Related papers: Learning Primitive-aware Discriminative Representa…
In this paper, we are interested in the few-shot learning problem. In particular, we focus on a challenging scenario where the number of categories is large and the number of examples per novel category is very limited, e.g. 1, 2, or 3.…
Training a neural network model that can quickly adapt to a new task is highly desirable yet challenging for few-shot learning problems. Recent few-shot learning methods mostly concentrate on developing various meta-learning strategies from…
Deep convolutional neural networks generally perform well in underwater object recognition tasks on both optical and sonar images. Many such methods require hundreds, if not thousands, of images per class to generalize well to unseen…
Recent few-shot learning works focus on training a model with prior meta-knowledge to fast adapt to new tasks with unseen classes and samples. However, conventional time-series classification algorithms fail to tackle the few-shot scenario.…
Few-shot learning that trains image classifiers over few labeled examples per category is a challenging task. In this paper, we propose to exploit an additional big dataset with different categories to improve the accuracy of few-shot…
Zero-shot learning (ZSL) aims to recognize unseen classes with zero samples by transferring semantic knowledge from seen classes. Current approaches typically correlate global visual features with semantic information (i.e., attributes) or…
Few-shot learning is a challenging problem since only a few examples are provided to recognize a new class. Several recent studies exploit additional semantic information, e.g. text embeddings of class names, to address the issue of rare…
Few-shot learning aims to learn novel categories from very few samples given some base categories with sufficient training samples. The main challenge of this task is the novel categories are prone to dominated by color, texture, shape of…
Few-shot learning (FSL) based on manifold regularization aims to improve the recognition capacity of novel objects with limited training samples by mixing two samples from different categories with a blending factor. However, this mixing…
Recent studies on few-shot classification using transfer learning pose challenges to the effectiveness and efficiency of episodic meta-learning algorithms. Transfer learning approaches are a natural alternative, but they are restricted to…
Few-shot class-incremental learning is to recognize the new classes given few samples and not forget the old classes. It is a challenging task since representation optimization and prototype reorganization can only be achieved under little…
Feature quality is paramount for classification performance, particularly in few-shot scenarios. Contrastive learning, a widely adopted technique for enhancing feature quality, leverages sample relations to extract intrinsic features that…
Self-Explainable Models (SEMs) rely on Prototypical Concept Learning (PCL) to enable their visual recognition processes more interpretable, but they often struggle in data-scarce settings where insufficient training samples lead to…
Transferring learned models to novel tasks is a challenging problem, particularly if only very few labeled examples are available. Although this few-shot learning setup has received a lot of attention recently, most proposed methods focus…
Few-shot learning is a fundamental and challenging problem since it requires recognizing novel categories from only a few examples. The objects for recognition have multiple variants and can locate anywhere in images. Directly comparing…
Few-shot learning aims to train models that can be generalized to novel classes with only a few samples. Recently, a line of works are proposed to enhance few-shot learning with accessible semantic information from class names. However,…
To recognize the unseen classes with only few samples, few-shot learning (FSL) uses prior knowledge learned from the seen classes. A major challenge for FSL is that the distribution of the unseen classes is different from that of those…
Humans are capable of learning a new fine-grained concept with very little supervision, \emph{e.g.}, few exemplary images for a species of bird, yet our best deep learning systems need hundreds or thousands of labeled examples. In this…
Resembling the rapid learning capability of human, few-shot learning empowers vision systems to understand new concepts by training with few samples. Leading approaches derived from meta-learning on images with a single visual object.…
The goal of few-shot learning is to recognize new visual concepts with just a few amount of labeled samples in each class. Recent effective metric-based few-shot approaches employ neural networks to learn a feature similarity comparison…