相关论文: Adaptive Parametric Prototype Learning for Cross-D…

The advances in deep learning have enabled machine learning methods to outperform human beings in various areas, but it remains a great challenge for a well-trained model to quickly adapt to a new task. One promising solution to realize…

The significant amount of training data required for training Convolutional Neural Networks has become a bottleneck for applications like semantic segmentation. Few-shot semantic segmentation algorithms address this problem, with an aim to…

The goal of few-shot learning is to classify unseen categories with few labeled samples. Recently, the low-level information metric-learning based methods have achieved satisfying performance, since local representations (LRs) are more…

Viewpoint estimation for known categories of objects has been improved significantly thanks to deep networks and large datasets, but generalization to unknown categories is still very challenging. With an aim towards improving performance…

Few-shot object detection (FSOD) has thrived in recent years to learn novel object classes with limited data by transferring knowledge gained on abundant base classes. FSOD approaches commonly assume that both the scarcely provided examples…

Unsupervised domain adaption (UDA) aims to adapt models learned from a well-annotated source domain to a target domain, where only unlabeled samples are given. Current UDA approaches learn domain-invariant features by aligning source and…

Current few-shot learning models capture visual object relations in the so-called meta-learning setting under a fixed-resolution input. However, such models have a limited generalization ability under the scale and location mismatch between…

In this paper, we explore contrastive learning for few-shot classification, in which we propose to use it as an additional auxiliary training objective acting as a data-dependent regularizer to promote more general and transferable…

Relation classification (RC) task is one of fundamental tasks of information extraction, aiming to detect the relation information between entity pairs in unstructured natural language text and generate structured data in the form of…

Fine-tuning a deep network trained with the standard cross-entropy loss is a strong baseline for few-shot learning. When fine-tuned transductively, this outperforms the current state-of-the-art on standard datasets such as Mini-ImageNet,…

Learning to classify new categories based on just one or a few examples is a long-standing challenge in modern computer vision. In this work, we proposes a simple yet effective method for few-shot (and one-shot) object recognition. Our…

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,…

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 leverage all samples of the query set. The two existing classes…

Few-shot recognition aims to recognize novel categories under low-data regimes. Some recent few-shot recognition methods introduce auxiliary semantic modality, i.e., category attribute information, into representation learning, which…

When training data is scarce, it is common to make use of a feature extractor that has been pre-trained on a large base dataset, either by fine-tuning its parameters on the ``target'' dataset or by directly adopting its representation as…

Transfer learning has been widely adopted for few-shot classification. Recent studies reveal that obtaining good generalization representation of images on novel classes is the key to improving the few-shot classification accuracy. To…

The recent CLIP-based methods have shown promising zero-shot and few-shot performance on image classification tasks. Existing approaches such as CoOp and Tip-Adapter only focus on high-level visual features that are fully aligned with…

The contrastive vision-language pre-training, known as CLIP, demonstrates remarkable potential in perceiving open-world visual concepts, enabling effective zero-shot image recognition. Nevertheless, few-shot learning methods based on CLIP…

The prototypical network is a prototype classifier based on meta-learning and is widely used for few-shot learning because it classifies unseen examples by constructing class-specific prototypes without adjusting hyper-parameters during…

Standard few-shot benchmarks are often built upon simplifying assumptions on the query sets, which may not always hold in practice. In particular, for each task at testing time, the classes effectively present in the unlabeled query set are…