Open-vocabulary models are a promising new paradigm for image classification. Unlike
traditional classification models, open-vocabulary models classify among any arbitrary set of …

The rapid development of deep learning provides great convenience for production and life.
However, the massive labels required for training models limits further development. Few …

In this paper, we mainly focus on the problem of how to learn additional feature
representations for few-shot image classification through pretext tasks (eg, rotation or color …

Few-shot learning aims to recognize novel classes from only a few labeled training
examples. Aligning semantically relevant local regions has shown promise in effectively …

Semantic information provides intra-class consistency and inter-class discriminability
beyond visual concepts, which has been employed in Few-Shot Learning (FSL) to achieve …

It is assumed that pre-training provides the feature extractor with strong class transferability
and that high novel class generalization can be achieved by simply reusing the transferable …

Few-shot learning suffers from the scarcity of labeled training data. Regarding local
descriptors of an image as representations for the image could greatly augment existing …

Due to deteriorating environmental conditions and increasing human activity, conservation
efforts directed towards wildlife is crucial. Motion-activated camera traps constitute an …

Few-shot fine-grained image classification (FSFGIC) methods refer to the classification of
images (eg, birds, flowers, and airplanes) belonging to different subclasses of the same …

Learning to generate a task-aware base learner proves a promising direction to deal with
few-shot learning (FSL) problem. Existing methods mainly focus on generating an …