Although augmentations (eg, perturbation of graph edges, image crops) boost the efficiency of Contrastive Learning (CL), feature level augmentation is another plausible …
L Wang, P Koniusz - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
Many skeletal action recognition models use GCNs to represent the human body by 3D body joints connected body parts. GCNs aggregate one-or few-hop graph neighbourhoods …
H Zhu, P Koniusz - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
Few-shot learning (FSL) is popular due to its ability to adapt to novel classes. Compared with inductive few-shot learning, transductive models typically perform better as they …
S Lin, K Wang, X Zeng, R Zhao - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Few-shot object detection (FSOD) aims to expand an object detector for novel categories given only a few instances for training. The few training samples restrict the performance of …
In the field of visual scene understanding, deep neural networks have made impressive advancements in various core tasks like segmentation, tracking, and detection. However …
D Kang, P Koniusz, M Cho… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
We address the task of weakly-supervised few-shot image classification and segmentation, by leveraging a Vision Transformer (ViT) pretrained with self-supervision. Our proposed …
Visual representation based on covariance matrix has demonstrates its efficacy for image classification by characterising the pairwise correlation of different channels in convolutional …
Few-shot object detection, the problem of modelling novel object detection categories with few training instances, is an emerging topic in the area of few-shot learning and object …
In this paper, we tackle the challenging problem of Few-shot Object Detection. Existing FSOD pipelines (i) use average-pooled representations that result in information loss; and/or …