Related papers: Unifying Few- and Zero-Shot Egocentric Action Reco…
Few-shot classification consists of a training phase where a model is learned on a relatively large dataset and an adaptation phase where the learned model is adapted to previously-unseen tasks with limited labeled samples. In this paper,…
Conversational NLU providers often need to scale to thousands of intent-classification models where new customers often face the cold-start problem. Scaling to so many customers puts a constraint on storage space as well. In this paper, we…
First person action recognition is becoming an increasingly researched area thanks to the rising popularity of wearable cameras. This is bringing to light cross-domain issues that are yet to be addressed in this context. Indeed, the…
Vision-language foundation models pretrained on large-scale data provide a powerful tool for many visual understanding tasks. Notably, many vision-language models build two encoders (visual and textual) that can map two modalities into the…
Few-shot classification aims to recognize unlabeled samples from unseen classes given only few labeled samples. The unseen classes and low-data problem make few-shot classification very challenging. Many existing approaches extracted…
Few-shot learning aims to handle previously unseen tasks using only a small amount of new training data. In preparing (or meta-training) a few-shot learner, however, massive labeled data are necessary. In the real world, unfortunately,…
We consider the problem of zero-shot one-class visual classification, extending traditional one-class classification to scenarios where only the label of the target class is available. This method aims to discriminate between positive and…
State-of-the-art audio classification often employs a zero-shot approach, which involves comparing audio embeddings with embeddings from text describing the respective audio class. These embeddings are usually generated by neural networks…
Understanding alignment techniques begins with comprehending zero-shot generalization brought by instruction tuning, but little of the mechanism has been understood. Existing work has largely been confined to the task level, without…
Few-shot learning has recently attracted wide interest in image classification, but almost all the current public benchmarks are focused on natural images. The few-shot paradigm is highly relevant in medical-imaging applications due to the…
Methods for object detection and segmentation rely on large scale instance-level annotations for training, which are difficult and time-consuming to collect. Efforts to alleviate this look at varying degrees and quality of supervision.…
Few-shot segmentation aims to train a segmentation model that can fast adapt to a novel task for which only a few annotated images are provided. Most recent models have adopted a prototype-based paradigm for few-shot inference. These…
Recently few-shot segmentation (FSS) has been extensively developed. Most previous works strive to achieve generalization through the meta-learning framework derived from classification tasks; however, the trained models are biased towards…
Intent classification (IC) and slot filling (SF) are core components in most goal-oriented dialogue systems. Current IC/SF models perform poorly when the number of training examples per class is small. We propose a new few-shot learning…
Few-shot node classification, which aims to predict labels for nodes on graphs with only limited labeled nodes as references, is of great significance in real-world graph mining tasks. Particularly, in this paper, we refer to the task of…
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…
Few-shot segmentation (FSS) aims to segment objects of unseen classes given only a few annotated support images. Most existing methods simply stitch query features with independent support prototypes and segment the query image by feeding…
Current methods for few-shot segmentation (FSSeg) have mainly focused on improving the performance of novel classes while neglecting the performance of base classes. To overcome this limitation, the task of generalized few-shot semantic…
Meta-learning approaches have addressed few-shot problems by finding initialisations suited for fine-tuning to target tasks. Often there are additional properties within training data (which we refer to as context), not relevant to the…
Few-shot classification aims to adapt classifiers to novel classes with a few training samples. However, the insufficiency of training data may cause a biased estimation of feature distribution in a certain class. To alleviate this problem,…