Searcharxiv⌕ Search

arXiv subjects

Hao Feng

Publications and source records attributed to Hao Feng.

At least 91 records · Page 5Linked to original sources
arXiv2023

Deep Unrestricted Document Image Rectification

In recent years, tremendous efforts have been made on document image rectification, but existing advanced algorithms are limited to processing restricted document images, i.e., the input images must incorporate a complete document. Once the captured image merely involves a local text region, its rectification quality is degraded and unsatisfactory. Our previously proposed DocTr, a transformer-assisted network for document image rectification, also suffers from this limitation. In this work, we present DocTr++, a novel unified framework for document image rectification, without any restrictions on the input distorted images. Our major technical improvements can be concluded in three aspects. Firstly, we upgrade the original architecture by adopting a hierarchical encoder-decoder structure for multi-scale representation extraction and parsing. Secondly, we reformulate the pixel-wise mapping relationship between the unrestricted distorted document images and the distortion-free counterparts. The obtained data is used to train our DocTr++ for unrestricted document image rectification. Thirdly, we contribute a real-world test set and metrics applicable for evaluating the rectification quality. To our best knowledge, this is the first learning-based method for the rectification of unrestricted document images. Extensive experiments are conducted, and the results demonstrate the effectiveness and superiority of our method. We hope our DocTr++ will serve as a strong baseline for generic document image rectification, prompting the further advancement and application of learning-based algorithms. The source code and the proposed dataset are publicly available at https://github.com/fh2019ustc/DocTr-Plus.

cs.CV↗
arXiv2023

Towards Improving Document Understanding: An Exploration on Text-Grounding via MLLMs

In the field of document understanding, significant advances have been made in the fine-tuning of Multimodal Large Language Models (MLLMs) with instruction-following data. Nevertheless, the potential of text-grounding capability within text-rich scenarios remains underexplored. In this paper, we present a text-grounding document understanding model, termed TGDoc, which addresses this deficiency by enhancing MLLMs with the ability to discern the spatial positioning of text within images. Empirical evidence suggests that text-grounding improves the model's interpretation of textual content, thereby elevating its proficiency in comprehending text-rich images. Specifically, we compile a dataset containing 99K PowerPoint presentations sourced from the internet. We formulate instruction tuning tasks including text detection, recognition, and spotting to facilitate the cohesive alignment between the visual encoder and large language model. Moreover, we curate a collection of text-rich images and prompt the text-only GPT-4 to generate 12K high-quality conversations, featuring textual locations within text-rich scenarios. By integrating text location data into the instructions, TGDoc is adept at discerning text locations during the visual question process. Extensive experiments demonstrate that our method achieves state-of-the-art performance across multiple text-rich benchmarks, validating the effectiveness of our method.

cs.CV↗
arXiv2023

UCE-FID: Using Large Unlabeled, Medium Crowdsourced-Labeled, and Small Expert-Labeled Tweets for Foodborne Illness Detection

Foodborne illnesses significantly impact public health. Deep learning surveillance applications using social media data aim to detect early warning signals. However, labeling foodborne illness-related tweets for model training requires extensive human resources, making it challenging to collect a sufficient number of high-quality labels for tweets within a limited budget. The severe class imbalance resulting from the scarcity of foodborne illness-related tweets among the vast volume of social media further exacerbates the problem. Classifiers trained on a class-imbalanced dataset are biased towards the majority class, making accurate detection difficult. To overcome these challenges, we propose EGAL, a deep learning framework for foodborne illness detection that uses small expert-labeled tweets augmented by crowdsourced-labeled and massive unlabeled data. Specifically, by leveraging tweets labeled by experts as a reward set, EGAL learns to assign a weight of zero to incorrectly labeled tweets to mitigate their negative influence. Other tweets receive proportionate weights to counter-balance the unbalanced class distribution. Extensive experiments on real-world \textit{TWEET-FID} data show that EGAL outperforms strong baseline models across different settings, including varying expert-labeled set sizes and class imbalance ratios. A case study on a multistate outbreak of Salmonella Typhimurium infection linked to packaged salad greens demonstrates how the trained model captures relevant tweets offering valuable outbreak insights. EGAL, funded by the U.S. Department of Agriculture (USDA), has the potential to be deployed for real-time analysis of tweet streaming, contributing to foodborne illness outbreak surveillance efforts.

cs.CL↗
arXiv2023

Parameter-efficient is not sufficient: Exploring Parameter, Memory, and Time Efficient Adapter Tuning for Dense Predictions

Pre-training & fine-tuning is a prevalent paradigm in computer vision (CV). Recently, parameter-efficient transfer learning (PETL) methods have shown promising performance in adapting to downstream tasks with only a few trainable parameters. Despite their success, the existing PETL methods in CV can be computationally expensive and require large amounts of memory and time cost during training, which limits low-resource users from conducting research and applications on large models. In this work, we propose Parameter, Memory, and Time Efficient Visual Adapter ($\mathrm{E^3VA}$) tuning to address this issue. We provide a gradient backpropagation highway for low-rank adapters which eliminates the need for expensive backpropagation through the frozen pre-trained model, resulting in substantial savings of training memory and training time. Furthermore, we optimise the $\mathrm{E^3VA}$ structure for CV tasks to promote model performance. Extensive experiments on COCO, ADE20K, and Pascal VOC benchmarks show that $\mathrm{E^3VA}$ can save up to 62.2% training memory and 26.2% training time on average, while achieving comparable performance to full fine-tuning and better performance than most PETL methods. Note that we can even train the Swin-Large-based Cascade Mask RCNN on GTX 1080Ti GPUs with less than 1.5% trainable parameters.

cs.CV↗
arXiv2023

Scalable AI Generative Content for Vehicular Network Semantic Communication

Perceiving vehicles in a driver's blind spot is vital for safe driving. The detection of potentially dangerous vehicles in these blind spots can benefit from vehicular network semantic communication technology. However, efficient semantic communication involves a trade-off between accuracy and delay, especially in bandwidth-limited situations. This paper unveils a scalable Artificial Intelligence Generated Content (AIGC) system that leverages an encoder-decoder architecture. This system converts images into textual representations and reconstructs them into quality-acceptable images, optimizing transmission for vehicular network semantic communication. Moreover, when bandwidth allows, auxiliary information is integrated. The encoder-decoder aims to maintain semantic equivalence with the original images across various tasks. Then the proposed approach employs reinforcement learning to enhance the reliability of the generated contents. Experimental results suggest that the proposed method surpasses the baseline in perceiving vehicles in blind spots and effectively compresses communication data. While this method is specifically designed for driving scenarios, this encoder-decoder architecture also holds potential for wide use across various semantic communication scenarios.

cs.AI↗
arXiv2023

Progressive Recurrent Network for Shadow Removal

Single-image shadow removal is a significant task that is still unresolved. Most existing deep learning-based approaches attempt to remove the shadow directly, which can not deal with the shadow well. To handle this issue, we consider removing the shadow in a coarse-to-fine fashion and propose a simple but effective Progressive Recurrent Network (PRNet). The network aims to remove the shadow progressively, enabing us to flexibly adjust the number of iterations to strike a balance between performance and time. Our network comprises two parts: shadow feature extraction and progressive shadow removal. Specifically, the first part is a shallow ResNet which constructs the representations of the input shadow image on its original size, preventing the loss of high-frequency details caused by the downsampling operation. The second part has two critical components: the re-integration module and the update module. The proposed re-integration module can fully use the outputs of the previous iteration, providing input for the update module for further shadow removal. In this way, the proposed PRNet makes the whole process more concise and only uses 29% network parameters than the best published method. Extensive experiments on the three benchmarks, ISTD, ISTD+, and SRD, demonstrate that our method can effectively remove shadows and achieve superior performance.

cs.CV↗
arXiv2023

Ditto: An Elastic and Adaptive Memory-Disaggregated Caching System

In-memory caching systems are fundamental building blocks in cloud services. However, due to the coupled CPU and memory on monolithic servers, existing caching systems cannot elastically adjust resources in a resource-efficient and agile manner. To achieve better elasticity, we propose to port in-memory caching systems to the disaggregated memory (DM) architecture, where compute and memory resources are decoupled and can be allocated flexibly. However, constructing an elastic caching system on DM is challenging since accessing cached objects with CPU-bypass remote memory accesses hinders the execution of caching algorithms. Moreover, the elastic changes of compute and memory resources on DM affect the access patterns of cached data, compromising the hit rates of caching algorithms. We design Ditto, the first caching system on DM, to address these challenges. Ditto first proposes a client-centric caching framework to efficiently execute various caching algorithms in the compute pool of DM, relying only on remote memory accesses. Then, Ditto employs a distributed adaptive caching scheme that adaptively switches to the best-fit caching algorithm in real-time based on the performance of multiple caching algorithms to improve cache hit rates. Our experiments show that Ditto effectively adapts to the changing resources on DM and outperforms the state-of-the-art caching systems by up to 3.6x in real-world workloads and 9x in YCSB

cs.DC↗
arXiv2023

UniDoc: A Universal Large Multimodal Model for Simultaneous Text Detection, Recognition, Spotting and Understanding

In the era of Large Language Models (LLMs), tremendous strides have been made in the field of multimodal understanding. However, existing advanced algorithms are limited to effectively utilizing the immense representation capabilities and rich world knowledge inherent to these large pre-trained models, and the beneficial connections among tasks within the context of text-rich scenarios have not been sufficiently explored. In this work, we introduce UniDoc, a novel multimodal model equipped with text detection and recognition capabilities, which are deficient in existing approaches. Moreover, UniDoc capitalizes on the beneficial interactions among tasks to enhance the performance of each individual task. To implement UniDoc, we perform unified multimodal instruct tuning on the contributed large-scale instruction following datasets. Quantitative and qualitative experimental results show that UniDoc sets state-of-the-art scores across multiple challenging benchmarks. To the best of our knowledge, this is the first large multimodal model capable of simultaneous text detection, recognition, spotting, and understanding.

cs.AI↗
arXiv2023

Sign Language Translation with Iterative Prototype

This paper presents IP-SLT, a simple yet effective framework for sign language translation (SLT). Our IP-SLT adopts a recurrent structure and enhances the semantic representation (prototype) of the input sign language video via an iterative refinement manner. Our idea mimics the behavior of human reading, where a sentence can be digested repeatedly, till reaching accurate understanding. Technically, IP-SLT consists of feature extraction, prototype initialization, and iterative prototype refinement. The initialization module generates the initial prototype based on the visual feature extracted by the feature extraction module. Then, the iterative refinement module leverages the cross-attention mechanism to polish the previous prototype by aggregating it with the original video feature. Through repeated refinement, the prototype finally converges to a more stable and accurate state, leading to a fluent and appropriate translation. In addition, to leverage the sequential dependence of prototypes, we further propose an iterative distillation loss to compress the knowledge of the final iteration into previous ones. As the autoregressive decoding process is executed only once in inference, our IP-SLT is ready to improve various SLT systems with acceptable overhead. Extensive experiments are conducted on public benchmarks to demonstrate the effectiveness of the IP-SLT.

cs.CV↗
arXiv2023

SimFIR: A Simple Framework for Fisheye Image Rectification with Self-supervised Representation Learning

In fisheye images, rich distinct distortion patterns are regularly distributed in the image plane. These distortion patterns are independent of the visual content and provide informative cues for rectification. To make the best of such rectification cues, we introduce SimFIR, a simple framework for fisheye image rectification based on self-supervised representation learning. Technically, we first split a fisheye image into multiple patches and extract their representations with a Vision Transformer (ViT). To learn fine-grained distortion representations, we then associate different image patches with their specific distortion patterns based on the fisheye model, and further subtly design an innovative unified distortion-aware pretext task for their learning. The transfer performance on the downstream rectification task is remarkably boosted, which verifies the effectiveness of the learned representations. Extensive experiments are conducted, and the quantitative and qualitative results demonstrate the superiority of our method over the state-of-the-art algorithms as well as its strong generalization ability on real-world fisheye images.

cs.CV↗
arXiv2023

Mobile Supply: The Last Piece of Jigsaw of Recommender System

Recommendation system is a fundamental functionality of online platforms. With the development of computing power of mobile phones, some researchers have deployed recommendation algorithms on users' mobile devices to address the problems of data transmission delay and pagination trigger mechanism. However, the existing edge-side mobile rankings cannot completely solve the problem of pagination trigger mechanism. The mobile ranking can only sort the items on the current page, and the fixed set of candidate items limits the performance of the mobile ranking. Besides, after the user has viewed the items of interest to the user on the current page, the user refresh to get a new page of items. This will affect the user's immersive experience because the user is not satisfied with the left items on the current page. In order to address the problem of pagination trigger mechanism, we propose a completely new module in the pipeline of recommender system named Mobile Supply. The pipeline of recommender system is extended to "retrival->pre-ranking->ranking->re-ranking->Mobile Supply->mobile ranking". Specifically, we introduce the concept of list value and use point-wise paradigm to approximate list-wise estimation to calculate the maximum revenue that can be achieved by mobile ranking for the current page. We also design a new mobile ranking approach named device-aware mobile ranking considering the differences of mobile devices tailored to the new pipeline. Extensive offline and online experiments show the superiority of our proposed method and prove that Mobile Supply can further improve the performance of edge-side recommender system and user experience. Mobile Supply has been deployed on the homepage of a large-scale online food platform and has yielded considerable profits in our business.

cs.IR↗
arXiv2023

ESMC: Entire Space Multi-Task Model for Post-Click Conversion Rate via Parameter Constraint

Large-scale online recommender system spreads all over the Internet being in charge of two basic tasks: Click-Through Rate (CTR) and Post-Click Conversion Rate (CVR) estimations. However, traditional CVR estimators suffer from well-known Sample Selection Bias and Data Sparsity issues. Entire space models were proposed to address the two issues via tracing the decision-making path of "exposure_click_purchase". Further, some researchers observed that there are purchase-related behaviors between click and purchase, which can better draw the user's decision-making intention and improve the recommendation performance. Thus, the decision-making path has been extended to "exposure_click_in-shop action_purchase" and can be modeled with conditional probability approach. Nevertheless, we observe that the chain rule of conditional probability does not always hold. We report Probability Space Confusion (PSC) issue and give a derivation of difference between ground-truth and estimation mathematically. We propose a novel Entire Space Multi-Task Model for Post-Click Conversion Rate via Parameter Constraint (ESMC) and two alternatives: Entire Space Multi-Task Model with Siamese Network (ESMS) and Entire Space Multi-Task Model in Global Domain (ESMG) to address the PSC issue. Specifically, we handle "exposure_click_in-shop action" and "in-shop action_purchase" separately in the light of characteristics of in-shop action. The first path is still treated with conditional probability while the second one is treated with parameter constraint strategy. Experiments on both offline and online environments in a large-scale recommendation system illustrate the superiority of our proposed methods over state-of-the-art models. The real-world datasets will be released.

cs.AI↗
arXiv2023

Multi-Task Cross-Modality Attention-Fusion for 2D Object Detection

Accurate and robust object detection is critical for autonomous driving. Image-based detectors face difficulties caused by low visibility in adverse weather conditions. Thus, radar-camera fusion is of particular interest but presents challenges in optimally fusing heterogeneous data sources. To approach this issue, we propose two new radar preprocessing techniques to better align radar and camera data. In addition, we introduce a Multi-Task Cross-Modality Attention-Fusion Network (MCAF-Net) for object detection, which includes two new fusion blocks. These allow for exploiting information from the feature maps more comprehensively. The proposed algorithm jointly detects objects and segments free space, which guides the model to focus on the more relevant part of the scene, namely, the occupied space. Our approach outperforms current state-of-the-art radar-camera fusion-based object detectors in the nuScenes dataset and achieves more robust results in adverse weather conditions and nighttime scenarios.

cs.CV↗
arXiv2023

Active RIS-Assisted mmWave Indoor Signal Enhancement Based on Transparent RIS

Due to the serious path loss of millimeter-wave (mmWave), the signal sent by the base station is seriously attenuated when it reaches the indoors. Recent studies have proposed a glass-based metasurface that can enhance mmWave indoor signals. The transparent reconfigurable intelligent surface (RIS) focuses on the mmWave signal to a specific location indoors. In this paper, a novel RIS-assisted mmWave indoor enhancement scheme is proposed, in which a transparent RIS is deployed on the glass to enhance mmWave indoor signals, and three assisted transmission scenarios, namely passive RIS (PRIS), active RIS (ARIS), and a novel hybrid RIS (HRIS) are proposed. This paper aims to maximize the signal-to-noise ratio (SNR) of the received signal for the three assisted transmission scenarios. The closed-form solution to the maximum SNR is presented in the PRIS and the ARIS-assisted transmission scenarios. Meanwhile, the closed-form solution to the maximum SNR for the HRIS-assisted transmission scenario is presented for given active unit cells. In addition, the performance of the proposed scheme is analyzed under three assisted transmission scenarios. The results indicate that under a specific RIS power budget, the ARIS-assisted transmission scenario achieves the highest data rate and energy efficiency. Also, it requires very few unit cells, thus dramatically reducing the size of the metasurface.

eess.SP↗
arXiv2023

Model-Based Monitoring and State Estimation for Digital Twins: The Kalman Filter

A digital twin (DT) monitors states of the physical twin (PT) counterpart and provides a number of benefits such as advanced visualizations, fault detection capabilities, and reduced maintenance cost. It is the ability to be able to detect the states inside the DT that enable such benefits. In order to estimate the desired states of a PT, we propose the use of a Kalman Filter (KF). In this tutorial, we provide an introduction and detailed derivation of the KF. We demonstrate the use of KF to monitor and anomaly detection through an incubator system. Our experimental result shows that KF successfully can detect the anomaly during monitoring.

eess.SP↗
arXiv2023

mmWave RIS Phase Shift Feedback Based on Knowledge Base Autoencoder Framework

In reconfigurable intelligent surface (RIS)-assisted wireless communication systems, adjusting the phase shift of RIS unit cells is crucial for improving communication performance. Due to massive RIS unit cells, the number of phase shift parameters fed back from the base station (BS) to the RIS is enormous, which occupies a large number of frequency resources. In this paper, we propose a feedback scheme for millimeter-wave RIS phase shift applying a knowledge base autoencoder framework, in which the learnable knowledge base is shared at the BS and the RIS. The encoder at the BS compresses the RIS phase shift matrix to multiple feature vectors. Then the knowledge base vectors index is obtained by calculating the similarity between feature vectors and knowledge base vectors and transmitted to the RIS. With utilizing the index at the RIS, the corresponding knowledge base vectors are extracted and used as the decoder's inputs to reconstruct the phase shift of the RIS. Simulation results show that the proposed scheme can significantly improve the accuracy of phase shift feedback and impressively reduce the amount of RIS phase shift feedback data. Moreover, the proposed scheme is easy to deploy in actual scenarios due to lower complexity and fewer parameters.

eess.SP↗
arXiv2023

Diffusion Probabilistic Model Based Accurate and High-Degree-of-Freedom Metasurface Inverse Design

Conventional meta-atom designs rely heavily on researchers' prior knowledge and trial-and-error searches using full-wave simulations, resulting in time-consuming and inefficient processes. Inverse design methods based on optimization algorithms, such as evolutionary algorithms, and topological optimizations, have been introduced to design metamaterials. However, none of these algorithms are general enough to fulfill multi-objective tasks. Recently, deep learning methods represented by Generative Adversarial Networks (GANs) have been applied to inverse design of metamaterials, which can directly generate high-degree-of-freedom meta-atoms based on S-parameter requirements. However, the adversarial training process of GANs makes the network unstable and results in high modeling costs. This paper proposes a novel metamaterial inverse design method based on the diffusion probability theory. By learning the Markov process that transforms the original structure into a Gaussian distribution, the proposed method can gradually remove the noise starting from the Gaussian distribution and generate new high-degree-of-freedom meta-atoms that meet S-parameter conditions, which avoids the model instability introduced by the adversarial training process of GANs and ensures more accurate and high-quality generation results. Experiments have proven that our method is superior to representative methods of GANs in terms of model convergence speed, generation accuracy, and quality.

cs.LG↗
arXiv2023

DocMAE: Document Image Rectification via Self-supervised Representation Learning

Tremendous efforts have been made on document image rectification, but how to learn effective representation of such distorted images is still under-explored. In this paper, we present DocMAE, a novel self-supervised framework for document image rectification. Our motivation is to encode the structural cues in document images by leveraging masked autoencoder to benefit the rectification, i.e., the document boundaries, and text lines. Specifically, we first mask random patches of the background-excluded document images and then reconstruct the missing pixels. With such a self-supervised learning approach, the network is encouraged to learn the intrinsic structure of deformed documents by restoring document boundaries and missing text lines. Transfer performance in the downstream rectification task validates the effectiveness of our method. Extensive experiments are conducted to demonstrate the effectiveness of our method.

cs.CV↗