Searcharxiv⌕ Search

arXiv subjects

Dong Xu

Publications and source records attributed to Dong Xu.

At least 145 records · Page 8Linked to original sources
arXiv2024

Diffusion Model is Secretly a Training-free Open Vocabulary Semantic Segmenter

The pre-trained text-image discriminative models, such as CLIP, has been explored for open-vocabulary semantic segmentation with unsatisfactory results due to the loss of crucial localization information and awareness of object shapes. Recently, there has been a growing interest in expanding the application of generative models from generation tasks to semantic segmentation. These approaches utilize generative models either for generating annotated data or extracting features to facilitate semantic segmentation. This typically involves generating a considerable amount of synthetic data or requiring additional mask annotations. To this end, we uncover the potential of generative text-to-image diffusion models (e.g., Stable Diffusion) as highly efficient open-vocabulary semantic segmenters, and introduce a novel training-free approach named DiffSegmenter. The insight is that to generate realistic objects that are semantically faithful to the input text, both the complete object shapes and the corresponding semantics are implicitly learned by diffusion models. We discover that the object shapes are characterized by the self-attention maps while the semantics are indicated through the cross-attention maps produced by the denoising U-Net, forming the basis of our segmentation results.Additionally, we carefully design effective textual prompts and a category filtering mechanism to further enhance the segmentation results. Extensive experiments on three benchmark datasets show that the proposed DiffSegmenter achieves impressive results for open-vocabulary semantic segmentation.

cs.CV↗
arXiv2024

Harnessing Neuron Stability to Improve DNN Verification

Deep Neural Networks (DNN) have emerged as an effective approach to tackling real-world problems. However, like human-written software, DNNs are susceptible to bugs and attacks. This has generated significant interests in developing effective and scalable DNN verification techniques and tools. In this paper, we present VeriStable, a novel extension of recently proposed DPLL-based constraint DNN verification approach. VeriStable leverages the insight that while neuron behavior may be non-linear across the entire DNN input space, at intermediate states computed during verification many neurons may be constrained to have linear behavior - these neurons are stable. Efficiently detecting stable neurons reduces combinatorial complexity without compromising the precision of abstractions. Moreover, the structure of clauses arising in DNN verification problems shares important characteristics with industrial SAT benchmarks. We adapt and incorporate multi-threading and restart optimizations targeting those characteristics to further optimize DPLL-based DNN verification. We evaluate the effectiveness of VeriStable across a range of challenging benchmarks including fully-connected feedforward networks (FNNs), convolutional neural networks (CNNs) and residual networks (ResNets) applied to the standard MNIST and CIFAR datasets. Preliminary results show that VeriStable is competitive and outperforms state-of-the-art DNN verification tools, including $α$-$β$-CROWN and MN-BaB, the first and second performers of the VNN-COMP, respectively.

cs.LG↗
arXiv2024

Inversion-by-Inversion: Exemplar-based Sketch-to-Photo Synthesis via Stochastic Differential Equations without Training

Exemplar-based sketch-to-photo synthesis allows users to generate photo-realistic images based on sketches. Recently, diffusion-based methods have achieved impressive performance on image generation tasks, enabling highly-flexible control through text-driven generation or energy functions. However, generating photo-realistic images with color and texture from sketch images remains challenging for diffusion models. Sketches typically consist of only a few strokes, with most regions left blank, making it difficult for diffusion-based methods to produce photo-realistic images. In this work, we propose a two-stage method named ``Inversion-by-Inversion" for exemplar-based sketch-to-photo synthesis. This approach includes shape-enhancing inversion and full-control inversion. During the shape-enhancing inversion process, an uncolored photo is generated with the guidance of a shape-energy function. This step is essential to ensure control over the shape of the generated photo. In the full-control inversion process, we propose an appearance-energy function to control the color and texture of the final generated photo.Importantly, our Inversion-by-Inversion pipeline is training-free and can accept different types of exemplars for color and texture control. We conducted extensive experiments to evaluate our proposed method, and the results demonstrate its effectiveness. The code and project can be found at https://ximinng.github.io/inversion-by-inversion-project/.

cs.CV↗
arXiv2023

Multi-modality Affinity Inference for Weakly Supervised 3D Semantic Segmentation

3D point cloud semantic segmentation has a wide range of applications. Recently, weakly supervised point cloud segmentation methods have been proposed, aiming to alleviate the expensive and laborious manual annotation process by leveraging scene-level labels. However, these methods have not effectively exploited the rich geometric information (such as shape and scale) and appearance information (such as color and texture) present in RGB-D scans. Furthermore, current approaches fail to fully leverage the point affinity that can be inferred from the feature extraction network, which is crucial for learning from weak scene-level labels. Additionally, previous work overlooks the detrimental effects of the long-tailed distribution of point cloud data in weakly supervised 3D semantic segmentation. To this end, this paper proposes a simple yet effective scene-level weakly supervised point cloud segmentation method with a newly introduced multi-modality point affinity inference module. The point affinity proposed in this paper is characterized by features from multiple modalities (e.g., point cloud and RGB), and is further refined by normalizing the classifier weights to alleviate the detrimental effects of long-tailed distribution without the need of the prior of category distribution. Extensive experiments on the ScanNet and S3DIS benchmarks verify the effectiveness of our proposed method, which outperforms the state-of-the-art by ~4% to ~6% mIoU. Codes are released at https://github.com/Sunny599/AAAI24-3DWSSG-MMA.

cs.CV↗
arXiv2023

UFDA: Universal Federated Domain Adaptation with Practical Assumptions

Conventional Federated Domain Adaptation (FDA) approaches usually demand an abundance of assumptions, which makes them significantly less feasible for real-world situations and introduces security hazards. This paper relaxes the assumptions from previous FDAs and studies a more practical scenario named Universal Federated Domain Adaptation (UFDA). It only requires the black-box model and the label set information of each source domain, while the label sets of different source domains could be inconsistent, and the target-domain label set is totally blind. Towards a more effective solution for our newly proposed UFDA scenario, we propose a corresponding methodology called Hot-Learning with Contrastive Label Disambiguation (HCLD). It particularly tackles UFDA's domain shifts and category gaps problems by using one-hot outputs from the black-box models of various source domains. Moreover, to better distinguish the shared and unknown classes, we further present a cluster-level strategy named Mutual-Voting Decision (MVD) to extract robust consensus knowledge across peer classes from both source and target domains. Extensive experiments on three benchmark datasets demonstrate that our method achieves comparable performance for our UFDA scenario with much fewer assumptions, compared to previous methodologies with comprehensive additional assumptions.

cs.LG↗
arXiv2023

Adapting Segment Anything Model (SAM) through Prompt-based Learning for Enhanced Protein Identification in Cryo-EM Micrographs

Cryo-electron microscopy (cryo-EM) remains pivotal in structural biology, yet the task of protein particle picking, integral for 3D protein structure construction, is laden with manual inefficiencies. While recent AI tools such as Topaz and crYOLO are advancing the field, they do not fully address the challenges of cryo-EM images, including low contrast, complex shapes, and heterogeneous conformations. This study explored prompt-based learning to adapt the state-of-the-art image segmentation foundation model Segment Anything Model (SAM) for cryo-EM. This focus was driven by the desire to optimize model performance with a small number of labeled data without altering pre-trained parameters, aiming for a balance between adaptability and foundational knowledge retention. Through trials with three prompt-based learning strategies, namely head prompt, prefix prompt, and encoder prompt, we observed enhanced performance and reduced computational requirements compared to the fine-tuning approach. This work not only highlights the potential of prompting SAM in protein identification from cryo-EM micrographs but also suggests its broader promise in biomedical image segmentation and object detection.

cs.CV↗
arXiv2023

Large AI Models in Health Informatics: Applications, Challenges, and the Future

Large AI models, or foundation models, are models recently emerging with massive scales both parameter-wise and data-wise, the magnitudes of which can reach beyond billions. Once pretrained, large AI models demonstrate impressive performance in various downstream tasks. A prime example is ChatGPT, whose capability has compelled people's imagination about the far-reaching influence that large AI models can have and their potential to transform different domains of our lives. In health informatics, the advent of large AI models has brought new paradigms for the design of methodologies. The scale of multi-modal data in the biomedical and health domain has been ever-expanding especially since the community embraced the era of deep learning, which provides the ground to develop, validate, and advance large AI models for breakthroughs in health-related areas. This article presents a comprehensive review of large AI models, from background to their applications. We identify seven key sectors in which large AI models are applicable and might have substantial influence, including 1) bioinformatics; 2) medical diagnosis; 3) medical imaging; 4) medical informatics; 5) medical education; 6) public health; and 7) medical robotics. We examine their challenges, followed by a critical discussion about potential future directions and pitfalls of large AI models in transforming the field of health informatics.

cs.AI↗
arXiv2023

Bid Optimization for Offsite Display Ad Campaigns on eCommerce

Online retailers often use third-party demand-side-platforms (DSPs) to conduct offsite advertising and reach shoppers across the Internet on behalf of their advertisers. The process involves the retailer participating in instant auctions with real-time bidding for each ad slot of their interest. In this paper, we introduce a bid optimization system that leverages the dimensional bidding function provided by most well-known DSPs for Walmart offsite display ad campaigns. The system starts by automatically searching for the optimal segmentation of the ad requests space based on their characteristics such as geo location, time, ad format, serving website, device type, etc. Then, it assesses the quality of impressions observed from each dimension based on revenue signals driven by the campaign effect. During the campaign, the system iteratively approximates the bid landscape based on the data observed and calculates the bid adjustments for each dimension. Finally, a higher bid adjustment factor is applied to dimensions with potentially higher revenue over ad spend (ROAS), and vice versa. The initial A/B test results of the proposed optimization system has shown its effectiveness of increasing the ROAS and conversion rate while reducing the effective cost per mille for ad serving.

eess.SY↗
arXiv2023

Distortion-aware Transformer in 360° Salient Object Detection

With the emergence of VR and AR, 360° data attracts increasing attention from the computer vision and multimedia communities. Typically, 360° data is projected into 2D ERP (equirectangular projection) images for feature extraction. However, existing methods cannot handle the distortions that result from the projection, hindering the development of 360-data-based tasks. Therefore, in this paper, we propose a Transformer-based model called DATFormer to address the distortion problem. We tackle this issue from two perspectives. Firstly, we introduce two distortion-adaptive modules. The first is a Distortion Mapping Module, which guides the model to pre-adapt to distorted features globally. The second module is a Distortion-Adaptive Attention Block that reduces local distortions on multi-scale features. Secondly, to exploit the unique characteristics of 360° data, we present a learnable relation matrix and use it as part of the positional embedding to further improve performance. Extensive experiments are conducted on three public datasets, and the results show that our model outperforms existing 2D SOD (salient object detection) and 360 SOD methods.

cs.CV↗
arXiv2023

VideoControlNet: A Motion-Guided Video-to-Video Translation Framework by Using Diffusion Model with ControlNet

Recently, diffusion models like StableDiffusion have achieved impressive image generation results. However, the generation process of such diffusion models is uncontrollable, which makes it hard to generate videos with continuous and consistent content. In this work, by using the diffusion model with ControlNet, we proposed a new motion-guided video-to-video translation framework called VideoControlNet to generate various videos based on the given prompts and the condition from the input video. Inspired by the video codecs that use motion information for reducing temporal redundancy, our framework uses motion information to prevent the regeneration of the redundant areas for content consistency. Specifically, we generate the first frame (i.e., the I-frame) by using the diffusion model with ControlNet. Then we generate other key frames (i.e., the P-frame) based on the previous I/P-frame by using our newly proposed motion-guided P-frame generation (MgPG) method, in which the P-frames are generated based on the motion information and the occlusion areas are inpainted by using the diffusion model. Finally, the rest frames (i.e., the B-frame) are generated by using our motion-guided B-frame interpolation (MgBI) module. Our experiments demonstrate that our proposed VideoControlNet inherits the generation capability of the pre-trained large diffusion model and extends the image diffusion model to the video diffusion model by using motion information. More results are provided at our project page.

cs.CV↗
arXiv2023

Q2ATransformer: Improving Medical VQA via an Answer Querying Decoder

Medical Visual Question Answering (VQA) systems play a supporting role to understand clinic-relevant information carried by medical images. The questions to a medical image include two categories: close-end (such as Yes/No question) and open-end. To obtain answers, the majority of the existing medical VQA methods relies on classification approaches, while a few works attempt to use generation approaches or a mixture of the two. The classification approaches are relatively simple but perform poorly on long open-end questions. To bridge this gap, in this paper, we propose a new Transformer based framework for medical VQA (named as Q2ATransformer), which integrates the advantages of both the classification and the generation approaches and provides a unified treatment for the close-end and open-end questions. Specifically, we introduce an additional Transformer decoder with a set of learnable candidate answer embeddings to query the existence of each answer class to a given image-question pair. Through the Transformer attention, the candidate answer embeddings interact with the fused features of the image-question pair to make the decision. In this way, despite being a classification-based approach, our method provides a mechanism to interact with the answer information for prediction like the generation-based approaches. On the other hand, by classification, we mitigate the task difficulty by reducing the search space of answers. Our method achieves new state-of-the-art performance on two medical VQA benchmarks. Especially, for the open-end questions, we achieve 79.19% on VQA-RAD and 54.85% on PathVQA, with 16.09% and 41.45% absolute improvements, respectively.

cs.CV↗
arXiv2023

Association of stroke lesion distributions with atrial fibrillation detected after stroke

Background Atrial fibrillation is often missed by traditional intermittent electrocardiogram monitoring after ischemic stroke due to its paroxysmal and asymptomatic nature. The knowledge of the unique characteristics of the population with atrial fibrillation detected after stroke (AFDAS) enables more ischemic stroke patients to benefit from more aggressive anticoagulation therapy and AF management. Method This is an observational, retrospective, MRI imaging-based single-center study. Patients with AFDAS were matched in 1:3 ratio with patients without AF (NoAF)and patients with known AF before stroke(KAF) in PSM model based on age, gender, and time from stroke onset to admission. Multivariate logistic models were used to test the association of MRI-based stroke lesion distribution, other clinical parameters and AF. A backward stepwise elimination regression was conducted to identify the most important variables. Results Compared to the NoAF group(n=103), the patients with AFDAS (n=42) had more cortical involvement(p=0.016), as well as temporal(p<0.001) and insular lobes(p=0.018) infraction. After performing a backward stepwise elimination model in regression analysis, the temporal lobe infraction(OR 0.274, 95%CI 0.090-0.838, p=0.023) remained independently associated with the detection of AF. Compared to the KAF group(n=89), LAD(OR 1.113, 95%CI 1.022-1.211, p=0.014), Number of lobes infarction(p=0.012), 3-lobes involvement(OR 0.177, 95%CI 0.056-0.559, p=0.003), and left hemisphere lobe involvement(OR 5.966, 95%CI 2.273-15.817, p<0.001)) were independently associated with AFDAS and KAF. Conclusions Ischemic stroke patients with AF detected after stroke present more temporal lobe infraction and cortical involvement. These lesion distribution characteristics with clinical characteristics together may help in stratifying patients with long-term cardiac monitoring after stroke.

q-bio.NC↗
arXiv2023

Rethinking Memory Profiling and Migration for Multi-Tiered Large Memory Systems

Multi-tiered large memory systems call for rethinking of memory profiling and migration because of the unique problems unseen in the traditional memory systems with smaller capacity and fewer tiers. We develop MTM, an application-transparent page management system based on three principles: (1) connecting the control of profiling overhead with the profiling mechanism for high-quality profiling; (2) building a universal page migration policy on the complex multi-tiered memory for high performance; and (3) introducing huge page awareness. We evaluate MTM using common big-data applications with realistic working sets (hundreds of GB to 1 TB). MTM outperforms seven state-of-the-art solutions by up to 42% (17% on average)

cs.PF↗
arXiv2023

Broadband nonlinear modulation of incoherent light using a transparent optoelectronic neuron array

Nonlinear optical processing of ambient natural light is highly desired in computational imaging and sensing applications. A strong optical nonlinear response that can work under weak broadband incoherent light is essential for this purpose. Here we introduce an optoelectronic nonlinear filter array that can address this emerging need. By merging 2D transparent phototransistors (TPTs) with liquid crystal (LC) modulators, we create an optoelectronic neuron array that allows self-amplitude modulation of spatially incoherent light, achieving a large nonlinear contrast over a broad spectrum at orders-of-magnitude lower intensity than what is achievable in most optical nonlinear materials. For a proof-of-concept demonstration, we fabricated a 10,000-pixel array of optoelectronic neurons, each serving as a nonlinear filter, and experimentally demonstrated an intelligent imaging system that uses the nonlinear response to instantly reduce input glares while retaining the weaker-intensity objects within the field of view of a cellphone camera. This intelligent glare-reduction capability is important for various imaging applications, including autonomous driving, machine vision, and security cameras. Beyond imaging and sensing, this optoelectronic neuron array, with its rapid nonlinear modulation for processing incoherent broadband light, might also find applications in optical computing, where nonlinear activation functions that can work under ambient light conditions are highly sought.

physics.optics↗
arXiv2023

Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentation

Semi-supervised semantic segmentation (SSS) has recently gained increasing research interest as it can reduce the requirement for large-scale fully-annotated training data. The current methods often suffer from the confirmation bias from the pseudo-labelling process, which can be alleviated by the co-training framework. The current co-training-based SSS methods rely on hand-crafted perturbations to prevent the different sub-nets from collapsing into each other, but these artificial perturbations cannot lead to the optimal solution. In this work, we propose a new conflict-based cross-view consistency (CCVC) method based on a two-branch co-training framework which aims at enforcing the two sub-nets to learn informative features from irrelevant views. In particular, we first propose a new cross-view consistency (CVC) strategy that encourages the two sub-nets to learn distinct features from the same input by introducing a feature discrepancy loss, while these distinct features are expected to generate consistent prediction scores of the input. The CVC strategy helps to prevent the two sub-nets from stepping into the collapse. In addition, we further propose a conflict-based pseudo-labelling (CPL) method to guarantee the model will learn more useful information from conflicting predictions, which will lead to a stable training process. We validate our new CCVC approach on the SSS benchmark datasets where our method achieves new state-of-the-art performance. Our code is available at https://github.com/xiaoyao3302/CCVC.

cs.CV↗
arXiv2023

VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud

The task of 3D semantic scene graph (3DSSG) prediction in the point cloud is challenging since (1) the 3D point cloud only captures geometric structures with limited semantics compared to 2D images, and (2) long-tailed relation distribution inherently hinders the learning of unbiased prediction. Since 2D images provide rich semantics and scene graphs are in nature coped with languages, in this study, we propose Visual-Linguistic Semantics Assisted Training (VL-SAT) scheme that can significantly empower 3DSSG prediction models with discrimination about long-tailed and ambiguous semantic relations. The key idea is to train a powerful multi-modal oracle model to assist the 3D model. This oracle learns reliable structural representations based on semantics from vision, language, and 3D geometry, and its benefits can be heterogeneously passed to the 3D model during the training stage. By effectively utilizing visual-linguistic semantics in training, our VL-SAT can significantly boost common 3DSSG prediction models, such as SGFN and SGGpoint, only with 3D inputs in the inference stage, especially when dealing with tail relation triplets. Comprehensive evaluations and ablation studies on the 3DSSG dataset have validated the effectiveness of the proposed scheme. Code is available at https://github.com/wz7in/CVPR2023-VLSAT.

cs.CV↗
arXiv2023

Optical and Near-infrared Observations of the Distant but Bright 'New Year's Burst' GRB 220101A

High-redshift gamma-ray bursts (GRBs) provide a powerful tool to probe the early universe, but still for relatively few do we have good observations of the afterglow. We here report the optical and near-infrared observations of the afterglow of a relatively high-redshift event, GRB\,220101A, triggered on New Year's Day of 2022. With the optical spectra obtained at XL2.16/BFOSC and NOT/ALFOSC, we determine the redshift of the burst at $z= 4.615$. Based on our optical and near-infrared data, combined with the X-ray data, we perform multiband fit with the python package \emph{afterglowpy}. A jet-break at $\sim$ 0.7 day post-burst is found to constrain the opening angle of the jet as $\sim$ 3.4 degree. We also determine circumburst density of $n_0 = 0.15\ {\rm cm}^{-3}$ as well as kinetic energy $E_{\rm K, iso} = 3.52\times 10^{54}$ erg. The optical afterglow is among the most luminous ever detected. We also find a ``mirror'' feature in the lightcurve during the prompt phase of the burst from 80 s to 120 s. The physical origin of such mirror feature is unclear.

astro-ph.HE↗
arXiv2023

Bridging Synthetic and Real Images: a Transferable and Multiple Consistency aided Fundus Image Enhancement Framework

Deep learning based image enhancement models have largely improved the readability of fundus images in order to decrease the uncertainty of clinical observations and the risk of misdiagnosis. However, due to the difficulty of acquiring paired real fundus images at different qualities, most existing methods have to adopt synthetic image pairs as training data. The domain shift between the synthetic and the real images inevitably hinders the generalization of such models on clinical data. In this work, we propose an end-to-end optimized teacher-student framework to simultaneously conduct image enhancement and domain adaptation. The student network uses synthetic pairs for supervised enhancement, and regularizes the enhancement model to reduce domain-shift by enforcing teacher-student prediction consistency on the real fundus images without relying on enhanced ground-truth. Moreover, we also propose a novel multi-stage multi-attention guided enhancement network (MAGE-Net) as the backbones of our teacher and student network. Our MAGE-Net utilizes multi-stage enhancement module and retinal structure preservation module to progressively integrate the multi-scale features and simultaneously preserve the retinal structures for better fundus image quality enhancement. Comprehensive experiments on both real and synthetic datasets demonstrate that our framework outperforms the baseline approaches. Moreover, our method also benefits the downstream clinical tasks.

eess.IV↗