Related papers: The Document Vectors Using Cosine Similarity Revis…

Cosine similarity is a widely used measure of the relatedness of pre-trained word embeddings, trained on a language modeling goal. Datasets such as WordSim-353 and SimLex-999 rate how similar words are according to human annotators, and as…

In the robotics literature, different knowledge transfer approaches have been proposed to leverage the experience from a source task or robot -- real or virtual -- to accelerate the learning process on a new task or robot. A commonly made…

Deep neural object detection or segmentation networks are commonly trained with pristine, uncompressed data. However, in practical applications the input images are usually deteriorated by compression that is applied to efficiently transmit…

Vector averaging remains one of the most popular sentence embedding methods in spite of its obvious disregard for syntactic structure. While more complex sequential or convolutional networks potentially yield superior classification…

For visual document understanding (VDU), self-supervised pretraining has been shown to successfully generate transferable representations, yet, effective adaptation of such representations to distribution shifts at test-time remains to be…

One major drawback of state of the art Neural Networks (NN)-based approaches for document classification purposes is the large number of training samples required to obtain an efficient classification. The minimum required number is around…

Recent studies demonstrated the eligibility of convolutional neural networks (CNNs) for solving the image registration problem. CNNs enable faster transformation estimation and greater generalization capability needed for better support…

Visual Odometry (VO) is used in many applications including robotics and autonomous systems. However, traditional approaches based on feature matching are computationally expensive and do not directly address failure cases, instead relying…

We present an exhaustive investigation of recent Deep Learning architectures, algorithms, and strategies for the task of document image classification to finally reduce the error by more than half. Existing approaches, such as the…

Despite the success of distributional semantics, composing phrases from word vectors remains an important challenge. Several methods have been tried for benchmark tasks such as sentiment classification, including word vector averaging,…

Document expansion is a classical technique for improving retrieval quality, and is attractive since it shifts computation offline, avoiding additional query-time processing. However, when applied to modern retrievers, it has been shown to…

For most natural language processing tasks, the dominant practice is to finetune large pretrained transformer models (e.g., BERT) using smaller downstream datasets. Despite the success of this approach, it remains unclear to what extent…

The accuracy of deformable image registration (DIR) has a significant dosimetric impact in radiation treatment planning. We evaluated accuracy of various DIR algorithms using variations of the deformation point and volume. The reference…

Quantization of weights of deep neural networks (DNN) has proven to be an effective solution for the purpose of implementing DNNs on edge devices such as mobiles, ASICs and FPGAs, because they have no sufficient resources to support…

This paper shows that further evaluation metrics during model training are needed to decide about its applicability in inference. As an example, a LayoutLM-based model is trained for token classification in documents. The documents are…

Tracking-by-detection methods have demonstrated competitive performance in recent years. In these approaches, the tracking model heavily relies on the quality of the training set. Due to the limited amount of labeled training data,…

Wedemonstratedeep-learningneuralnetwork(NN)-baseddynamicopticalcoherence tomography (DOCT), which generates high-quality logarithmic-intensity-variance (LIV) DOCT images from only four OCT frames. The NN model is trained for tumor spheroid…

Binarization of document images is an important pre-processing step in the field of document analysis. Traditional image binarization techniques usually rely on histograms or local statistics to identify a valid threshold to differentiate…

Previous studies have compared neural activities in the visual cortex to representations in deep neural networks trained on image classification. Interestingly, while some suggest that their representations are highly similar, others argued…

The processing of Visually-Rich Documents (VRDs) is highly important in information extraction tasks associated with Document Intelligence. We introduce DI-Metrics, a Python library devoted to VRD model evaluation comprising text-based,…