Self-Supervised Pre-training with Symmetric Superimposition Modeling for Scene Text Recognition

In text recognition, self-supervised pre-training emerges as a good solution to reduce dependence on expansive annotated real data. Previous studies primarily focus on local visual representation by leveraging mask image modeling or sequence contrastive learning. However, they omit modeling the linguistic information in text images, which is crucial for recognizing text. To simultaneously capture local character features and linguistic information in visual space, we propose Symmetric Superimposition Modeling (SSM). The objective of SSM is to reconstruct the direction-specific pixel and feature signals from the symmetrically superimposed input. Specifically, we add the original image with its inverted views to create the symmetrically superimposed inputs. At the pixel level, we reconstruct the original and inverted images to capture character shapes and texture-level linguistic context. At the feature level, we reconstruct the feature of the same original image and inverted image with different augmentations to model the semantic-level linguistic context and the local character discrimination. In our design, we disrupt the character shape and linguistic rules. Consequently, the dual-level reconstruction facilitates understanding character shapes and linguistic information from the perspective of visual texture and feature semantics. Experiments on various text recognition benchmarks demonstrate the effectiveness and generality of SSM, with 4.1% average performance gains and 86.6% new state-of-the-art average word accuracy on Union14M benchmarks. The code is available at https://github.com/FaltingsA/SSM.

Symmetrical Linguistic Feature Distillation with CLIP for Scene Text Recognition

In this paper, we explore the potential of the Contrastive Language-Image Pretraining (CLIP) model in scene text recognition (STR), and establish a novel Symmetrical Linguistic Feature Distillation framework (named CLIP-OCR) to leverage both visual and linguistic knowledge in CLIP. Different from previous CLIP-based methods mainly considering feature generalization on visual encoding, we propose a symmetrical distillation strategy (SDS) that further captures the linguistic knowledge in the CLIP text encoder. By cascading the CLIP image encoder with the reversed CLIP text encoder, a symmetrical structure is built with an image-to-text feature flow that covers not only visual but also linguistic information for distillation.Benefiting from the natural alignment in CLIP, such guidance flow provides a progressive optimization objective from vision to language, which can supervise the STR feature forwarding process layer-by-layer.Besides, a new Linguistic Consistency Loss (LCL) is proposed to enhance the linguistic capability by considering second-order statistics during the optimization. Overall, CLIP-OCR is the first to design a smooth transition between image and text for the STR task.Extensive experiments demonstrate the effectiveness of CLIP-OCR with 93.8% average accuracy on six popular STR benchmarks.Code will be available at https://github.com/wzx99/CLIPOCR.

VisKoP: Visual Knowledge oriented Programming for Interactive Knowledge Base Question Answering

We present Visual Knowledge oriented Programming platform (VisKoP), a knowledge base question answering (KBQA) system that integrates human into the loop to edit and debug the knowledge base (KB) queries. VisKoP not only provides a neural program induction module, which converts natural language questions into knowledge oriented program language (KoPL), but also maps KoPL programs into graphical elements. KoPL programs can be edited with simple graphical operators, such as dragging to add knowledge operators and slot filling to designate operator arguments. Moreover, VisKoP provides auto-completion for its knowledge base schema and users can easily debug the KoPL program by checking its intermediate results. To facilitate the practical KBQA on a million-entity-level KB, we design a highly efficient KoPL execution engine for the back-end. Experiment results show that VisKoP is highly efficient and user interaction can fix a large portion of wrong KoPL programs to acquire the correct answer. The VisKoP online demo https://demoviskop.xlore.cn (Stable release of this paper) and https://viskop.xlore.cn (Beta release with new features), highly efficient KoPL engine https://pypi.org/project/kopl-engine, and screencast video https://youtu.be/zAbJtxFPTXo are now publicly available.

Functional sufficient dimension reduction through information maximization with application to classification

Considering the case where the response variable is a categorical variable and the predictor is a random function, two novel functional sufficient dimensional reduction (FSDR) methods are proposed based on mutual information and square loss mutual information. Compared to the classical FSDR methods, such as functional sliced inverse regression and functional sliced average variance estimation, the proposed methods are appealing because they are capable of estimating multiple effective dimension reduction directions in the case of a relatively small number of categories, especially for the binary response. Moreover, the proposed methods do not require the restrictive linear conditional mean assumption and the constant covariance assumption. They avoid the inverse problem of the covariance operator which is often encountered in the functional sufficient dimension reduction. The functional principal component analysis with truncation be used as a regularization mechanism. Under some mild conditions, the statistical consistency of the proposed methods is established. It is demonstrated that the two methods are competitive compared with some existing FSDR methods by simulations and real data analyses.

Linguistic More: Taking a Further Step toward Efficient and Accurate Scene Text Recognition

Vision model have gained increasing attention due to their simplicity and efficiency in Scene Text Recognition (STR) task. However, due to lacking the perception of linguistic knowledge and information, recent vision models suffer from two problems: (1) the pure vision-based query results in attention drift, which usually causes poor recognition and is summarized as linguistic insensitive drift (LID) problem in this paper. (2) the visual feature is suboptimal for the recognition in some vision-missing cases (e.g. occlusion, etc.). To address these issues, we propose a $\textbf{L}$inguistic $\textbf{P}$erception $\textbf{V}$ision model (LPV), which explores the linguistic capability of vision model for accurate text recognition. To alleviate the LID problem, we introduce a Cascade Position Attention (CPA) mechanism that obtains high-quality and accurate attention maps through step-wise optimization and linguistic information mining. Furthermore, a Global Linguistic Reconstruction Module (GLRM) is proposed to improve the representation of visual features by perceiving the linguistic information in the visual space, which gradually converts visual features into semantically rich ones during the cascade process. Different from previous methods, our method obtains SOTA results while keeping low complexity (92.4% accuracy with only 8.11M parameters). Code is available at https://github.com/CyrilSterling/LPV.

Federated Covariate Shift Adaptation for Missing Target Output Values

The most recent multi-source covariate shift algorithm is an efficient hyperparameter optimization algorithm for missing target output. In this paper, we extend this algorithm to the framework of federated learning. For data islands in federated learning and covariate shift adaptation, we propose the federated domain adaptation estimate of the target risk which is asymptotically unbiased with a desirable asymptotic variance property. We construct a weighted model for the target task and propose the federated covariate shift adaptation algorithm which works preferably in our setting. The efficacy of our method is justified both theoretically and empirically.

Online Kernel Sliced Inverse Regression

Online dimension reduction is a common method for high-dimensional streaming data processing. Online principal component analysis, online sliced inverse regression, online kernel principal component analysis and other methods have been studied in depth, but as far as we know, online supervised nonlinear dimension reduction methods have not been fully studied. In this article, an online kernel sliced inverse regression method is proposed. By introducing the approximate linear dependence condition and dictionary variable sets, we address the problem of increasing variable dimensions with the sample size in the online kernel sliced inverse regression method, and propose a reduced-order method for updating variables online. We then transform the problem into an online generalized eigen-decomposition problem, and use the stochastic optimization method to update the centered dimension reduction directions. Simulations and the real data analysis show that our method can achieve close performance to batch processing kernel sliced inverse regression.

Federated Sufficient Dimension Reduction Through High-Dimensional Sparse Sliced Inverse Regression

Federated learning has become a popular tool in the big data era nowadays. It trains a centralized model based on data from different clients while keeping data decentralized. In this paper, we propose a federated sparse sliced inverse regression algorithm for the first time. Our method can simultaneously estimate the central dimension reduction subspace and perform variable selection in a federated setting. We transform this federated high-dimensional sparse sliced inverse regression problem into a convex optimization problem by constructing the covariance matrix safely and losslessly. We then use a linearized alternating direction method of multipliers algorithm to estimate the central subspace. We also give approaches of Bayesian information criterion and hold-out validation to ascertain the dimension of the central subspace and the hyper-parameter of the algorithm. We establish an upper bound of the statistical error rate of our estimator under the heterogeneous setting. We demonstrate the effectiveness of our method through simulations and real world applications.

Exploring Stroke-Level Modifications for Scene Text Editing

Scene text editing (STE) aims to replace text with the desired one while preserving background and styles of the original text. However, due to the complicated background textures and various text styles, existing methods fall short in generating clear and legible edited text images. In this study, we attribute the poor editing performance to two problems: 1) Implicit decoupling structure. Previous methods of editing the whole image have to learn different translation rules of background and text regions simultaneously. 2) Domain gap. Due to the lack of edited real scene text images, the network can only be well trained on synthetic pairs and performs poorly on real-world images. To handle the above problems, we propose a novel network by MOdifying Scene Text image at strokE Level (MOSTEL). Firstly, we generate stroke guidance maps to explicitly indicate regions to be edited. Different from the implicit one by directly modifying all the pixels at image level, such explicit instructions filter out the distractions from background and guide the network to focus on editing rules of text regions. Secondly, we propose a Semi-supervised Hybrid Learning to train the network with both labeled synthetic images and unpaired real scene text images. Thus, the STE model is adapted to real-world datasets distributions. Moreover, two new datasets (Tamper-Syn2k and Tamper-Scene) are proposed to fill the blank of public evaluation datasets. Extensive experiments demonstrate that our MOSTEL outperforms previous methods both qualitatively and quantitatively. Datasets and code will be available at https://github.com/qqqyd/MOSTEL.

Pretraining-Based Natural Language Generation for Text Summarization

In this paper, we propose a novel pretraining-based encoder-decoder framework, which can generate the output sequence based on the input sequence in a two-stage manner. For the encoder of our model, we encode the input sequence into context representations using BERT. For the decoder, there are two stages in our model, in the first stage, we use a Transformer-based decoder to generate a draft output sequence. In the second stage, we mask each word of the draft sequence and feed it to BERT, then by combining the input sequence and the draft representation generated by BERT, we use a Transformer-based decoder to predict the refined word for each masked position. To the best of our knowledge, our approach is the first method which applies the BERT into text generation tasks. As the first step in this direction, we evaluate our proposed method on the text summarization task. Experimental results show that our model achieves new state-of-the-art on both CNN/Daily Mail and New York Times datasets.