arXiv subjects

Kai Hu

Publications and source records attributed to Kai Hu.

At least 73 records · Page 4Linked to original sources

arXiv2024

UniVIE: A Unified Label Space Approach to Visual Information Extraction from Form-like Documents

Existing methods for Visual Information Extraction (VIE) from form-like documents typically fragment the process into separate subtasks, such as key information extraction, key-value pair extraction, and choice group extraction. However, these approaches often overlook the hierarchical structure of form documents, including hierarchical key-value pairs and hierarchical choice groups. To address these limitations, we present a new perspective, reframing VIE as a relation prediction problem and unifying labels of different tasks into a single label space. This unified approach allows for the definition of various relation types and effectively tackles hierarchical relationships in form-like documents. In line with this perspective, we present UniVIE, a unified model that addresses the VIE problem comprehensively. UniVIE functions using a coarse-to-fine strategy. It initially generates tree proposals through a tree proposal network, which are subsequently refined into hierarchical trees by a relation decoder module. To enhance the relation prediction capabilities of UniVIE, we incorporate two novel tree constraints into the relation decoder: a tree attention mask and a tree level embedding. Extensive experimental evaluations on both our in-house dataset HierForms and a publicly available dataset SIBR, substantiate that our method achieves state-of-the-art results, underscoring the effectiveness and potential of our unified approach in advancing the field of VIE.

cs.CL↗

arXiv2024

Dynamic Relation Transformer for Contextual Text Block Detection

Contextual Text Block Detection (CTBD) is the task of identifying coherent text blocks within the complexity of natural scenes. Previous methodologies have treated CTBD as either a visual relation extraction challenge within computer vision or as a sequence modeling problem from the perspective of natural language processing. We introduce a new framework that frames CTBD as a graph generation problem. This methodology consists of two essential procedures: identifying individual text units as graph nodes and discerning the sequential reading order relationships among these units as graph edges. Leveraging the cutting-edge capabilities of DQ-DETR for node detection, our framework innovates further by integrating a novel mechanism, a Dynamic Relation Transformer (DRFormer), dedicated to edge generation. DRFormer incorporates a dual interactive transformer decoder that deftly manages a dynamic graph structure refinement process. Through this iterative process, the model systematically enhances the graph's fidelity, ultimately resulting in improved precision in detecting contextual text blocks. Comprehensive experimental evaluations conducted on both SCUT-CTW-Context and ReCTS-Context datasets substantiate that our method achieves state-of-the-art results, underscoring the effectiveness and potential of our graph generation framework in advancing the field of CTBD.

cs.CV↗

arXiv2023

Unlocking Deterministic Robustness Certification on ImageNet

Despite the promise of Lipschitz-based methods for provably-robust deep learning with deterministic guarantees, current state-of-the-art results are limited to feed-forward Convolutional Networks (ConvNets) on low-dimensional data, such as CIFAR-10. This paper investigates strategies for expanding certifiably robust training to larger, deeper models. A key challenge in certifying deep networks is efficient calculation of the Lipschitz bound for residual blocks found in ResNet and ViT architectures. We show that fast ways of bounding the Lipschitz constant for conventional ResNets are loose, and show how to address this by designing a new residual block, leading to the \emph{Linear ResNet} (LiResNet) architecture. We then introduce \emph{Efficient Margin MAximization} (EMMA), a loss function that stabilizes robust training by simultaneously penalizing worst-case adversarial examples from \emph{all} classes. Together, these contributions yield new \emph{state-of-the-art} robust accuracy on CIFAR-10/100 and Tiny-ImageNet under $\ell_2$ perturbations. Moreover, for the first time, we are able to scale up fast deterministic robustness guarantees to ImageNet, demonstrating that this approach to robust learning can be applied to real-world applications. We release our code on Github: \url{https://github.com/klasleino/gloro}.

cs.LG↗

arXiv2023

Is Certifying $\ell_p$ Robustness Still Worthwhile?

Over the years, researchers have developed myriad attacks that exploit the ubiquity of adversarial examples, as well as defenses that aim to guard against the security vulnerabilities posed by such attacks. Of particular interest to this paper are defenses that provide provable guarantees against the class of $\ell_p$-bounded attacks. Certified defenses have made significant progress, taking robustness certification from toy models and datasets to large-scale problems like ImageNet classification. While this is undoubtedly an interesting academic problem, as the field has matured, its impact in practice remains unclear, thus we find it useful to revisit the motivation for continuing this line of research. There are three layers to this inquiry, which we address in this paper: (1) why do we care about robustness research? (2) why do we care about the $\ell_p$-bounded threat model? And (3) why do we care about certification as opposed to empirical defenses? In brief, we take the position that local robustness certification indeed confers practical value to the field of machine learning. We focus especially on the latter two questions from above. With respect to the first of the two, we argue that the $\ell_p$-bounded threat model acts as a minimal requirement for safe application of models in security-critical domains, while at the same time, evidence has mounted suggesting that local robustness may lead to downstream external benefits not immediately related to robustness. As for the second, we argue that (i) certification provides a resolution to the cat-and-mouse game of adversarial attacks; and furthermore, that (ii) perhaps contrary to popular belief, there may not exist a fundamental trade-off between accuracy, robustness, and certifiability, while moreover, certified training techniques constitute a particularly promising way for learning robust models.

cs.LG↗

arXiv2023

FunCodec: A Fundamental, Reproducible and Integrable Open-source Toolkit for Neural Speech Codec

This paper presents FunCodec, a fundamental neural speech codec toolkit, which is an extension of the open-source speech processing toolkit FunASR. FunCodec provides reproducible training recipes and inference scripts for the latest neural speech codec models, such as SoundStream and Encodec. Thanks to the unified design with FunASR, FunCodec can be easily integrated into downstream tasks, such as speech recognition. Along with FunCodec, pre-trained models are also provided, which can be used for academic or generalized purposes. Based on the toolkit, we further propose the frequency-domain codec models, FreqCodec, which can achieve comparable speech quality with much lower computation and parameter complexity. Experimental results show that, under the same compression ratio, FunCodec can achieve better reconstruction quality compared with other toolkits and released models. We also demonstrate that the pre-trained models are suitable for downstream tasks, including automatic speech recognition and personalized text-to-speech synthesis. This toolkit is publicly available at https://github.com/alibaba-damo-academy/FunCodec.

cs.SD↗

arXiv2023

Enhancing Quality of Pose-varied Face Restoration with Local Weak Feature Sensing and GAN Prior

Facial semantic guidance (including facial landmarks, facial heatmaps, and facial parsing maps) and facial generative adversarial networks (GAN) prior have been widely used in blind face restoration (BFR) in recent years. Although existing BFR methods have achieved good performance in ordinary cases, these solutions have limited resilience when applied to face images with serious degradation and pose-varied (e.g., looking right, looking left, laughing, etc.) in real-world scenarios. In this work, we propose a well-designed blind face restoration network with generative facial prior. The proposed network is mainly comprised of an asymmetric codec and a StyleGAN2 prior network. In the asymmetric codec, we adopt a mixed multi-path residual block (MMRB) to gradually extract weak texture features of input images, which can better preserve the original facial features and avoid excessive fantasy. The MMRB can also be plug-and-play in other networks. Furthermore, thanks to the affluent and diverse facial priors of the StyleGAN2 model, we adopt it as the primary generator network in our proposed method and specially design a novel self-supervised training strategy to fit the distribution closer to the target and flexibly restore natural and realistic facial details. Extensive experiments on synthetic and real-world datasets demonstrate that our model performs superior to the prior art for face restoration and face super-resolution tasks.

cs.CV↗

arXiv2023

A Question-Answering Approach to Key Value Pair Extraction from Form-like Document Images

In this paper, we present a new question-answering (QA) based key-value pair extraction approach, called KVPFormer, to robustly extracting key-value relationships between entities from form-like document images. Specifically, KVPFormer first identifies key entities from all entities in an image with a Transformer encoder, then takes these key entities as \textbf{questions} and feeds them into a Transformer decoder to predict their corresponding \textbf{answers} (i.e., value entities) in parallel. To achieve higher answer prediction accuracy, we propose a coarse-to-fine answer prediction approach further, which first extracts multiple answer candidates for each identified question in the coarse stage and then selects the most likely one among these candidates in the fine stage. In this way, the learning difficulty of answer prediction can be effectively reduced so that the prediction accuracy can be improved. Moreover, we introduce a spatial compatibility attention bias into the self-attention/cross-attention mechanism for \Ours{} to better model the spatial interactions between entities. With these new techniques, our proposed \Ours{} achieves state-of-the-art results on FUNSD and XFUND datasets, outperforming the previous best-performing method by 7.2\% and 13.2\% in F1 score, respectively.

cs.CL↗

arXiv2023

Enhanced Training of Query-Based Object Detection via Selective Query Recollection

This paper investigates a phenomenon where query-based object detectors mispredict at the last decoding stage while predicting correctly at an intermediate stage. We review the training process and attribute the overlooked phenomenon to two limitations: lack of training emphasis and cascading errors from decoding sequence. We design and present Selective Query Recollection (SQR), a simple and effective training strategy for query-based object detectors. It cumulatively collects intermediate queries as decoding stages go deeper and selectively forwards the queries to the downstream stages aside from the sequential structure. Such-wise, SQR places training emphasis on later stages and allows later stages to work with intermediate queries from earlier stages directly. SQR can be easily plugged into various query-based object detectors and significantly enhances their performance while leaving the inference pipeline unchanged. As a result, we apply SQR on Adamixer, DAB-DETR, and Deformable-DETR across various settings (backbone, number of queries, schedule) and consistently brings 1.4-2.8 AP improvement.

cs.CV↗

arXiv2022

Contextual Expressive Text-to-Speech

The goal of expressive Text-to-speech (TTS) is to synthesize natural speech with desired content, prosody, emotion, or timbre, in high expressiveness. Most of previous studies attempt to generate speech from given labels of styles and emotions, which over-simplifies the problem by classifying styles and emotions into a fixed number of pre-defined categories. In this paper, we introduce a new task setting, Contextual TTS (CTTS). The main idea of CTTS is that how a person speaks depends on the particular context she is in, where the context can typically be represented as text. Thus, in the CTTS task, we propose to utilize such context to guide the speech synthesis process instead of relying on explicit labels of styles and emotions. To achieve this task, we construct a synthetic dataset and develop an effective framework. Experiments show that our framework can generate high-quality expressive speech based on the given context both in synthetic datasets and real-world scenarios.

eess.AS↗

arXiv2022

The VolcTrans System for WMT22 Multilingual Machine Translation Task

This report describes our VolcTrans system for the WMT22 shared task on large-scale multilingual machine translation. We participated in the unconstrained track which allows the use of external resources. Our system is a transformerbased multilingual model trained on data from multiple sources including the public training set from the data track, NLLB data provided by Meta AI, self-collected parallel corpora, and pseudo bitext from back-translation. A series of heuristic rules clean both bilingual and monolingual texts. On the official test set, our system achieves 17.3 BLEU, 21.9 spBLEU, and 41.9 chrF2++ on average over all language pairs. The average inference speed is 11.5 sentences per second using a single Nvidia Tesla V100 GPU. Our code and trained models are available at https://github.com/xian8/wmt22

cs.CL↗

arXiv2022

Composite FORCE learning of chaotic echo state networks for time-series prediction

Echo state network (ESN), a kind of recurrent neural networks, consists of a fixed reservoir in which neurons are connected randomly and recursively and obtains the desired output only by training output connection weights. First-order reduced and controlled error (FORCE) learning is an online supervised training approach that can change the chaotic activity of ESNs into specified activity patterns. This paper proposes a composite FORCE learning method based on recursive least squares to train ESNs whose initial activity is spontaneously chaotic, where a composite learning technique featured by dynamic regressor extension and memory data exploitation is applied to enhance parameter convergence. The proposed method is applied to a benchmark problem about predicting chaotic time series generated by the Mackey-Glass system, and numerical results have shown that it significantly improves learning and prediction performances compared with existing methods.

cs.LG↗

arXiv2022

Text to Image Generation with Semantic-Spatial Aware GAN

Text-to-image synthesis (T2I) aims to generate photo-realistic images which are semantically consistent with the text descriptions. Existing methods are usually built upon conditional generative adversarial networks (GANs) and initialize an image from noise with sentence embedding, and then refine the features with fine-grained word embedding iteratively. A close inspection of their generated images reveals a major limitation: even though the generated image holistically matches the description, individual image regions or parts of somethings are often not recognizable or consistent with words in the sentence, e.g. "a white crown". To address this problem, we propose a novel framework Semantic-Spatial Aware GAN for synthesizing images from input text. Concretely, we introduce a simple and effective Semantic-Spatial Aware block, which (1) learns semantic-adaptive transformation conditioned on text to effectively fuse text features and image features, and (2) learns a semantic mask in a weakly-supervised way that depends on the current text-image fusion process in order to guide the transformation spatially. Experiments on the challenging COCO and CUB bird datasets demonstrate the advantage of our method over the recent state-of-the-art approaches, regarding both visual fidelity and alignment with input text description.

cs.CV↗

arXiv2022

Global well-posedness of shock front solutions to one-dimensional piston problem for combustion Euler flows

This paper is devoted to the well-posedness theory of piston problem for compressible {combustion} Euler flows with physical ignition condition. A significant combustion phenomena called detonation will occur provided the reactant is compressed and ignited by a leading shock. Mathematically, the problem can be formulated as an initial-boundary value problem for hyperbolic balance laws with a large shock front as free boundary. In present paper, we establish the global well-posedness of entropy solutions via wave front tracking scheme within the framework of $BV\cap L^1$ space. The main difficulties here stem from the discontinuous source term without uniform dissipation structure, and from the characteristic-boundary associated with degenerate characteristic field. In dealing with the obstacles caused by ignition temperature, we develop a modified Glimm-type functional to control the oscillation growth of combustion waves, even if the exothermic source fails to uniformly decay. As to the characteristic boundary, the degeneracy of contact discontinuity is fully employed to get elegant stability estimates near the piston boundary. Meanwhile, we devise a weighted Lyapunov functional to balance the nonlinear effects arising from large shock, characteristic boundary and exothermic reaction, then obtain the $L^1-$stability of combustion wave solutions. Our results reveal that one dimensional \emph{ZND} detonation waves {supported} by a forward piston are indeed nonlinearly stable under small perturbation in $BV$ sense. This is the first work on well-posedness of inviscid reacting Euler fluids dominated by ignition temperature.

math.AP↗

arXiv2021

ViBERTgrid: A Jointly Trained Multi-Modal 2D Document Representation for Key Information Extraction from Documents

Recent grid-based document representations like BERTgrid allow the simultaneous encoding of the textual and layout information of a document in a 2D feature map so that state-of-the-art image segmentation and/or object detection models can be straightforwardly leveraged to extract key information from documents. However, such methods have not achieved comparable performance to state-of-the-art sequence- and graph-based methods such as LayoutLM and PICK yet. In this paper, we propose a new multi-modal backbone network by concatenating a BERTgrid to an intermediate layer of a CNN model, where the input of CNN is a document image and the BERTgrid is a grid of word embeddings, to generate a more powerful grid-based document representation, named ViBERTgrid. Unlike BERTgrid, the parameters of BERT and CNN in our multimodal backbone network are trained jointly. Our experimental results demonstrate that this joint training strategy improves significantly the representation ability of ViBERTgrid. Consequently, our ViBERTgrid-based key information extraction approach has achieved state-of-the-art performance on real-world datasets.

cs.CL↗

arXiv2020

Formal Verification of Solidity contracts in Event-B

Smart contracts are the artifact of the blockchain that provide immutable and verifiable specifications of physical transactions. Solidity is a domain-specific programming language with the purpose of defining smart contracts. It aims at reducing the transaction costs occasioned by the execution of contracts on the distributed ledgers such as the Ethereum. However, Solidity contracts need to adhere safety and security requirements that require formal verification and certification. This paper proposes a method to meet such requirements by translating Solidity contracts to Event-B models, supporting certification. To that purpose, we define a restrained Solidity subset and a transfer function which translates Solidity contracts to Event-B models. Then we take advantage of Event-B method capabilities to refine models at different levels of abstraction to verify Solidity contracts' properties. And we can verify the generated proof obligations of the Event-B model with the help of the Rodin platform.

cs.SE↗

arXiv2020

A Neural Architecture Search based Framework for Liquid State Machine Design

Liquid State Machine (LSM), also known as the recurrent version of Spiking Neural Networks (SNN), has attracted great research interests thanks to its high computational power, biological plausibility from the brain, simple structure and low training complexity. By exploring the design space in network architectures and parameters, recent works have demonstrated great potential for improving the accuracy of LSM model with low complexity. However, these works are based on manually-defined network architectures or predefined parameters. Considering the diversity and uniqueness of brain structure, the design of LSM model should be explored in the largest search space possible. In this paper, we propose a Neural Architecture Search (NAS) based framework to explore both architecture and parameter design space for automatic dataset-oriented LSM model. To handle the exponentially-increased design space, we adopt a three-step search for LSM, including multi-liquid architecture search, variation on the number of neurons and parameters search such as percentage connectivity and excitatory neuron ratio within each liquid. Besides, we propose to use Simulated Annealing (SA) algorithm to implement the three-step heuristic search. Three datasets, including image dataset of MNIST and NMNIST and speech dataset of FSDD, are used to test the effectiveness of our proposed framework. Simulation results show that our proposed framework can produce the dataset-oriented optimal LSM models with high accuracy and low complexity. The best classification accuracy on the three datasets is 93.2%, 92.5% and 84% respectively with only 1000 spiking neurons, and the network connections can be averagely reduced by 61.4% compared with a single LSM. Moreover, we find that the total quantity of neurons in optimal LSM models on three datasets can be further reduced by 20% with only about 0.5% accuracy loss.

cs.NE↗

arXiv2019

Higher-order Network for Action Recognition

Capturing spatiotemporal dynamics is an essential topic in video recognition. In this paper, we present learnable higher-order operations as a generic family of building blocks for capturing spatiotemporal dynamics from RGB input video space. Similar to higher-order functions, the weights of higher-order operations are themselves derived from the data with learnable parameters. Classical architectures such as residual learning and network-in-network are first-order operations where weights are directly learned from the data. Higher-order operations make it easier to capture context-sensitive patterns, such as motion. Self-attention models are also higher-order operations, but the attention weights are mostly computed from an affine operation or dot product. Learnable higher-order operations can be more generic and flexible. Experimentally, we show that on the task of video recognition, our higher-order models can achieve results on par with or better than the existing state-of-the-art methods on Something-Something (V1 and V2), Kinetics and Charades datasets.

cs.CV↗

arXiv2019

RotationOut as a Regularization Method for Neural Network

In this paper, we propose a novel regularization method, RotationOut, for neural networks. Different from Dropout that handles each neuron/channel independently, RotationOut regards its input layer as an entire vector and introduces regularization by randomly rotating the vector. RotationOut can also be used in convolutional layers and recurrent layers with small modifications. We further use a noise analysis method to interpret the difference between RotationOut and Dropout in co-adaptation reduction. Using this method, we also show how to use RotationOut/Dropout together with Batch Normalization. Extensive experiments in vision and language tasks are conducted to show the effectiveness of the proposed method. Codes are available at \url{https://github.com/RotationOut/RotationOut}.

cs.LG↗