Related papers: Enabling On-Device Learning via Experience Replay …

We present a new method to learn video representations from unlabeled data. Given large-scale unlabeled video data, the objective is to benefit from such data by learning a generic and transferable representation space that can be directly…

On-device session-based recommendation systems have been achieving increasing attention on account of the low energy/resource consumption and privacy protection while providing promising recommendation performance. To fit the powerful…

Dataset Condensation (DC) aims to obtain a condensed dataset that allows models trained on the condensed dataset to achieve performance comparable to those trained on the full dataset. Recent DC approaches increasingly focus on encoding…

Few-shot learning has been extensively explored to address problems where the amount of labeled samples is very limited for some classes. In the semi-supervised few-shot learning setting, substantial quantities of unlabeled samples are…

Learning with noisy labels has aroused much research interest since data annotations, especially for large-scale datasets, may be inevitably imperfect. Recent approaches resort to a semi-supervised learning problem by dividing training…

Recent work on distilling Whisper's knowledge into small models using pseudo-labels shows promising performance while reducing the size by up to 50%. This results in small, efficient, and dedicated models. However, a critical step of…

Online Knowledge Distillation (KD) is recently highlighted to train large models in Federated Learning (FL) environments. Many existing studies adopt the logit ensemble method to perform KD on the server side. However, they often assume…

The study of label noise in sound event recognition has recently gained attention with the advent of larger and noisier datasets. This work addresses the problem of missing labels, one of the big weaknesses of large audio datasets, and one…

Dataset condensation aims to condense a large dataset with a lot of training samples into a small set. Previous methods usually condense the dataset into the pixels format. However, it suffers from slow optimization speed and large number…

Continuously learning new classes without catastrophic forgetting is a challenging problem for on-device environmental sound classification given the restrictions on computation resources (e.g., model size, running memory). To address this…

Modern recommender systems operate in a fully server-based fashion. To cater to millions of users, the frequent model maintaining and the high-speed processing for concurrent user requests are required, which comes at the cost of a huge…

To safely deploy autonomous vehicles, onboard perception systems must work reliably at high accuracy across a diverse set of environments and geographies. One of the most common techniques to improve the efficacy of such systems in new…

Given an unlabeled dataset and an annotation budget, we study how to selectively label a fixed number of instances so that semi-supervised learning (SSL) on such a partially labeled dataset is most effective. We focus on selecting the right…

The goal of test-time adaptation is to adapt a source-pretrained model to a continuously changing target domain without relying on any source data. Typically, this is either done by updating the parameters of the model (model adaptation)…

Label noise may affect the generalization of classifiers, and the effective learning of main patterns from samples with noisy labels is an important challenge. Recent studies have shown that deep neural networks tend to prioritize the…

Dataset pruning reduces the storage and training costs of deep learning by selecting an informative subset from a large dataset. However, most existing pruning methods require fully labeled data, which limits their applicability in…

In semi-supervised representation learning frameworks, when the number of labelled data is very scarce, the quality and representativeness of these samples become increasingly important. Existing literature on semi-supervised learning…

Many attempts have been done to extend the great success of convolutional neural networks (CNNs) achieved on high-end GPU servers to portable devices such as smart phones. Providing compression and acceleration service of deep learning…

Most existing distance metric learning approaches use fully labeled data to learn the sample similarities in an embedding space. We present a self-training framework, SLADE, to improve retrieval performance by leveraging additional…

Edge learning facilitates ubiquitous intelligence by enabling model training and adaptation directly on data-generating devices, thereby mitigating privacy risks and communication latency. However, the high computational and energy overhead…