In image classification, it is common practice to train deep networks to extract a single feature vector per input image. Few-shot classification methods also mostly follow this trend …
In graph classification, attention-and pooling-based graph neural networks (GNNs) prevail to extract the critical features from the input graph and support the prediction. They mostly …
Deep neural networks (DNNs) used for brain–computer interface (BCI) classification are commonly expected to learn general features when trained across a variety of contexts, such …
T Lin, Z Yu, H Hu, Y Xu… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Multi-instance learning (MIL) is an effective paradigm for whole-slide pathological images (WSIs) classification to handle the gigapixel resolution and slide-level label. Prevailing MIL …
G Nan, R Qiao, Y Xiao, J Liu, S Leng… - Proceedings of the …, 2021 - openaccess.thecvf.com
Video grounding aims to localize a moment from an untrimmed video for a given textual query. Existing approaches focus more on the alignment of visual and language stimuli with …
Recommender systems usually amplify the biases in the data. The model learned from historical interactions with imbalanced item distribution will amplify the imbalance by over …
J Tan, X Lu, G Zhang, C Yin… - Proceedings of the IEEE …, 2021 - openaccess.thecvf.com
Recently proposed decoupled training methods emerge as a dominant paradigm for long- tailed object detection. But they require an extra fine-tuning stage, and the disjointed …
X Wang, Z Wu, L Lian, SX Yu - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
This work studies the bias issue of pseudo-labeling, a natural phenomenon that widely occurs but often overlooked by prior research. Pseudo-labels are generated when a …
Y Zhang, B Hooi, L Hong… - Advances in Neural …, 2022 - proceedings.neurips.cc
Existing long-tailed recognition methods, aiming to train class-balanced models from long- tailed data, generally assume the models would be evaluated on the uniform test class …