Zobrazeno 1 - 10
of 840
pro vyhledávání: '"Li, Mengke"'
Personalized Federated Learning (PFL) aims to acquire customized models for each client without disclosing raw data by leveraging the collective knowledge of distributed clients. However, the data collected in real-world scenarios is likely to follow
Externí odkaz:
http://arxiv.org/abs/2408.02019
Pre-trained large-scale models have exhibited remarkable efficacy in computer vision, particularly for 2D image analysis. However, when it comes to 3D point clouds, the constrained accessibility of data, in contrast to the vast repositories of images
Externí odkaz:
http://arxiv.org/abs/2407.13200
The vision-language pre-training has enabled deep models to make a huge step forward in generalizing across unseen domains. The recent learning method based on the vision-language pre-training model is a great tool for domain generalization and can s
Externí odkaz:
http://arxiv.org/abs/2404.18758
Existing continual learning literature relies heavily on a strong assumption that tasks arrive with a balanced data stream, which is often unrealistic in real-world applications. In this work, we explore task-imbalanced continual learning (TICL) scen
Externí odkaz:
http://arxiv.org/abs/2404.14721
Knowledge distillation (KD) has become a widely used technique in the field of model compression, which aims to transfer knowledge from a large teacher model to a lightweight student model for efficient network development. In addition to the supervi
Externí odkaz:
http://arxiv.org/abs/2404.03693
The imbalanced distribution of long-tailed data presents a considerable challenge for deep learning models, as it causes them to prioritize the accurate classification of head classes but largely disregard tail classes. The biased decision boundary c
Externí odkaz:
http://arxiv.org/abs/2306.06963
The downlink channel state information (CSI) estimation and low overhead acquisition are the major challenges for massive MIMO systems in frequency division duplex to enable high MIMO gain. Recently, numerous studies have been conducted to harness th
Externí odkaz:
http://arxiv.org/abs/2306.06125
Publikováno v:
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 6929-6938
Long-tailed data is still a big challenge for deep neural networks, even though they have achieved great success on balanced data. We observe that vanilla training on long-tailed data with cross-entropy loss makes the instance-rich head classes sever
Externí odkaz:
http://arxiv.org/abs/2305.11733
Deep neural networks frequently suffer from performance degradation when the training data is long-tailed because several majority classes dominate the training, resulting in a biased model. Recent studies have made a great effort in solving this iss
Externí odkaz:
http://arxiv.org/abs/2305.10772
It is not uncommon that real-world data are distributed with a long tail. For such data, the learning of deep neural networks becomes challenging because it is hard to classify tail classes correctly. In the literature, several existing methods have
Externí odkaz:
http://arxiv.org/abs/2305.10648