Related papers: Oracle-MNIST: a Dataset of Oracle Characters for B…

Recently, techniques have been developed to provably guarantee the robustness of a classifier to adversarial perturbations of bounded L_1 and L_2 magnitudes by using randomized smoothing: the robust classification is a consensus of base…

Although deep learning models have taken on commercial and political relevance, key aspects of their training and operation remain poorly understood. This has sparked interest in science of deep learning projects, many of which require…

This project proposes a new method that uses fuzzy comprehensive evaluation method to integrate ResNet-50 self-supervised and RepVGG supervised learning. The source image dataset HWOBC oracle is taken as input, the target image is selected,…

We study the problem of training machine learning models incrementally with batches of samples annotated with noisy oracles. We select each batch of samples that are important and also diverse via clustering and importance sampling. More…

Oracle Bone Inscription (OBI) is the earliest mature writing system in China, which represents a crucial stage in the development of hieroglyphs. Nevertheless, the substantial quantity of undeciphered OBI characters remains a significant…

Deep neural networks (DNNs) trained on large-scale datasets have exhibited significant performance in image classification. Many large-scale datasets are collected from websites, however they tend to contain inaccurate labels that are…

We present MULTICONER V2, a dataset for fine-grained Named Entity Recognition covering 33 entity classes across 12 languages, in both monolingual and multilingual settings. This dataset aims to tackle the following practical challenges in…

Training triplet networks with large-scale data is challenging in face recognition. Due to the number of possible triplets explodes with the number of samples, previous studies adopt the online hard negative mining(OHNM) to handle it.…

Convolutional neural network (CNN) approaches available in the current literature are designed to work primarily with low-resolution images. When applied on very large images, challenges related to GPU memory, smaller receptive field than…

In neural machine translation (NMT), researchers face the challenge of un-seen (or out-of-vocabulary OOV) words translation. To solve this, some researchers propose the splitting of western languages such as English and German into…

Noisy or non-standard input text can cause disastrous mistranslations in most modern Machine Translation (MT) systems, and there has been growing research interest in creating noise-robust MT systems. However, as of yet there are no…

Oracle bone inscriptions (OBIs) contain some of the oldest characters in the world and were used in China about 3000 years ago. As an ancient form of literature, OBIs store a lot of information that can help us understand the world history,…

Robust machine learning depends on clean data, yet current image data cleaning benchmarks rely on synthetic noise or narrow human studies, limiting comparison and real-world relevance. We introduce CleanPatrick, the first large-scale…

Training speech translation (ST) models requires large and high-quality datasets. MuST-C is one of the most widely used ST benchmark datasets. It contains around 400 hours of speech-transcript-translation data for each of the eight…

The proper handling of out-of-distribution (OOD) samples in deep classifiers is a critical concern for ensuring the suitability of deep neural networks in safety-critical systems. Existing approaches developed for robust OOD detection in…

Learning sparse feature representations is a useful instrument for solving an unsupervised learning problem. In this paper, we present three labeled handwritten digit datasets, collectively called n-MNIST. Then, we propose a novel framework…

Optical character recognition (OCR) has advanced rapidly with the rise of vision-language models, yet evaluation has remained concentrated on a small cluster of high- and mid-resource scripts. We introduce GlotOCR Bench, a comprehensive…

Vision Large Language Models (VLLMs) have achieved remarkable success in modern text-rich visual understanding. However, their perceptual robustness in the face of the continuous morphological evolution of historical writing systems remains…

Oracle pruning, which selects unimportant weights by minimizing the pruned train loss, has been taken as the foundation for most neural network pruning methods for over 35 years, while few (if not none) have thought about how much the…

Machine learning methods can automate the in silico design of biological sequences, aiming to reduce costs and accelerate medical research. Given the limited access to wet labs, in silico design methods commonly use an oracle model to…