In recent years, the optical character recognition (OCR) field has been proliferating with plentiful cutting-edge approaches for a wide spectrum of tasks. However, these approaches are task-specifically designed with divergent paradigms, architectures, and training strategies, which significantly increases the complexity of research and maintenance and hinders the fast deployment in applications. To this end, we propose UPOCR, a simple-yet-effective generalist model for Unified Pixel-level OCR interface. Specifically, the UPOCR unifies the paradigm of diverse OCR tasks as image-to-image transformation and the architecture as a vision Transformer (ViT)-based encoder-decoder. Learnable task prompts are introduced to push the general feature representations extracted by the encoder toward task-specific spaces, endowing the decoder with task awareness. Moreover, the model training is uniformly aimed at minimizing the discrepancy between the generated and ground-truth images regardless of the inhomogeneity among tasks. Experiments are conducted on three pixel-level OCR tasks including text removal, text segmentation, and tampered text detection. Without bells and whistles, the experimental results showcase that the proposed method can simultaneously achieve state-of-the-art performance on three tasks with a unified single model, which provides valuable strategies and insights for future research on generalist OCR models. Code will be publicly available.
This paper presents a comprehensive evaluation of the Optical Character Recognition (OCR) capabilities of the recently released GPT-4V(ision), a Large Multimodal Model (LMM). We assess the model's performance across a range of OCR tasks, including scene text recognition, handwritten text recognition, handwritten mathematical expression recognition, table structure recognition, and information extraction from visually-rich document. The evaluation reveals that GPT-4V performs well in recognizing and understanding Latin contents, but struggles with multilingual scenarios and complex tasks. Specifically, it showed limitations when dealing with non-Latin languages and complex tasks such as handwriting mathematical expression recognition, table structure recognition, and end-to-end semantic entity recognition and pair extraction from document image. Based on these observations, we affirm the necessity and continued research value of specialized OCR models. In general, despite its versatility in handling diverse OCR tasks, GPT-4V does not outperform existing state-of-the-art OCR models. How to fully utilize pre-trained general-purpose LMMs such as GPT-4V for OCR downstream tasks remains an open problem. The study offers a critical reference for future research in OCR with LMMs. Evaluation pipeline and results are available at https://github.com/SCUT-DLVCLab/GPT-4V_OCR.
Fine-tuning pre-trained Vision Transformers (ViT) has consistently demonstrated promising performance in the realm of visual recognition. However, adapting large pre-trained models to various tasks poses a significant challenge. This challenge arises from the need for each model to undergo an independent and comprehensive fine-tuning process, leading to substantial computational and memory demands. While recent advancements in Parameter-efficient Transfer Learning (PETL) have demonstrated their ability to achieve superior performance compared to full fine-tuning with a smaller subset of parameter updates, they tend to overlook dense prediction tasks such as object detection and segmentation. In this paper, we introduce Hierarchical Side-Tuning (HST), a novel PETL approach that enables ViT transfer to various downstream tasks effectively. Diverging from existing methods that exclusively fine-tune parameters within input spaces or certain modules connected to the backbone, we tune a lightweight and hierarchical side network (HSN) that leverages intermediate activations extracted from the backbone and generates multi-scale features to make predictions. To validate HST, we conducted extensive experiments encompassing diverse visual tasks, including classification, object detection, instance segmentation, and semantic segmentation. Notably, our method achieves state-of-the-art average Top-1 accuracy of 76.0% on VTAB-1k, all while fine-tuning a mere 0.78M parameters. When applied to object detection tasks on COCO testdev benchmark, HST even surpasses full fine-tuning and obtains better performance with 49.7 box AP and 43.2 mask AP using Cascade Mask R-CNN.
In recent years, end-to-end scene text spotting approaches are evolving to the Transformer-based framework. While previous studies have shown the crucial importance of the intrinsic synergy between text detection and recognition, recent advances in Transformer-based methods usually adopt an implicit synergy strategy with shared query, which can not fully realize the potential of these two interactive tasks. In this paper, we argue that the explicit synergy considering distinct characteristics of text detection and recognition can significantly improve the performance text spotting. To this end, we introduce a new model named Explicit Synergy-based Text Spotting Transformer framework (ESTextSpotter), which achieves explicit synergy by modeling discriminative and interactive features for text detection and recognition within a single decoder. Specifically, we decompose the conventional shared query into task-aware queries for text polygon and content, respectively. Through the decoder with the proposed vision-language communication module, the queries interact with each other in an explicit manner while preserving discriminative patterns of text detection and recognition, thus improving performance significantly. Additionally, we propose a task-aware query initialization scheme to ensure stable training. Experimental results demonstrate that our model significantly outperforms previous state-of-the-art methods. Code is available at https://github.com/mxin262/ESTextSpotter.
This paper presents a new vision Transformer, Scale-Aware Modulation Transformer (SMT), that can handle various downstream tasks efficiently by combining the convolutional network and vision Transformer. The proposed Scale-Aware Modulation (SAM) in the SMT includes two primary novel designs. Firstly, we introduce the Multi-Head Mixed Convolution (MHMC) module, which can capture multi-scale features and expand the receptive field. Secondly, we propose the Scale-Aware Aggregation (SAA) module, which is lightweight but effective, enabling information fusion across different heads. By leveraging these two modules, convolutional modulation is further enhanced. Furthermore, in contrast to prior works that utilized modulations throughout all stages to build an attention-free network, we propose an Evolutionary Hybrid Network (EHN), which can effectively simulate the shift from capturing local to global dependencies as the network becomes deeper, resulting in superior performance. Extensive experiments demonstrate that SMT significantly outperforms existing state-of-the-art models across a wide range of visual tasks. Specifically, SMT with 11.5M / 2.4GFLOPs and 32M / 7.7GFLOPs can achieve 82.2% and 84.3% top-1 accuracy on ImageNet-1K, respectively. After pretrained on ImageNet-22K in 224^2 resolution, it attains 87.1% and 88.1% top-1 accuracy when finetuned with resolution 224^2 and 384^2, respectively. For object detection with Mask R-CNN, the SMT base trained with 1x and 3x schedule outperforms the Swin Transformer counterpart by 4.2 and 1.3 mAP on COCO, respectively. For semantic segmentation with UPerNet, the SMT base test at single- and multi-scale surpasses Swin by 2.0 and 1.1 mIoU respectively on the ADE20K.
This paper aims to re-assess scene text recognition (STR) from a data-oriented perspective. We begin by revisiting the six commonly used benchmarks in STR and observe a trend of performance saturation, whereby only 2.91% of the benchmark images cannot be accurately recognized by an ensemble of 13 representative models. While these results are impressive and suggest that STR could be considered solved, however, we argue that this is primarily due to the less challenging nature of the common benchmarks, thus concealing the underlying issues that STR faces. To this end, we consolidate a large-scale real STR dataset, namely Union14M, which comprises 4 million labeled images and 10 million unlabeled images, to assess the performance of STR models in more complex real-world scenarios. Our experiments demonstrate that the 13 models can only achieve an average accuracy of 66.53% on the 4 million labeled images, indicating that STR still faces numerous challenges in the real world. By analyzing the error patterns of the 13 models, we identify seven open challenges in STR and develop a challenge-driven benchmark consisting of eight distinct subsets to facilitate further progress in the field. Our exploration demonstrates that STR is far from being solved and leveraging data may be a promising solution. In this regard, we find that utilizing the 10 million unlabeled images through self-supervised pre-training can significantly improve the robustness of STR model in real-world scenarios and leads to state-of-the-art performance.
Scene text removal (STR) aims at replacing text strokes in natural scenes with visually coherent backgrounds. Recent STR approaches rely on iterative refinements or explicit text masks, resulting in higher complexity and sensitivity to the accuracy of text localization. Moreover, most existing STR methods utilize convolutional neural networks (CNNs) for feature representation while the potential of vision Transformers (ViTs) remains largely unexplored. In this paper, we propose a simple-yet-effective ViT-based text eraser, dubbed ViTEraser. Following a concise encoder-decoder framework, different types of ViTs can be easily integrated into ViTEraser to enhance the long-range dependencies and global reasoning. Specifically, the encoder hierarchically maps the input image into the hidden space through ViT blocks and patch embedding layers, while the decoder gradually upsamples the hidden features to the text-erased image with ViT blocks and patch splitting layers. As ViTEraser implicitly integrates text localization and inpainting, we propose a novel end-to-end pretraining method, termed SegMIM, which focuses the encoder and decoder on the text box segmentation and masked image modeling tasks, respectively. To verify the effectiveness of the proposed methods, we comprehensively explore the architecture, pretraining, and scalability of the ViT-based encoder-decoder for STR, which provides deep insights into the application of ViT to STR. Experimental results demonstrate that ViTEraser with SegMIM achieves state-of-the-art performance on STR by a substantial margin. Furthermore, the extended experiment on tampered scene text detection demonstrates the generality of ViTEraser to other tasks. We believe this paper can inspire more research on ViT-based STR approaches. Code will be available at https://github.com/shannanyinxiang/ViTEraser.
Recently, there has been a growing interest in research concerning document image analysis and recognition in photographic scenarios. However, the lack of labeled datasets for this emerging challenge poses a significant obstacle, as manual annotation can be time-consuming and impractical. To tackle this issue, we present DocAligner, a novel method that streamlines the manual annotation process to a simple step of taking pictures. DocAligner achieves this by establishing dense correspondence between photographic document images and their clean counterparts. It enables the automatic transfer of existing annotations in clean document images to photographic ones and helps to automatically acquire labels that are unavailable through manual labeling. Considering the distinctive characteristics of document images, DocAligner incorporates several innovative features. First, we propose a non-rigid pre-alignment technique based on the document's edges, which effectively eliminates interference caused by significant global shifts and repetitive patterns present in document images. Second, to handle large shifts and ensure high accuracy, we introduce a hierarchical aligning approach that combines global and local correlation layers. Furthermore, considering the importance of fine-grained elements in document images, we present a details recurrent refinement module to enhance the output in a high-resolution space. To train DocAligner, we construct a synthetic dataset and introduce a self-supervised learning approach to enhance its robustness for real-world data. Through extensive experiments, we demonstrate the effectiveness of DocAligner and the acquired dataset. Datasets and codes will be publicly available.