CREPE: Coordinate-Aware End-to-End Document Parser

In this study, we formulate an OCR-free sequence generation model for visual document understanding (VDU). Our model not only parses text from document images but also extracts the spatial coordinates of the text based on the multi-head architecture. Named as Coordinate-aware End-to-end Document Parser (CREPE), our method uniquely integrates these capabilities by introducing a special token for OCR text, and token-triggered coordinate decoding. We also proposed a weakly-supervised framework for cost-efficient training, requiring only parsing annotations without high-cost coordinate annotations. Our experimental evaluations demonstrate CREPE's state-of-the-art performances on document parsing tasks. Beyond that, CREPE's adaptability is further highlighted by its successful usage in other document understanding tasks such as layout analysis, document visual question answering, and so one. CREPE's abilities including OCR and semantic parsing not only mitigate error propagation issues in existing OCR-dependent methods, it also significantly enhance the functionality of sequence generation models, ushering in a new era for document understanding studies.

HyperCLOVA X Technical Report

We introduce HyperCLOVA X, a family of large language models (LLMs) tailored to the Korean language and culture, along with competitive capabilities in English, math, and coding. HyperCLOVA X was trained on a balanced mix of Korean, English, and code data, followed by instruction-tuning with high-quality human-annotated datasets while abiding by strict safety guidelines reflecting our commitment to responsible AI. The model is evaluated across various benchmarks, including comprehensive reasoning, knowledge, commonsense, factuality, coding, math, chatting, instruction-following, and harmlessness, in both Korean and English. HyperCLOVA X exhibits strong reasoning capabilities in Korean backed by a deep understanding of the language and cultural nuances. Further analysis of the inherent bilingual nature and its extension to multilingualism highlights the model's cross-lingual proficiency and strong generalization ability to untargeted languages, including machine translation between several language pairs and cross-lingual inference tasks. We believe that HyperCLOVA X can provide helpful guidance for regions or countries in developing their sovereign LLMs.

EGTR: Extracting Graph from Transformer for Scene Graph Generation

Scene Graph Generation (SGG) is a challenging task of detecting objects and predicting relationships between objects. After DETR was developed, one-stage SGG models based on a one-stage object detector have been actively studied. However, complex modeling is used to predict the relationship between objects, and the inherent relationship between object queries learned in the multi-head self-attention of the object detector has been neglected. We propose a lightweight one-stage SGG model that extracts the relation graph from the various relationships learned in the multi-head self-attention layers of the DETR decoder. By fully utilizing the self-attention by-products, the relation graph can be extracted effectively with a shallow relation extraction head. Considering the dependency of the relation extraction task on the object detection task, we propose a novel relation smoothing technique that adjusts the relation label adaptively according to the quality of the detected objects. By the relation smoothing, the model is trained according to the continuous curriculum that focuses on object detection task at the beginning of training and performs multi-task learning as the object detection performance gradually improves. Furthermore, we propose a connectivity prediction task that predicts whether a relation exists between object pairs as an auxiliary task of the relation extraction. We demonstrate the effectiveness and efficiency of our method for the Visual Genome and Open Image V6 datasets. Our code is publicly available at https://github.com/naver-ai/egtr.

Cream: Visually-Situated Natural Language Understanding with Contrastive Reading Model and Frozen Large Language Models

Advances in Large Language Models (LLMs) have inspired a surge of research exploring their expansion into the visual domain. While recent models exhibit promise in generating abstract captions for images and conducting natural conversations, their performance on text-rich images leaves room for improvement. In this paper, we propose the Contrastive Reading Model (Cream), a novel neural architecture designed to enhance the language-image understanding capability of LLMs by capturing intricate details typically overlooked by existing methods. Cream integrates vision and auxiliary encoders, complemented by a contrastive feature alignment technique, resulting in a more effective understanding of textual information within document images. Our approach, thus, seeks to bridge the gap between vision and language understanding, paving the way for more sophisticated Document Intelligence Assistants. Rigorous evaluations across diverse tasks, such as visual question answering on document images, demonstrate the efficacy of Cream as a state-of-the-art model in the field of visual document understanding. We provide our codebase and newly-generated datasets at https://github.com/naver-ai/cream

Grounding Visual Representations with Texts for Domain Generalization

Reducing the representational discrepancy between source and target domains is a key component to maximize the model generalization. In this work, we advocate for leveraging natural language supervision for the domain generalization task. We introduce two modules to ground visual representations with texts containing typical reasoning of humans: (1) Visual and Textual Joint Embedder and (2) Textual Explanation Generator. The former learns the image-text joint embedding space where we can ground high-level class-discriminative information into the model. The latter leverages an explainable model and generates explanations justifying the rationale behind its decision. To the best of our knowledge, this is the first work to leverage the vision-and-language cross-modality approach for the domain generalization task. Our experiments with a newly created CUB-DG benchmark dataset demonstrate that cross-modality supervision can be successfully used to ground domain-invariant visual representations and improve the model generalization. Furthermore, in the large-scale DomainBed benchmark, our proposed method achieves state-of-the-art results and ranks 1st in average performance for five multi-domain datasets. The dataset and codes are available at https://github.com/mswzeus/GVRT.

An Embedding-Dynamic Approach to Self-supervised Learning

A number of recent self-supervised learning methods have shown impressive performance on image classification and other tasks. A somewhat bewildering variety of techniques have been used, not always with a clear understanding of the reasons for their benefits, especially when used in combination. Here we treat the embeddings of images as point particles and consider model optimization as a dynamic process on this system of particles. Our dynamic model combines an attractive force for similar images, a locally dispersive force to avoid local collapse, and a global dispersive force to achieve a globally-homogeneous distribution of particles. The dynamic perspective highlights the advantage of using a delayed-parameter image embedding (a la BYOL) together with multiple views of the same image. It also uses a purely-dynamic local dispersive force (Brownian motion) that shows improved performance over other methods and does not require knowledge of other particle coordinates. The method is called MSBReg which stands for (i) a Multiview centroid loss, which applies an attractive force to pull different image view embeddings toward their centroid, (ii) a Singular value loss, which pushes the particle system toward spatially homogeneous density, (iii) a Brownian diffusive loss. We evaluate downstream classification performance of MSBReg on ImageNet as well as transfer learning tasks including fine-grained classification, multi-class object classification, object detection, and instance segmentation. In addition, we also show that applying our regularization term to other methods further improves their performance and stabilize the training by preventing a mode collapse.

DEER: Detection-agnostic End-to-End Recognizer for Scene Text Spotting

Recent end-to-end scene text spotters have achieved great improvement in recognizing arbitrary-shaped text instances. Common approaches for text spotting use region of interest pooling or segmentation masks to restrict features to single text instances. However, this makes it hard for the recognizer to decode correct sequences when the detection is not accurate i.e. one or more characters are cropped out. Considering that it is hard to accurately decide word boundaries with only the detector, we propose a novel Detection-agnostic End-to-End Recognizer, DEER, framework. The proposed method reduces the tight dependency between detection and recognition modules by bridging them with a single reference point for each text instance, instead of using detected regions. The proposed method allows the decoder to recognize the texts that are indicated by the reference point, with features from the whole image. Since only a single point is required to recognize the text, the proposed method enables text spotting without an arbitrarily-shaped detector or bounding polygon annotations. Experimental results present that the proposed method achieves competitive results on regular and arbitrarily-shaped text spotting benchmarks. Further analysis shows that DEER is robust to the detection errors. The code and dataset will be publicly available.

Semi-Structured Query Grounding for Document-Oriented Databases with Deep Retrieval and Its Application to Receipt and POI Matching

Semi-structured query systems for document-oriented databases have many real applications. One particular application that we are interested in is matching each financial receipt image with its corresponding place of interest (POI, e.g., restaurant) in the nationwide database. The problem is especially challenging in the real production environment where many similar or incomplete entries exist in the database and queries are noisy (e.g., errors in optical character recognition). In this work, we aim to address practical challenges when using embedding-based retrieval for the query grounding problem in semi-structured data. Leveraging recent advancements in deep language encoding for retrieval, we conduct extensive experiments to find the most effective combination of modules for the embedding and retrieval of both query and database entries without any manually engineered component. The proposed model significantly outperforms the conventional manual pattern-based model while requiring much less development and maintenance cost. We also discuss some core observations in our experiments, which could be helpful for practitioners working on a similar problem in other domains.

Donut: Document Understanding Transformer without OCR

Understanding document images (e.g., invoices) has been an important research topic and has many applications in document processing automation. Through the latest advances in deep learning-based Optical Character Recognition (OCR), current Visual Document Understanding (VDU) systems have come to be designed based on OCR. Although such OCR-based approach promise reasonable performance, they suffer from critical problems induced by the OCR, e.g., (1) expensive computational costs and (2) performance degradation due to the OCR error propagation. In this paper, we propose a novel VDU model that is end-to-end trainable without underpinning OCR framework. To this end, we propose a new task and a synthetic document image generator to pre-train the model to mitigate the dependencies on large-scale real document images. Our approach achieves state-of-the-art performance on various document understanding tasks in public benchmark datasets and private industrial service datasets. Through extensive experiments and analysis, we demonstrate the effectiveness of the proposed model especially with consideration for a real-world application.

SelfReg: Self-supervised Contrastive Regularization for Domain Generalization

In general, an experimental environment for deep learning assumes that the training and the test dataset are sampled from the same distribution. However, in real-world situations, a difference in the distribution between two datasets, domain shift, may occur, which becomes a major factor impeding the generalization performance of the model. The research field to solve this problem is called domain generalization, and it alleviates the domain shift problem by extracting domain-invariant features explicitly or implicitly. In recent studies, contrastive learning-based domain generalization approaches have been proposed and achieved high performance. These approaches require sampling of the negative data pair. However, the performance of contrastive learning fundamentally depends on quality and quantity of negative data pairs. To address this issue, we propose a new regularization method for domain generalization based on contrastive learning, self-supervised contrastive regularization (SelfReg). The proposed approach use only positive data pairs, thus it resolves various problems caused by negative pair sampling. Moreover, we propose a class-specific domain perturbation layer (CDPL), which makes it possible to effectively apply mixup augmentation even when only positive data pairs are used. The experimental results show that the techniques incorporated by SelfReg contributed to the performance in a compatible manner. In the recent benchmark, DomainBed, the proposed method shows comparable performance to the conventional state-of-the-art alternatives. Codes are available at https://github.com/dnap512/SelfReg.