Searcharxiv⌕ Search

arXiv subjects

Wei Feng

Publications and source records attributed to Wei Feng.

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

Structured Satellite-UAV-Terrestrial Networks for 6G Internet of Things

The upcoming sixth generation (6G) wireless communication network is envisioned to cover space, air, and maritime areas, in addition to urban-centered terrestrial coverage by the fifth generation (5G) network, to support intelligent Internet of Things (IoT). Towards this end, we investigate structured integration of satellites, unmanned aerial vehicles (UAVs), and terrestrial networks, aiming to serve future universal IoT possibly with a massive number of devices in the coverage holes of current 5G. The hybrid satellite-UAV-terrestrial network usually leads to high system complexity, due to the heterogeneity and dynamics of space/air/ground links. With a systematic thinking, we propose to create and exploit hierarchies for the integrated network. Four basic structures are discussed by learning from the synergies in our human body. To orchestrate multiple heterogeneous basic structures, we further propose a process-oriented on-demand coverage method, which characterizes the system behavior as a series of events over time and is able to tackle the system complexity elaborately. We also outline open issues for promoting the agility and intelligence of structured satellite-UAV-terrestrial networks in the making.

cs.IT↗
arXiv2024

Structure-Informed Shadow Removal Networks

Existing deep learning-based shadow removal methods still produce images with shadow remnants. These shadow remnants typically exist in homogeneous regions with low-intensity values, making them untraceable in the existing image-to-image mapping paradigm. We observe that shadows mainly degrade images at the image-structure level (in which humans perceive object shapes and continuous colors). Hence, in this paper, we propose to remove shadows at the image structure level. Based on this idea, we propose a novel structure-informed shadow removal network (StructNet) to leverage the image-structure information to address the shadow remnant problem. Specifically, StructNet first reconstructs the structure information of the input image without shadows and then uses the restored shadow-free structure prior to guiding the image-level shadow removal. StructNet contains two main novel modules: (1) a mask-guided shadow-free extraction (MSFE) module to extract image structural features in a non-shadow-to-shadow directional manner, and (2) a multi-scale feature & residual aggregation (MFRA) module to leverage the shadow-free structure information to regularize feature consistency. In addition, we also propose to extend StructNet to exploit multi-level structure information (MStructNet), to further boost the shadow removal performance with minimum computational overheads. Extensive experiments on three shadow removal benchmarks demonstrate that our method outperforms existing shadow removal methods, and our StructNet can be integrated with existing methods to improve them further.

cs.CV↗
arXiv2024

Unveiling the Power of Self-supervision for Multi-view Multi-human Association and Tracking

Multi-view multi-human association and tracking (MvMHAT), is a new but important problem for multi-person scene video surveillance, aiming to track a group of people over time in each view, as well as to identify the same person across different views at the same time, which is different from previous MOT and multi-camera MOT tasks only considering the over-time human tracking. This way, the videos for MvMHAT require more complex annotations while containing more information for self learning. In this work, we tackle this problem with a self-supervised learning aware end-to-end network. Specifically, we propose to take advantage of the spatial-temporal self-consistency rationale by considering three properties of reflexivity, symmetry and transitivity. Besides the reflexivity property that naturally holds, we design the self-supervised learning losses based on the properties of symmetry and transitivity, for both appearance feature learning and assignment matrix optimization, to associate the multiple humans over time and across views. Furthermore, to promote the research on MvMHAT, we build two new large-scale benchmarks for the network training and testing of different algorithms. Extensive experiments on the proposed benchmarks verify the effectiveness of our method. We have released the benchmark and code to the public.

cs.CV↗
arXiv2024

Relation-Aware Diffusion Model for Controllable Poster Layout Generation

Poster layout is a crucial aspect of poster design. Prior methods primarily focus on the correlation between visual content and graphic elements. However, a pleasant layout should also consider the relationship between visual and textual contents and the relationship between elements. In this study, we introduce a relation-aware diffusion model for poster layout generation that incorporates these two relationships in the generation process. Firstly, we devise a visual-textual relation-aware module that aligns the visual and textual representations across modalities, thereby enhancing the layout's efficacy in conveying textual information. Subsequently, we propose a geometry relation-aware module that learns the geometry relationship between elements by comprehensively considering contextual information. Additionally, the proposed method can generate diverse layouts based on user constraints. To advance research in this field, we have constructed a poster layout dataset named CGL-Dataset V2. Our proposed method outperforms state-of-the-art methods on CGL-Dataset V2. The data and code will be available at https://github.com/liuan0803/RADM.

cs.CV↗
arXiv2024

Elastic Multi-Gradient Descent for Parallel Continual Learning

The goal of Continual Learning (CL) is to continuously learn from new data streams and accomplish the corresponding tasks. Previously studied CL assumes that data are given in sequence nose-to-tail for different tasks, thus indeed belonging to Serial Continual Learning (SCL). This paper studies the novel paradigm of Parallel Continual Learning (PCL) in dynamic multi-task scenarios, where a diverse set of tasks is encountered at different time points. PCL presents challenges due to the training of an unspecified number of tasks with varying learning progress, leading to the difficulty of guaranteeing effective model updates for all encountered tasks. In our previous conference work, we focused on measuring and reducing the discrepancy among gradients in a multi-objective optimization problem, which, however, may still contain negative transfers in every model update. To address this issue, in the dynamic multi-objective optimization problem, we introduce task-specific elastic factors to adjust the descent direction towards the Pareto front. The proposed method, called Elastic Multi-Gradient Descent (EMGD), ensures that each update follows an appropriate Pareto descent direction, minimizing any negative impact on previously learned tasks. To balance the training between old and new tasks, we also propose a memory editing mechanism guided by the gradient computed using EMGD. This editing process updates the stored data points, reducing interference in the Pareto descent direction from previous tasks. Experiments on public datasets validate the effectiveness of our EMGD in the PCL setting.

cs.LG↗
arXiv2023

COMMA: Co-Articulated Multi-Modal Learning

Pretrained large-scale vision-language models such as CLIP have demonstrated excellent generalizability over a series of downstream tasks. However, they are sensitive to the variation of input text prompts and need a selection of prompt templates to achieve satisfactory performance. Recently, various methods have been proposed to dynamically learn the prompts as the textual inputs to avoid the requirements of laboring hand-crafted prompt engineering in the fine-tuning process. We notice that these methods are suboptimal in two aspects. First, the prompts of the vision and language branches in these methods are usually separated or uni-directionally correlated. Thus, the prompts of both branches are not fully correlated and may not provide enough guidance to align the representations of both branches. Second, it's observed that most previous methods usually achieve better performance on seen classes but cause performance degeneration on unseen classes compared to CLIP. This is because the essential generic knowledge learned in the pretraining stage is partly forgotten in the fine-tuning process. In this paper, we propose Co-Articulated Multi-Modal Learning (COMMA) to handle the above limitations. Especially, our method considers prompts from both branches to generate the prompts to enhance the representation alignment of both branches. Besides, to alleviate forgetting about the essential knowledge, we minimize the feature discrepancy between the learned prompts and the embeddings of hand-crafted prompts in the pre-trained CLIP in the late transformer layers. We evaluate our method across three representative tasks of generalization to novel classes, new target datasets and unseen domain shifts. Experimental results demonstrate the superiority of our method by exhibiting a favorable performance boost upon all tasks with high efficiency.

cs.CV↗
arXiv2023

Generation of 3D Molecules in Pockets via Language Model

Generative models for molecules based on sequential line notation (e.g. SMILES) or graph representation have attracted an increasing interest in the field of structure-based drug design, but they struggle to capture important 3D spatial interactions and often produce undesirable molecular structures. To address these challenges, we introduce Lingo3DMol, a pocket-based 3D molecule generation method that combines language models and geometric deep learning technology. A new molecular representation, fragment-based SMILES with local and global coordinates, was developed to assist the model in learning molecular topologies and atomic spatial positions. Additionally, we trained a separate noncovalent interaction predictor to provide essential binding pattern information for the generative model. Lingo3DMol can efficiently traverse drug-like chemical spaces, preventing the formation of unusual structures. The Directory of Useful Decoys-Enhanced (DUD-E) dataset was used for evaluation. Lingo3DMol outperformed state-of-the-art methods in terms of drug-likeness, synthetic accessibility, pocket binding mode, and molecule generation speed.

cs.LG↗
arXiv2023

Long-Tailed Learning as Multi-Objective Optimization

Real-world data is extremely imbalanced and presents a long-tailed distribution, resulting in models that are biased towards classes with sufficient samples and perform poorly on rare classes. Recent methods propose to rebalance classes but they undertake the seesaw dilemma (what is increasing performance on tail classes may decrease that of head classes, and vice versa). In this paper, we argue that the seesaw dilemma is derived from gradient imbalance of different classes, in which gradients of inappropriate classes are set to important for updating, thus are prone to overcompensation or undercompensation on tail classes. To achieve ideal compensation, we formulate the long-tailed recognition as an multi-objective optimization problem, which fairly respects the contributions of head and tail classes simultaneously. For efficiency, we propose a Gradient-Balancing Grouping (GBG) strategy to gather the classes with similar gradient directions, thus approximately make every update under a Pareto descent direction. Our GBG method drives classes with similar gradient directions to form more representative gradient and provide ideal compensation to the tail classes. Moreover, We conduct extensive experiments on commonly used benchmarks in long-tailed learning and demonstrate the superiority of our method over existing SOTA methods.

cs.CV↗
arXiv2023

NurViD: A Large Expert-Level Video Database for Nursing Procedure Activity Understanding

The application of deep learning to nursing procedure activity understanding has the potential to greatly enhance the quality and safety of nurse-patient interactions. By utilizing the technique, we can facilitate training and education, improve quality control, and enable operational compliance monitoring. However, the development of automatic recognition systems in this field is currently hindered by the scarcity of appropriately labeled datasets. The existing video datasets pose several limitations: 1) these datasets are small-scale in size to support comprehensive investigations of nursing activity; 2) they primarily focus on single procedures, lacking expert-level annotations for various nursing procedures and action steps; and 3) they lack temporally localized annotations, which prevents the effective localization of targeted actions within longer video sequences. To mitigate these limitations, we propose NurViD, a large video dataset with expert-level annotation for nursing procedure activity understanding. NurViD consists of over 1.5k videos totaling 144 hours, making it approximately four times longer than the existing largest nursing activity datasets. Notably, it encompasses 51 distinct nursing procedures and 177 action steps, providing a much more comprehensive coverage compared to existing datasets that primarily focus on limited procedures. To evaluate the efficacy of current deep learning methods on nursing activity understanding, we establish three benchmarks on NurViD: procedure recognition on untrimmed videos, procedure and action recognition on trimmed videos, and action detection. Our benchmark and code will be available at \url{https://github.com/minghu0830/NurViD-benchmark}.

cs.CV↗
arXiv2023

Generating Bell states and $N$-partite $W$ states of long-distance qubits in superconducting waveguide QED

We show how to generate Bell states and $N$-partite $W$ states of long-distance superconducting (SC) qubits in a SC waveguide quantum electrodynamical (QED) system, where SC qubits are coupled to an open microwave transmission line. In the two-qubit case, the Bell state of two long-distance qubits can be a dark state of the system by choosing appropriate system parameters. If one proper microwave pulse drives one of two qubits, the two qubits will evolve from their ground states to a Bell state. Further, we extend this scheme to the multi-qubit case. We show that $W$ states of $N$ long-distance qubits can also be generated. Because both the Bell and $W$ states are decoupled from the waveguide (i.e., dark states of the system), they are steady and have very long lifetimes in the ideal case without decoherence of qubits. In contrast to the ideal case, the presence of decoherence of qubits limits the lifetimes of the Bell and $W$ states. Our study provides a novel scheme for generating Bell states and $N$-partite $W$ states in SC waveguide QED, which can be used to entangle long-distance nodes in waveguide quantum networks.

quant-ph↗
arXiv2023

Leveraging Inpainting for Single-Image Shadow Removal

Fully-supervised shadow removal methods achieve the best restoration qualities on public datasets but still generate some shadow remnants. One of the reasons is the lack of large-scale shadow & shadow-free image pairs. Unsupervised methods can alleviate the issue but their restoration qualities are much lower than those of fully-supervised methods. In this work, we find that pretraining shadow removal networks on the image inpainting dataset can reduce the shadow remnants significantly: a naive encoder-decoder network gets competitive restoration quality w.r.t. the state-of-the-art methods via only 10% shadow & shadow-free image pairs. After analyzing networks with/without inpainting pre-training via the information stored in the weight (IIW), we find that inpainting pretraining improves restoration quality in non-shadow regions and enhances the generalization ability of networks significantly. Additionally, shadow removal fine-tuning enables networks to fill in the details of shadow regions. Inspired by these observations we formulate shadow removal as an adaptive fusion task that takes advantage of both shadow removal and image inpainting. Specifically, we develop an adaptive fusion network consisting of two encoders, an adaptive fusion block, and a decoder. The two encoders are responsible for extracting the feature from the shadow image and the shadow-masked image respectively. The adaptive fusion block is responsible for combining these features in an adaptive manner. Finally, the decoder converts the adaptive fused features to the desired shadow-free result. The extensive experiments show that our method empowered with inpainting outperforms all state-of-the-art methods.

cs.CV↗
arXiv2023

Open Compound Domain Adaptation with Object Style Compensation for Semantic Segmentation

Many methods of semantic image segmentation have borrowed the success of open compound domain adaptation. They minimize the style gap between the images of source and target domains, more easily predicting the accurate pseudo annotations for target domain's images that train segmentation network. The existing methods globally adapt the scene style of the images, whereas the object styles of different categories or instances are adapted improperly. This paper proposes the Object Style Compensation, where we construct the Object-Level Discrepancy Memory with multiple sets of discrepancy features. The discrepancy features in a set capture the style changes of the same category's object instances adapted from target to source domains. We learn the discrepancy features from the images of source and target domains, storing the discrepancy features in memory. With this memory, we select appropriate discrepancy features for compensating the style information of the object instances of various categories, adapting the object styles to a unified style of source domain. Our method enables a more accurate computation of the pseudo annotations for target domain's images, thus yielding state-of-the-art results on different datasets.

cs.CV↗
arXiv2023

Towards Novel Class Discovery: A Study in Novel Skin Lesions Clustering

Existing deep learning models have achieved promising performance in recognizing skin diseases from dermoscopic images. However, these models can only recognize samples from predefined categories, when they are deployed in the clinic, data from new unknown categories are constantly emerging. Therefore, it is crucial to automatically discover and identify new semantic categories from new data. In this paper, we propose a new novel class discovery framework for automatically discovering new semantic classes from dermoscopy image datasets based on the knowledge of known classes. Specifically, we first use contrastive learning to learn a robust and unbiased feature representation based on all data from known and unknown categories. We then propose an uncertainty-aware multi-view cross pseudo-supervision strategy, which is trained jointly on all categories of data using pseudo labels generated by a self-labeling strategy. Finally, we further refine the pseudo label by aggregating neighborhood information through local sample similarity to improve the clustering performance of the model for unknown categories. We conducted extensive experiments on the dermatology dataset ISIC 2019, and the experimental results show that our approach can effectively leverage knowledge from known categories to discover new semantic categories. We also further validated the effectiveness of the different modules through extensive ablation experiments. Our code will be released soon.

cs.CV↗
arXiv2023

Satellite-MEC Integration for 6G Internet of Things: Minimal Structures, Advances, and Prospects

The sixth-generation (6G) network is envisioned to shift its focus from the service requirements of human beings' to those of Internet-of-Things (IoT) devices'. Satellite communications are indispensable in 6G to support IoT devices operating in rural or disastrous areas. However, satellite networks face the inherent challenges of low data rate and large latency, which may not support computation-intensive and delay-sensitive IoT applications. Mobile Edge Computing (MEC) is a burgeoning paradigm by extending cloud computing capabilities to the network edge. By utilizing MEC technologies, the resource-limited IoT devices can access abundant computation resources with low latency, which enables the highly demanding applications while meeting strict delay requirements. Therefore, an integration of satellite communications and MEC technologies is necessary to better enable 6G IoT. In this survey, we provide a holistic overview of satellite-MEC integration. We first discuss the main challenges of the integrated satellite-MEC network and propose three minimal integrating structures. For each minimal structure, we summarize the current advances in terms of their research topics, after which we discuss the lessons learned and future directions of the minimal structure. Finally, we outline potential research issues to envision a more intelligent, more secure, and greener integrated satellite-MEC network.

cs.NI↗
arXiv2023

Improving the Transferability of Adversarial Examples with Arbitrary Style Transfer

Deep neural networks are vulnerable to adversarial examples crafted by applying human-imperceptible perturbations on clean inputs. Although many attack methods can achieve high success rates in the white-box setting, they also exhibit weak transferability in the black-box setting. Recently, various methods have been proposed to improve adversarial transferability, in which the input transformation is one of the most effective methods. In this work, we notice that existing input transformation-based works mainly adopt the transformed data in the same domain for augmentation. Inspired by domain generalization, we aim to further improve the transferability using the data augmented from different domains. Specifically, a style transfer network can alter the distribution of low-level visual features in an image while preserving semantic content for humans. Hence, we propose a novel attack method named Style Transfer Method (STM) that utilizes a proposed arbitrary style transfer network to transform the images into different domains. To avoid inconsistent semantic information of stylized images for the classification network, we fine-tune the style transfer network and mix up the generated images added by random noise with the original images to maintain semantic consistency and boost input diversity. Extensive experimental results on the ImageNet-compatible dataset show that our proposed method can significantly improve the adversarial transferability on either normally trained models or adversarially trained models than state-of-the-art input transformation-based attacks. Code is available at: https://github.com/Zhijin-Ge/STM.

cs.CV↗
arXiv2023

AdaBrowse: Adaptive Video Browser for Efficient Continuous Sign Language Recognition

Raw videos have been proven to own considerable feature redundancy where in many cases only a portion of frames can already meet the requirements for accurate recognition. In this paper, we are interested in whether such redundancy can be effectively leveraged to facilitate efficient inference in continuous sign language recognition (CSLR). We propose a novel adaptive model (AdaBrowse) to dynamically select a most informative subsequence from input video sequences by modelling this problem as a sequential decision task. In specific, we first utilize a lightweight network to quickly scan input videos to extract coarse features. Then these features are fed into a policy network to intelligently select a subsequence to process. The corresponding subsequence is finally inferred by a normal CSLR model for sentence prediction. As only a portion of frames are processed in this procedure, the total computations can be considerably saved. Besides temporal redundancy, we are also interested in whether the inherent spatial redundancy can be seamlessly integrated together to achieve further efficiency, i.e., dynamically selecting a lowest input resolution for each sample, whose model is referred to as AdaBrowse+. Extensive experimental results on four large-scale CSLR datasets, i.e., PHOENIX14, PHOENIX14-T, CSL-Daily and CSL, demonstrate the effectiveness of AdaBrowse and AdaBrowse+ by achieving comparable accuracy with state-of-the-art methods with 1.44$\times$ throughput and 2.12$\times$ fewer FLOPs. Comparisons with other commonly-used 2D CNNs and adaptive efficient methods verify the effectiveness of AdaBrowse. Code is available at \url{https://github.com/hulianyuyy/AdaBrowse}.

cs.CV↗
arXiv2023

A proposal to the '$\frac{1}{2}$ vs. $\frac{3}{2}$ puzzle'

We reconsider the semileptonic decays of $B\to D_1^{(\prime)}l\bar ν_l$. The previous theoretical calculations predict a significantly smaller rate for the semileptonic decay of $B$ to $D'_1(J_l=\frac{1}{2})$ compared with that to the $D_1(J_l=\frac{3}{2})$, which is not consistent with the current experimental data. This conflict is the so-called `$\frac{1}{2}$ vs. $\frac{3}{2}$ puzzle'. In this work, we propose a simple scheme to fix this problem, where we suppose that the strong eigenstates $D_1^{(\prime)}$ do not coincide with the eigenstate of the weak interaction, since no experimental results show the weak and the strong interactions have to share the same eigenstates. Within the framework of this tentative scheme, meson $B$ first weakly decays to {the weak eigenstates} $D_{α(β)}$ and then the latter are detected as the $D_1^{(\prime)}$ by the strong products $D^*π$. We predict that there exist two new particles $D_{α(β)}$ with $J^P=1^+$ which were not previously identified. The good performance of the new scheme in describing the experimental data may hint at new symmetry in the weak decays of $B_{q}$ to $1^+$ heavy-light mesons. To test the scheme proposed here, we suggest an experiment to detect the difference in the invariant mass spectra of $D_1$ reconstructed from the $B$ weak decay and from the strong decay products.

hep-ph↗
arXiv2023

Mutual Query Network for Multi-Modal Product Image Segmentation

Product image segmentation is vital in e-commerce. Most existing methods extract the product image foreground only based on the visual modality, making it difficult to distinguish irrelevant products. As product titles contain abundant appearance information and provide complementary cues for product image segmentation, we propose a mutual query network to segment products based on both visual and linguistic modalities. First, we design a language query vision module to obtain the response of language description in image areas, thus aligning the visual and linguistic representations across modalities. Then, a vision query language module utilizes the correlation between visual and linguistic modalities to filter the product title and effectively suppress the content irrelevant to the vision in the title. To promote the research in this field, we also construct a Multi-Modal Product Segmentation dataset (MMPS), which contains 30,000 images and corresponding titles. The proposed method significantly outperforms the state-of-the-art methods on MMPS.

cs.CV↗