R^{p\times m}$, and $\mathbf W\in \mathbb R^{n\times m}$, respectively, represent the sensing results, (unknown or missing) corresponding information, sensing matrix, signal of interest, and additive sensing noise. Given the observation $\mathbf Y$ and sensing matrix $\mathbf X$, we propose a one-step estimator to reconstruct $(\mathbf Π, \mathbf B)$. From the computational perspective, our estimator's complexity is $O(n^3 + np^2m)$, which is no greater than the maximum complexity of a linear assignment algorithm (e.g., $O(n^3)$) and a least square algorithm (e.g., $O(np^2 m)$). From the statistical perspective, we divide the minimum $snr$ requirement into four regimes, e.g., unknown, hard, medium, and easy regimes; and present sufficient conditions for the correct permutation recovery under each regime: $(i)$ $snr \geq Ω(1)$ in the easy regime; $(ii)$ $snr \geq Ω(\log n)$ in the medium regime; and $(iii)$ $snr \geq Ω((\log n)^{c_0}\cdot n^{{c_1}/{srank(\mathbf B)}})$ in the hard regime ($c_0, c_1$ are some positive constants and $srank(\mathbf B)$ denotes the stable rank of $\mathbf B$). In the end, we also provide numerical experiments to confirm the above claims.

stat.ML↗
arXiv2023

Unidirectional guided-wave-driven metasurfaces for arbitrary wavefront control

Metasurfaces, composed of subwavelength electromagnetic microstructures, known as meta-atoms, are capable of reshaping the wavefronts of incident beams in desired manners, making them great candidates for revolutionizing conventional optics. However, the requirement for external light excitation and the resonant nature of meta-atoms make it difficult to fully integrate metasurfaces on-chip or to control wavefronts at deep-subwavelength scales. Here, we introduce the concept and design of a new class of metasurfaces, driven by unidirectional guided waves, and being capable of arbitrary wavefront control based on the unique dispersion properties of unidirectional guided waves rather than resonant meta-atoms. Upon experimentally demonstrating the feasibility and practicality of the unidirectional nature of our designs in the microwave regime, we numerically validate this new principle through the design of several microwave meta-devices using metal-air-gyromagnetic unidirectional surface magnetoplamons, agilely converting unidirectional guided modes into the wavefronts of 3D Bessel beams, focused waves, and controllable vortex beams. We also numerically demonstrate sub-diffraction focusing, which is currently beyond the capability of conventional metasurfaces. Furthermore, we directly show how these concepts can be transferred to the terahertz regime, and discuss their feasibility in the optical domain, too. Based on this nonresonant (that is, broadband) mechanism and on standard plasmonic platforms, our metasurfaces can be integrated on-chip, enabling the manipulation of electromagnetic waves on deep subwavelength scales and over wide frequency ranges, thereby opening up new opportunities for applications in communications, remote sensing, displays, and so forth.

physics.optics↗
arXiv2023

Is Bio-Inspired Learning Better than Backprop? Benchmarking Bio Learning vs. Backprop

Bio-inspired learning has been gaining popularity recently given that Backpropagation (BP) is not considered biologically plausible. Many algorithms have been proposed in the literature which are all more biologically plausible than BP. However, apart from overcoming the biological implausibility of BP, a strong motivation for using Bio-inspired algorithms remains lacking. In this study, we undertake a holistic comparison of BP vs. multiple Bio-inspired algorithms to answer the question of whether Bio-learning offers additional benefits over BP. We test Bio-algorithms under different design choices such as access to only partial training data, resource constraints in terms of the number of training epochs, sparsification of the neural network parameters and addition of noise to input samples. Through these experiments, we notably find two key advantages of Bio-algorithms over BP. Firstly, Bio-algorithms perform much better than BP when the entire training dataset is not supplied. Four of the five Bio-algorithms tested outperform BP by upto 5% accuracy when only 20% of the training dataset is available. Secondly, even when the full dataset is available, Bio-algorithms learn much quicker and converge to a stable accuracy in far lesser training epochs than BP. Hebbian learning, specifically, is able to learn in just 5 epochs compared to around 100 epochs required by BP. These insights present practical reasons for utilising Bio-learning beyond just their biological plausibility and also point towards interesting new directions for future work on Bio-learning.

cs.LG↗
arXiv2023

PROD: Progressive Distillation for Dense Retrieval

Knowledge distillation is an effective way to transfer knowledge from a strong teacher to an efficient student model. Ideally, we expect the better the teacher is, the better the student. However, this expectation does not always come true. It is common that a better teacher model results in a bad student via distillation due to the nonnegligible gap between teacher and student. To bridge the gap, we propose PROD, a PROgressive Distillation method, for dense retrieval. PROD consists of a teacher progressive distillation and a data progressive distillation to gradually improve the student. We conduct extensive experiments on five widely-used benchmarks, MS MARCO Passage, TREC Passage 19, TREC Document 19, MS MARCO Document and Natural Questions, where PROD achieves the state-of-the-art within the distillation methods for dense retrieval. The code and models will be released.

cs.IR↗
arXiv2023

DAGrid: Directed Accumulator Grid

Recent research highlights that the Directed Accumulator (DA), through its parametrization of geometric priors into neural networks, has notably improved the performance of medical image recognition, particularly with small and imbalanced datasets. However, DA's potential in pixel-wise dense predictions is unexplored. To bridge this gap, we present the Directed Accumulator Grid (DAGrid), which allows geometric-preserving filtering in neural networks, thus broadening the scope of DA's applications to include pixel-level dense prediction tasks. DAGrid utilizes homogeneous data types in conjunction with designed sampling grids to construct geometrically transformed representations, retaining intricate geometric information and promoting long-range information propagation within the neural networks. Contrary to its symmetric counterpart, grid sampling, which might lose information in the sampling process, DAGrid aggregates all pixels, ensuring a comprehensive representation in the transformed space. The parallelization of DAGrid on modern GPUs is facilitated using CUDA programming, and also back propagation is enabled for deep neural network training. Empirical results show DAGrid-enhanced neural networks excel in supervised skin lesion segmentation and unsupervised cardiac image registration. Specifically, the network incorporating DAGrid has realized a 70.8% reduction in network parameter size and a 96.8% decrease in FLOPs, while concurrently improving the Dice score for skin lesion segmentation by 1.0% compared to state-of-the-art transformers. Furthermore, it has achieved improvements of 4.4% and 8.2% in the average Dice score and Dice score of the left ventricular mass, respectively, indicating an increase in registration accuracy for cardiac images. The source code is available at https://github.com/tinymilky/DeDA.

cs.CV↗
arXiv2023

mcLARO: Multi-Contrast Learned Acquisition and Reconstruction Optimization for simultaneous quantitative multi-parametric mapping

Purpose: To develop a method for rapid sub-millimeter T1, T2, T2* and QSM mapping in a single scan using multi-contrast Learned Acquisition and Reconstruction Optimization (mcLARO). Methods: A pulse sequence was developed by interleaving inversion recovery and T2 magnetization preparations and single-echo and multi-echo gradient echo acquisitions, which sensitized k-space data to T1, T2, T2* and magnetic susceptibility. The proposed mcLARO used a deep learning framework to optimize both the multi-contrast k-space under-sampling pattern and the image reconstruction based on image feature fusion. The proposed mcLARO method with R=8 under-sampling was validated in a retrospective ablation study using fully sampled data as reference and evaluated in a prospective study using separately acquired conventionally sampled quantitative maps as reference standard. Results: The retrospective ablation study showed improved image sharpness of mcLARO compared to the baseline network without multi-contrast sampling pattern optimization or image feature fusion, and negligible bias and narrow 95% limits of agreement on regional T1, T2, T2* and QSM values were obtained by the under-sampled reconstructions compared to the fully sampled reconstruction. The prospective study showed small or negligible bias and narrow 95% limits of agreement on regional T1, T2, T2* and QSM values by mcLARO (5:39 mins) compared to reference scans (40:03 mins in total). Conclusion: mcLARO enabled fast sub-millimeter T1, T2, T2* and QSM mapping in a single scan.

eess.IV↗
arXiv2023

Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP

Open-vocabulary semantic segmentation aims to segment an image into semantic regions according to text descriptions, which may not have been seen during training. Recent two-stage methods first generate class-agnostic mask proposals and then leverage pre-trained vision-language models, e.g., CLIP, to classify masked regions. We identify the performance bottleneck of this paradigm to be the pre-trained CLIP model, since it does not perform well on masked images. To address this, we propose to finetune CLIP on a collection of masked image regions and their corresponding text descriptions. We collect training data by mining an existing image-caption dataset (e.g., COCO Captions), using CLIP to match masked image regions to nouns in the image captions. Compared with the more precise and manually annotated segmentation labels with fixed classes (e.g., COCO-Stuff), we find our noisy but diverse dataset can better retain CLIP's generalization ability. Along with finetuning the entire model, we utilize the "blank" areas in masked images using a method we dub mask prompt tuning. Experiments demonstrate mask prompt tuning brings significant improvement without modifying any weights of CLIP, and it can further improve a fully finetuned model. In particular, when trained on COCO and evaluated on ADE20K-150, our best model achieves 29.6% mIoU, which is +8.5% higher than the previous state-of-the-art. For the first time, open-vocabulary generalist models match the performance of supervised specialist models in 2017 without dataset-specific adaptations.

cs.CV↗
arXiv2023

Sparse Recovery with Shuffled Labels: Statistical Limits and Practical Estimators

This paper considers the sparse recovery with shuffled labels, i.e., $\by = \bPitrue \bX \bbetatrue + \bw$, where $\by \in \RR^n$, $\bPi\in \RR^{n\times n}$, $\bX\in \RR^{n\times p}$, $\bbetatrue\in \RR^p$, $\bw \in \RR^n$ denote the sensing result, the unknown permutation matrix, the design matrix, the sparse signal, and the additive noise, respectively. Our goal is to reconstruct both the permutation matrix $\bPitrue$ and the sparse signal $\bbetatrue$. We investigate this problem from both the statistical and computational aspects. From the statistical aspect, we first establish the minimax lower bounds on the sample number $n$ and the \emph{signal-to-noise ratio} ($\snr$) for the correct recovery of permutation matrix $\bPitrue$ and the support set $\supp(\bbetatrue)$, to be more specific, $n \gtrsim k\log p$ and $\log\snr \gtrsim \log n + \frac{k\log p}{n}$. Then, we confirm the tightness of these minimax lower bounds by presenting an exhaustive-search based estimator whose performance matches the lower bounds thereof up to some multiplicative constants. From the computational aspect, we impose a parsimonious assumption on the number of permuted rows and propose a computationally-efficient estimator accordingly. Moreover, we show that our proposed estimator can obtain the ground-truth $(\bPitrue, \supp(\bbetatrue))$ under mild conditions. Furthermore, we provide numerical experiments to corroborate our claims.

cs.IT↗
arXiv2023

Backward Reachability Analysis of Neural Feedback Systems Using Hybrid Zonotopes

The proliferation of neural networks in safety-critical applications necessitates the development of effective methods to ensure their safety. This letter presents a novel approach for computing the exact backward reachable sets of neural feedback systems based on hybrid zonotopes. It is shown that the input-output relationship imposed by a ReLU-activated neural network can be exactly described by a hybrid zonotope-represented graph set. Based on that, the one-step exact backward reachable set of a neural feedback system is computed as a hybrid zonotope in the closed form. In addition, a necessary and sufficient condition is formulated as a mixed-integer linear program to certify whether the trajectories of a neural feedback system can avoid unsafe regions in finite time. Numerical examples are provided to demonstrate the efficiency of the proposed approach.

math.OC↗
arXiv2023

DeDA: Deep Directed Accumulator

Chronic active multiple sclerosis lesions, also termed as rim+ lesions, can be characterized by a hyperintense rim at the edge of the lesion on quantitative susceptibility maps. These rim+ lesions exhibit a geometrically simple structure, where gradients at the lesion edge are radially oriented and a greater magnitude of gradients is observed in contrast to rim- (non rim+) lesions. However, recent studies have shown that the identification performance of such lesions remains unsatisfied due to the limited amount of data and high class imbalance. In this paper, we propose a simple yet effective image processing operation, deep directed accumulator (DeDA), that provides a new perspective for injecting domain-specific inductive biases (priors) into neural networks for rim+ lesion identification. Given a feature map and a set of sampling grids, DeDA creates and quantizes an accumulator space into finite intervals, and accumulates feature values accordingly. This DeDA operation is a generalized discrete Radon transform and can also be regarded as a symmetric operation to the grid sampling within the forward-backward neural network framework, the process of which is order-agnostic, and can be efficiently implemented with the native CUDA programming. Experimental results on a dataset with 177 rim+ and 3986 rim- lesions show that 10.1% of improvement in a partial (false positive rate<0.1) area under the receiver operating characteristic curve (pROC AUC) and 10.2% of improvement in an area under the precision recall curve (PR AUC) can be achieved respectively comparing to other state-of-the-art methods. The source code is available online at https://github.com/tinymilky/DeDA

eess.IV↗