Related papers: AdaSelection: Accelerating Deep Learning Training …
Event cameras offer high temporal resolution and power efficiency, making them well-suited for edge AI applications. However, their high event rates present challenges for data transmission and processing. Subsampling methods provide a…
This paper proposes an incremental solution to Fast Subclass Discriminant Analysis (fastSDA). We present an exact and an approximate linear solution, along with an approximate kernelized variant. Extensive experiments on eight image…
We propose AdaFamily, a novel method for training deep neural networks. It is a family of adaptive gradient methods and can be interpreted as sort of a blend of the optimization algorithms Adam, AdaBelief and AdaMomentum. We perform…
Training deep networks and tuning hyperparameters on large datasets is computationally intensive. One of the primary research directions for efficient training is to reduce training costs by selecting well-generalizable subsets of training…
The objective of Continual Test-time Domain Adaptation (CTDA) is to gradually adapt a pre-trained model to a sequence of target domains without accessing the source data. This paper proposes a Dynamic Sample Selection (DSS) method for CTDA.…
Meta-learning aims to learn general knowledge with diverse training tasks conducted from limited data, and then transfer it to new tasks. It is commonly believed that increasing task diversity will enhance the generalization ability of…
The incorporation of advanced sensors and machine learning techniques has enabled modern manufacturing enterprises to perform data-driven classification-based anomaly detection based on the sensor data collected in manufacturing processes.…
The ability to train complex and highly effective models often requires an abundance of training data, which can easily become a bottleneck in cost, time, and computational resources. Batch active learning, which adaptively issues batched…
Affordable 3D scanners often produce sparse and non-uniform point clouds that negatively impact downstream applications in robotic systems. While existing point cloud upsampling architectures have demonstrated promising results on standard…
Discrete diffusion models (DDMs) have shown powerful generation ability for discrete data modalities like text and molecules. However, their practical application is hindered by inefficient sampling, requiring a large number of sampling…
Meta-learning synthesizes and leverages the knowledge from a given set of tasks to rapidly learn new tasks using very little data. Meta-learning of linear regression tasks, where the regressors lie in a low-dimensional subspace, is an…
Annotating training data for sequence tagging of texts is usually very time-consuming. Recent advances in transfer learning for natural language processing in conjunction with active learning open the possibility to significantly reduce the…
The emerging task of fine-grained image classification in low-data regimes assumes the presence of low inter-class variance and large intra-class variation along with a highly limited amount of training samples per class. However,…
Massive data analysis becomes increasingly prevalent, subsampling methods like BLB (Bag of Little Bootstraps) serves as powerful tools for assessing the quality of estimators for massive data. However, the performance of the subsampling…
Prompt-based learning, with its capability to tackle zero-shot and few-shot NLP tasks, has gained much attention in community. The main idea is to bridge the gap between NLP downstream tasks and language modeling (LM), by mapping these…
Self-Taught Reasoners (STaR), synonymously known as Rejection sampling Fine-Tuning (RFT), is an integral part of the training pipeline of self-improving reasoning Language Models (LMs). The self-improving mechanism often employs random…
Recent advances in image synthesis have been propelled by powerful generative models, such as Masked Generative Transformers (MaskGIT), autoregressive models, diffusion models, and rectified flow models. A common principle behind their…
Data sampling is an effective method to improve the training speed of neural networks, with recent results demonstrating that it can even break the neural scaling laws. These results critically rely on high-quality scores to estimate the…
One-class classification has been a prevailing method in building deep anomaly detection models under the assumption that a dataset consisting of normal samples is available. In practice, however, abnormal samples are often mixed in a…
Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…