Humans are able to learn to recognize new objects even from a few examples. In contrast,
training deep-learning-based object detectors requires huge amounts of annotated data. To …

Although augmentations (eg, perturbation of graph edges, image crops) boost the efficiency
of Contrastive Learning (CL), feature level augmentation is another plausible …

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 …

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 …

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 …

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 …