Related papers: LayeredDoc: Domain Adaptive Document Restoration w…
As global cross-lingual communication intensifies, language barriers in visually rich documents such as PDFs remain a practical bottleneck. Existing document translation pipelines face a tension between linguistic processing and layout…
We propose Diverse Restormer (DART), a novel image restoration method that effectively integrates information from various sources (long sequences, local and global regions, feature dimensions, and positional dimensions) to address…
Recent research efforts have shown that neural architectures can be effective in conventional information extraction tasks such as named entity recognition, yielding state-of-the-art results on standard newswire datasets. However, despite…
Domain adaptation, a pivotal branch of transfer learning, aims to enhance the performance of machine learning models when deployed in target domains with distinct data distributions. This is particularly critical for object detection tasks,…
Deep domain adaption has emerged as a new learning technique to address the lack of massive amounts of labeled data. Compared to conventional methods, which learn shared feature subspaces or reuse important source instances with shallow…
This work introduces CLIP-aware Domain-Adaptive Super-Resolution (CDASR), a novel framework that addresses the critical challenge of domain generalization in single image super-resolution. By leveraging the semantic capabilities of CLIP…
Domain adaptive text classification is a challenging problem for the large-scale pretrained language models because they often require expensive additional labeled data to adapt to new domains. Existing works usually fails to leverage the…
Most existing image restoration methods use neural networks to learn strong image-level priors from huge data to estimate the lost information. However, these works still struggle in cases when images have severe information deficits.…
Remote sensing image segmentation faces persistent challenges in distinguishing morphologically similar categories and adapting to diverse scene variations. While existing methods rely on implicit representation learning paradigms, they…
Large ground-truth datasets and recent advances in deep learning techniques have been useful for layout detection. However, because of the restricted layout diversity of these datasets, training on them requires a sizable number of…
Camera-captured document images often suffer from geometric distortions caused by paper deformation, perspective distortion, and lens aberrations, significantly reducing OCR accuracy. This study develops an efficient automated method for…
Unsupervised domain adaptation enables to alleviate the need for pixel-wise annotation in the semantic segmentation. One of the most common strategies is to translate images from the source domain to the target domain and then align their…
Domain specific information retrieval process has been a prominent and ongoing research in the field of natural language processing. Many researchers have incorporated different techniques to overcome the technical and domain specificity…
Document dewarping from a distorted camera-captured image is of great value for OCR and document understanding. The document boundary plays an important role which is more evident than the inner region in document dewarping. Current…
We introduce a novel unsupervised domain adaptation approach for object detection. We aim to alleviate the imperfect translation problem of pixel-level adaptations, and the source-biased discriminativity problem of feature-level adaptations…
The robustness of a model for real-world deployment is decided by how well it performs on unseen data and distinguishes between in-domain and out-of-domain samples. Visual document classifiers have shown impressive performance on…
High-resolution processing of seismic signals is crucial for subsurface geological characterization and thin-layer reservoir identification. Traditional high-resolution algorithms can partially recover high-frequency information but often…
Repair performance in hierarchical data centers is often bottlenecked by cross-rack network transfer. Recent theoretical results show that the cross-rack repair traffic can be minimized through repair layering, whose idea is to partition a…
Cross-domain recommendation has long been one of the major topics in recommender systems. Recently, various deep models have been proposed to transfer the learned knowledge across domains, but most of them focus on extracting abstract…
The introduction of generative models has significantly advanced image super-resolution (SR) in handling real-world degradations. However, they often incur fidelity-related issues, particularly distorting textual structures. In this paper,…