Abstract Machine learning methods strive to acquire a robust model during the training
process that can effectively generalize to test samples, even in the presence of distribution …

Deep learning has achieved remarkable success in numerous domains with help from large
amounts of big data. However, the quality of data labels is a concern because of the lack of …

Large language models (LLMs) have been recently leveraged as training data generators
for various natural language processing (NLP) tasks. While previous research has explored …

Unsupervised person re-identification (re-ID) aims at learning discriminative representations
for person retrieval from unlabeled data. Recent techniques accomplish this task by using …

Bounding box (bbox) regression is a fundamental task in computer vision. So far, the most
commonly used loss functions for bbox regression are the Intersection over Union (IoU) loss …

Self-training is a competitive approach in domain adaptive segmentation, which trains the
network with the pseudo labels on the target domain. However inevitably, the pseudo labels …

We propose a novel framework to perform classification via deep learning in the presence of
noisy annotations. When trained on noisy labels, deep neural networks have been observed …

Abstract Model heterogeneous federated learning is a challenging task since each client
independently designs its own model. Due to the annotation difficulty and free-riding …

Since experiencing domain shifts during test-time is inevitable in practice, test-time adaption
(TTA) continues to adapt the model after deployment. Recently, the area of continual and …

Existing research on learning with noisy labels mainly focuses on synthetic label noise.
Synthetic noise, though has clean structures which greatly enabled statistical analyses, often …