相关论文: Revisiting Unreasonable Effectiveness of Data in D…

Recent successes in visual recognition can be primarily attributed to feature representation, learning algorithms, and the ever-increasing size of labeled training data. Extensive research has been devoted to the first two, but much less…

Representation learning becomes especially important for complex systems with multimodal data sources such as cameras or sensors. Recent advances in reinforcement learning and optimal control make it possible to design control algorithms on…

Machine Learning algorithms have had a profound impact on the field of computer science over the past few decades. These algorithms performance is greatly influenced by the representations that are derived from the data in the learning…

The rapid progress in machine learning methods has been empowered by i) huge datasets that have been collected and annotated, ii) improved engineering (e.g. data pre-processing/normalization). The existing datasets typically include several…

Recent self-supervised representation learning techniques have largely closed the gap between supervised and unsupervised learning on ImageNet classification. While the particulars of pretraining on ImageNet are now relatively well…

Data size is the bottleneck for developing deep saliency models, because collecting eye-movement data is very time consuming and expensive. Most of current studies on human attention and saliency modeling have used high quality stereotype…

The reliance on large-scale datasets and extensive computational resources has become a major barrier to advancing representation learning in vision, especially in data-scarce domains. In this paper, we address the critical question: Can we…

Data seems cheap to get, and in many ways it is, but the process of creating a high quality labeled dataset from a mass of data is time-consuming and expensive. With the advent of rich 3D repositories, photo-realistic rendering systems…

Recent advances in self-supervised learning have highlighted the efficacy of data augmentation in learning data representation from unlabeled data. Training a linear model atop these enhanced representations can yield an adept classifier.…

Big data has ushered in a new wave of predictive power using machine learning models. In this work, we assess what {\it big} means in the context of typical materials-science machine-learning problems. This concerns not only data volume,…

Representation learning from unlabeled data has been extensively studied in statistics, data science and signal processing with a rich literature on techniques for dimension reduction, compression, multi-dimensional scaling among others.…

Modern machine learning suffers from catastrophic forgetting when learning new classes incrementally. The performance dramatically degrades due to the missing data of old classes. Incremental learning methods have been proposed to retain…

Humans have a remarkably large capacity to store detailed visual information in long-term memory even after a single exposure, as demonstrated by classic experiments in psychology. For example, Standing (1973) showed that humans could…

Learning representations of data is an important problem in statistics and machine learning. While the origin of learning representations can be traced back to factor analysis and multidimensional scaling in statistics, it has become a…

Machine learning continues to grow in popularity due to its ability to learn increasingly complex tasks. However, for many supervised models, the shift in a data distribution or the appearance of a new event can result in a severe decrease…

ConvNets achieve good results when training from clean data, but learning from noisy labels significantly degrades performances and remains challenging. Unlike previous works constrained by many conditions, making them infeasible to real…

Neural network models can now recognise images, understand text, translate languages, and play many human games at human or superhuman levels. These systems are highly abstracted, but are inspired by biological brains and use only…

Recent advancements in deep learning have been primarily driven by the use of large models trained on increasingly vast datasets. While neural scaling laws have emerged to predict network performance given a specific level of computational…

The optimal training of a vision transformer for brain encoding depends on three factors: model size, data size, and computational resources. This study investigates these three pillars, focusing on the effects of data scaling, model…

We investigate the potential of machine learning models for the prediction of visual improvement after macular hole surgery from preoperative data (retinal images and clinical features). Collecting our own data for the task, we end up with…