S Li, X Xia, S Ge, T Liu - … of the IEEE/CVF conference on …, 2022 - openaccess.thecvf.com
Deep networks have strong capacities of embedding data into latent representations and finishing following tasks. However, the capacities largely come from high-quality annotated …
The memorization effect of deep neural network (DNN) plays a pivotal role in many state-of- the-art label-noise learning methods. To exploit this property, the early stopping trick, which …
S Liu, Z Zhu, Q Qu, C You - International Conference on …, 2022 - proceedings.mlr.press
Recently, over-parameterized deep networks, with increasingly more network parameters than training samples, have dominated the performances of modern machine learning …
In label-noise learning, the noise transition matrix, bridging the class posterior for noisy and clean data, has been widely exploited to learn statistically consistent classifiers. The …
In this work, we study hallucinations in Neural Machine Translation (NMT), which lie at an extreme end on the spectrum of NMT pathologies. Firstly, we connect the phenomenon of …
Z Huang, G Niu, X Liu, W Ding… - Advances in Neural …, 2021 - proceedings.neurips.cc
Cross-modal matching, which aims to establish the correspondence between two different modalities, is fundamental to a variety of tasks such as cross-modal retrieval and vision-and …
S Rong, B Tu, Z Wang, J Li - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
The existing weakly supervised semantic segmentation (WSSS) methods pay much attention to generating accurate and complete class activation maps (CAMs) as pseudo …
F Wang, Z Han, Y Gong, Y Yin - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Source-free domain adaptation (SFDA) newly emerges to transfer the relevant knowledge of a well-trained source model to an unlabeled target domain, which is critical in various …
The sample selection approach is popular in learning with noisy labels. The state-of-the-art methods train two deep networks simultaneously for sample selection, which aims to employ …