arXiv subjects

Feng Zheng

Publications and source records attributed to Feng Zheng.

At least 109 records · Page 6Linked to original sources

arXiv2023

Deep Industrial Image Anomaly Detection: A Survey

The recent rapid development of deep learning has laid a milestone in industrial Image Anomaly Detection (IAD). In this paper, we provide a comprehensive review of deep learning-based image anomaly detection techniques, from the perspectives of neural network architectures, levels of supervision, loss functions, metrics and datasets. In addition, we extract the new setting from industrial manufacturing and review the current IAD approaches under our proposed our new setting. Moreover, we highlight several opening challenges for image anomaly detection. The merits and downsides of representative network architectures under varying supervision are discussed. Finally, we summarize the research findings and point out future research directions. More resources are available at https://github.com/M-3LAB/awesome-industrial-anomaly-detection.

cs.CV↗

arXiv2023

Cross-Modality Neuroimage Synthesis: A Survey

Multi-modality imaging improves disease diagnosis and reveals distinct deviations in tissues with anatomical properties. The existence of completely aligned and paired multi-modality neuroimaging data has proved its effectiveness in brain research. However, collecting fully aligned and paired data is expensive or even impractical, since it faces many difficulties, including high cost, long acquisition time, image corruption, and privacy issues. An alternative solution is to explore unsupervised or weakly supervised learning methods to synthesize the absent neuroimaging data. In this paper, we provide a comprehensive review of cross-modality synthesis for neuroimages, from the perspectives of weakly supervised and unsupervised settings, loss functions, evaluation metrics, imaging modalities, datasets, and downstream applications based on synthesis. We begin by highlighting several opening challenges for cross-modality neuroimage synthesis. Then, we discuss representative architectures of cross-modality synthesis methods under different supervisions. This is followed by a stepwise in-depth analysis to evaluate how cross-modality neuroimage synthesis improves the performance of its downstream tasks. Finally, we summarize the existing research findings and point out future research directions. All resources are available at https://github.com/M-3LAB/awesome-multimodal-brain-image-systhesis

eess.IV↗

arXiv2023

Prediction of superconductivity in metallic boron-carbon compounds from 0 to 100 GPa by high-throughput screening

Boron carbon compounds have been shown to have feasible superconductivity. In our earlier paper [Zheng et al., Phys. Rev. B 107, 014508 (2023)], we identified a new conventional superconductor of LiB3C at 100 GPa. Here, we aim to extend the investigation of possible superconductivity in this structural framework by replacing Li atoms with 27 different cations under pressures ranging from 0 to 100 GPa. Using the high-throughput screening method of zone-center electron-phonon interaction, we find that ternary compounds like CaB3C, SrB3C, TiB3C, and VB3C are promising candidates for superconductivity. The consecutive calculations using the full Brillouin zone confirm that they have Tc < 31 K at moderate pressures. Our study demonstrates that fast screening of superconductivity by calculating zone-center electron-phonon coupling strength is an effective strategy for high-throughput identification of new superconductors.

cond-mat.supr-con↗

arXiv2023

Learning Cross-Modal Affinity for Referring Video Object Segmentation Targeting Limited Samples

Referring video object segmentation (RVOS), as a supervised learning task, relies on sufficient annotated data for a given scene. However, in more realistic scenarios, only minimal annotations are available for a new scene, which poses significant challenges to existing RVOS methods. With this in mind, we propose a simple yet effective model with a newly designed cross-modal affinity (CMA) module based on a Transformer architecture. The CMA module builds multimodal affinity with a few samples, thus quickly learning new semantic information, and enabling the model to adapt to different scenarios. Since the proposed method targets limited samples for new scenes, we generalize the problem as - few-shot referring video object segmentation (FS-RVOS). To foster research in this direction, we build up a new FS-RVOS benchmark based on currently available datasets. The benchmark covers a wide range and includes multiple situations, which can maximally simulate real-world scenarios. Extensive experiments show that our model adapts well to different scenarios with only a few samples, reaching state-of-the-art performance on the benchmark. On Mini-Ref-YouTube-VOS, our model achieves an average performance of 53.1 J and 54.8 F, which are 10% better than the baselines. Furthermore, we show impressive results of 77.7 J and 74.8 F on Mini-Ref-SAIL-VOS, which are significantly better than the baselines. Code is publicly available at https://github.com/hengliusky/Few_shot_RVOS.

cs.CV↗

arXiv2023

EasyNet: An Easy Network for 3D Industrial Anomaly Detection

3D anomaly detection is an emerging and vital computer vision task in industrial manufacturing (IM). Recently many advanced algorithms have been published, but most of them cannot meet the needs of IM. There are several disadvantages: i) difficult to deploy on production lines since their algorithms heavily rely on large pre-trained models; ii) hugely increase storage overhead due to overuse of memory banks; iii) the inference speed cannot be achieved in real-time. To overcome these issues, we propose an easy and deployment-friendly network (called EasyNet) without using pre-trained models and memory banks: firstly, we design a multi-scale multi-modality feature encoder-decoder to accurately reconstruct the segmentation maps of anomalous regions and encourage the interaction between RGB images and depth images; secondly, we adopt a multi-modality anomaly segmentation network to achieve a precise anomaly map; thirdly, we propose an attention-based information entropy fusion module for feature fusion during inference, making it suitable for real-time deployment. Extensive experiments show that EasyNet achieves an anomaly detection AUROC of 92.6% without using pre-trained models and memory banks. In addition, EasyNet is faster than existing methods, with a high frame rate of 94.55 FPS on a Tesla V100 GPU.

cs.CV↗

arXiv2023

Extremely Large-scale Array Systems: Near-Field Codebook Design and Performance Analysis

Extremely Large-scale Array (ELAA) promises to deliver ultra-high data rates with increased antenna elements. However, increasing antenna elements leads to a wider realm of near-field, which challenges the traditional design of codebooks. In this paper, we propose novel near-field codebook schemes based on the fitting formula of codewords' quantization performance. First, we analyze the quantization performance properties of uniform linear array (ULA) and uniform planar array (UPA) codewords. Our findings reveal an intriguing property: the correlation formula for ULA codewords can be represented by the elliptic formula, while the correlation formula for UPA codewords can be approximated using the ellipsoid formula. Building on this insight, we propose a ULA uniform codebook that maximizes the minimum correlation based on the derived formula. Moreover, we introduce a ULA dislocation codebook to further reduce quantization overhead. Continuing our exploration, we propose UPA uniform and dislocation codebook schemes. Our investigation demonstrates that oversampling in the angular domain offers distinct advantages, achieving heightened accuracy while minimizing overhead in quantifying near-field channels. Numerical results demonstrate the appealing advantages of the proposed codebook over existing methods in decreasing quantization overhead and increasing quantization accuracy.

cs.IT↗

arXiv2023

Knowledge-Aware Prompt Tuning for Generalizable Vision-Language Models

Pre-trained vision-language models, e.g., CLIP, working with manually designed prompts have demonstrated great capacity of transfer learning. Recently, learnable prompts achieve state-of-the-art performance, which however are prone to overfit to seen classes, failing to generalize to unseen classes. In this paper, we propose a Knowledge-Aware Prompt Tuning (KAPT) framework for vision-language models. Our approach takes inspiration from human intelligence in which external knowledge is usually incorporated into recognizing novel categories of objects. Specifically, we design two complementary types of knowledge-aware prompts for the text encoder to leverage the distinctive characteristics of category-related external knowledge. The discrete prompt extracts the key information from descriptions of an object category, and the learned continuous prompt captures overall contexts. We further design an adaptation head for the visual encoder to aggregate salient attentive visual cues, which establishes discriminative and task-aware visual representations. We conduct extensive experiments on 11 widely-used benchmark datasets and the results verify the effectiveness in few-shot image classification, especially in generalizing to unseen categories. Compared with the state-of-the-art CoCoOp method, KAPT exhibits favorable performance and achieves an absolute gain of 3.22% on new classes and 2.57% in terms of harmonic mean.

cs.CV↗

arXiv2023

S$^2$Contact: Graph-based Network for 3D Hand-Object Contact Estimation with Semi-Supervised Learning

Despite the recent efforts in accurate 3D annotations in hand and object datasets, there still exist gaps in 3D hand and object reconstructions. Existing works leverage contact maps to refine inaccurate hand-object pose estimations and generate grasps given object models. However, they require explicit 3D supervision which is seldom available and therefore, are limited to constrained settings, e.g., where thermal cameras observe residual heat left on manipulated objects. In this paper, we propose a novel semi-supervised framework that allows us to learn contact from monocular images. Specifically, we leverage visual and geometric consistency constraints in large-scale datasets for generating pseudo-labels in semi-supervised learning and propose an efficient graph-based network to infer contact. Our semi-supervised learning framework achieves a favourable improvement over the existing supervised learning methods trained on data with `limited' annotations. Notably, our proposed model is able to achieve superior results with less than half the network parameters and memory access cost when compared with the commonly-used PointNet-based approach. We show benefits from using a contact map that rules hand-object interactions to produce more accurate reconstructions. We further demonstrate that training with pseudo-labels can extend contact map estimations to out-of-domain objects and generalise better across multiple datasets.

cs.CV↗

arXiv2023

Transferable Decoding with Visual Entities for Zero-Shot Image Captioning

Image-to-text generation aims to describe images using natural language. Recently, zero-shot image captioning based on pre-trained vision-language models (VLMs) and large language models (LLMs) has made significant progress. However, we have observed and empirically demonstrated that these methods are susceptible to modality bias induced by LLMs and tend to generate descriptions containing objects (entities) that do not actually exist in the image but frequently appear during training (i.e., object hallucination). In this paper, we propose ViECap, a transferable decoding model that leverages entity-aware decoding to generate descriptions in both seen and unseen scenarios. ViECap incorporates entity-aware hard prompts to guide LLMs' attention toward the visual entities present in the image, enabling coherent caption generation across diverse scenes. With entity-aware hard prompts, ViECap is capable of maintaining performance when transferring from in-domain to out-of-domain scenarios. Extensive experiments demonstrate that ViECap sets a new state-of-the-art cross-domain (transferable) captioning and performs competitively in-domain captioning compared to previous VLMs-based zero-shot methods. Our code is available at: https://github.com/FeiElysia/ViECap

cs.CV↗

arXiv2023

Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models

Vision-language pre-training (VLP) models have shown vulnerability to adversarial examples in multimodal tasks. Furthermore, malicious adversaries can be deliberately transferred to attack other black-box models. However, existing work has mainly focused on investigating white-box attacks. In this paper, we present the first study to investigate the adversarial transferability of recent VLP models. We observe that existing methods exhibit much lower transferability, compared to the strong attack performance in white-box settings. The transferability degradation is partly caused by the under-utilization of cross-modal interactions. Particularly, unlike unimodal learning, VLP models rely heavily on cross-modal interactions and the multimodal alignments are many-to-many, e.g., an image can be described in various natural languages. To this end, we propose a highly transferable Set-level Guidance Attack (SGA) that thoroughly leverages modality interactions and incorporates alignment-preserving augmentation with cross-modal guidance. Experimental results demonstrate that SGA could generate adversarial examples that can strongly transfer across different VLP models on multiple downstream vision-language tasks. On image-text retrieval, SGA significantly enhances the attack success rate for transfer attacks from ALBEF to TCL by a large margin (at least 9.78% and up to 30.21%), compared to the state-of-the-art.

cs.CV↗

arXiv2023

Structural prediction of Fe-Mg-O compounds at Super-Earth's pressures

Terrestrial exoplanets are of great interest for being simultaneously similar to and different from Earth. Their compositions are likely comparable to those of solar-terrestrial objects, but their internal pressures and temperatures can vary significantly with their masses/sizes. The most abundant non-volatile elements are O, Mg, Si, Fe, Al, and Ca, and there has been much recent progress in understanding the nature of magnesium silicates up to and beyond ~3 TPa. However, a critical element, Fe, has yet to be systematically included in materials discovery studies of potential terrestrial planet-forming phases at ultra-high pressures. Here, using the adaptive genetic algorithm (AGA) crystal structure prediction method, we predict several unreported stable crystalline phases in the binary Fe-Mg and ternary Fe-Mg-O systems up to pressures of 3 TPa. The analysis of the local packing motifs of the low-enthalpy Fe-Mg-O phases reveals that the Fe-Mg-O system favors a BCC motif under ultra-high pressures regardless of chemical composition. Besides, oxygen enrichment is conducive to lowering the enthalpies of the Fe-Mg-O phases. Our results extend the current knowledge of structural information of the Fe-Mg-O system to exoplanet pressures.

physics.geo-ph↗

arXiv2023

Learning Grounded Vision-Language Representation for Versatile Understanding in Untrimmed Videos

Joint video-language learning has received increasing attention in recent years. However, existing works mainly focus on single or multiple trimmed video clips (events), which makes human-annotated event boundaries necessary during inference. To break away from the ties, we propose a grounded vision-language learning framework for untrimmed videos, which automatically detects informative events and effectively excavates the alignments between multi-sentence descriptions and corresponding event segments. Instead of coarse-level video-language alignments, we present two dual pretext tasks to encourage fine-grained segment-level alignments, i.e., text-to-event grounding (TEG) and event-to-text generation (ETG). TEG learns to adaptively ground the possible event proposals given a set of sentences by estimating the cross-modal distance in a joint semantic space. Meanwhile, ETG aims to reconstruct (generate) the matched texts given event proposals, encouraging the event representation to retain meaningful semantic information. To encourage accurate label assignment between the event set and the text set, we propose a novel semantic-aware cost to mitigate the sub-optimal matching results caused by ambiguous boundary annotations. Our framework is easily extensible to tasks covering visually-grounded language understanding and generation. We achieve state-of-the-art dense video captioning performance on ActivityNet Captions, YouCook2 and YouMakeup, and competitive performance on several other language generation and understanding tasks. Our method also achieved 1st place in both the MTVG and MDVC tasks of the PIC 4th Challenge. Our code is publicly available at https://github.com/zjr2000/GVL.

cs.CV↗

arXiv2023

CageViT: Convolutional Activation Guided Efficient Vision Transformer

Recently, Transformers have emerged as the go-to architecture for both vision and language modeling tasks, but their computational efficiency is limited by the length of the input sequence. To address this, several efficient variants of Transformers have been proposed to accelerate computation or reduce memory consumption while preserving performance. This paper presents an efficient vision Transformer, called CageViT, that is guided by convolutional activation to reduce computation. Our CageViT, unlike current Transformers, utilizes a new encoder to handle the rearranged tokens, bringing several technical contributions: 1) Convolutional activation is used to pre-process the token after patchifying the image to select and rearrange the major tokens and minor tokens, which substantially reduces the computation cost through an additional fusion layer. 2) Instead of using the class activation map of the convolutional model directly, we design a new weighted class activation to lower the model requirements. 3) To facilitate communication between major tokens and fusion tokens, Gated Linear SRA is proposed to further integrate fusion tokens into the attention mechanism. We perform a comprehensive validation of CageViT on the image classification challenge. Experimental results demonstrate that the proposed CageViT outperforms the most recent state-of-the-art backbones by a large margin in terms of efficiency, while maintaining a comparable level of accuracy (e.g. a moderate-sized 43.35M model trained solely on 224 x 224 ImageNet-1K can achieve Top-1 accuracy of 83.4% accuracy).

cs.CV↗

arXiv2023

Track Anything: Segment Anything Meets Videos

Recently, the Segment Anything Model (SAM) gains lots of attention rapidly due to its impressive segmentation performance on images. Regarding its strong ability on image segmentation and high interactivity with different prompts, we found that it performs poorly on consistent segmentation in videos. Therefore, in this report, we propose Track Anything Model (TAM), which achieves high-performance interactive tracking and segmentation in videos. To be detailed, given a video sequence, only with very little human participation, i.e., several clicks, people can track anything they are interested in, and get satisfactory results in one-pass inference. Without additional training, such an interactive design performs impressively on video object tracking and segmentation. All resources are available on {https://github.com/gaomingqi/Track-Anything}. We hope this work can facilitate related research.

cs.CV↗

arXiv2023

Can Decentralized Stochastic Minimax Optimization Algorithms Converge Linearly for Finite-Sum Nonconvex-Nonconcave Problems?

Decentralized minimax optimization has been actively studied in the past few years due to its application in a wide range of machine learning models. However, the current theoretical understanding of its convergence rate is far from satisfactory since existing works only focus on the nonconvex-strongly-concave problem. This motivates us to study decentralized minimax optimization algorithms for the nonconvex-nonconcave problem. To this end, we develop two novel decentralized stochastic variance-reduced gradient descent ascent algorithms for the finite-sum nonconvex-nonconcave problem that satisfies the Polyak-Łojasiewicz (PL) condition. In particular, our theoretical analyses demonstrate how to conduct local updates and perform communication to achieve the linear convergence rate. To the best of our knowledge, this is the first work achieving linear convergence rates for decentralized nonconvex-nonconcave problems. Finally, we verify the performance of our algorithms on both synthetic and real-world datasets. The experimental results confirm the efficacy of our algorithms.

cs.LG↗

arXiv2023

FedMed-GAN: Federated Domain Translation on Unsupervised Cross-Modality Brain Image Synthesis

Utilizing multi-modal neuroimaging data has been proved to be effective to investigate human cognitive activities and certain pathologies. However, it is not practical to obtain the full set of paired neuroimaging data centrally since the collection faces several constraints, e.g., high examination cost, long acquisition time, and image corruption. In addition, these data are dispersed into different medical institutions and thus cannot be aggregated for centralized training considering the privacy issues. There is a clear need to launch a federated learning and facilitate the integration of the dispersed data from different institutions. In this paper, we propose a new benchmark for federated domain translation on unsupervised brain image synthesis (termed as FedMed-GAN) to bridge the gap between federated learning and medical GAN. FedMed-GAN mitigates the mode collapse without sacrificing the performance of generators, and is widely applied to different proportions of unpaired and paired data with variation adaptation property. We treat the gradient penalties by federally averaging algorithm and then leveraging differential privacy gradient descent to regularize the training dynamics. A comprehensive evaluation is provided for comparing FedMed-GAN and other centralized methods, which shows the new state-of-the-art performance by our FedMed-GAN. Our code has been released on the website: https://github.com/M-3LAB/FedMed-GAN

cs.CV↗

arXiv2023

What makes a good data augmentation for few-shot unsupervised image anomaly detection?

Data augmentation is a promising technique for unsupervised anomaly detection in industrial applications, where the availability of positive samples is often limited due to factors such as commercial competition and sample collection difficulties. In this paper, how to effectively select and apply data augmentation methods for unsupervised anomaly detection is studied. The impact of various data augmentation methods on different anomaly detection algorithms is systematically investigated through experiments. The experimental results show that the performance of different industrial image anomaly detection (termed as IAD) algorithms is not significantly affected by the specific data augmentation method employed and that combining multiple data augmentation methods does not necessarily yield further improvements in the accuracy of anomaly detection, although it can achieve excellent results on specific methods. These findings provide useful guidance on selecting appropriate data augmentation methods for different requirements in IAD.

cs.CV↗

arXiv2023

Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline

Existing audio-visual event localization (AVE) handles manually trimmed videos with only a single instance in each of them. However, this setting is unrealistic as natural videos often contain numerous audio-visual events with different categories. To better adapt to real-life applications, in this paper we focus on the task of dense-localizing audio-visual events, which aims to jointly localize and recognize all audio-visual events occurring in an untrimmed video. The problem is challenging as it requires fine-grained audio-visual scene and context understanding. To tackle this problem, we introduce the first Untrimmed Audio-Visual (UnAV-100) dataset, which contains 10K untrimmed videos with over 30K audio-visual events. Each video has 2.8 audio-visual events on average, and the events are usually related to each other and might co-occur as in real-life scenes. Next, we formulate the task using a new learning-based framework, which is capable of fully integrating audio and visual modalities to localize audio-visual events with various lengths and capture dependencies between them in a single pass. Extensive experiments demonstrate the effectiveness of our method as well as the significance of multi-scale cross-modal perception and dependency modeling for this task.

cs.CV↗