相关论文: Evaluating few shot and Contrastive learning Metho…

Few-shot classification is a challenging problem that aims to learn a model that can adapt to unseen classes given a few labeled samples. Recent approaches pre-train a feature extractor, and then fine-tune for episodic meta-learning. Other…

In-Batch contrastive learning is a state-of-the-art self-supervised method that brings semantically-similar instances close while pushing dissimilar instances apart within a mini-batch. Its key to success is the negative sharing strategy,…

Contrastive learning (CL) has shown impressive advances in image representation learning in whichever supervised multi-class classification or unsupervised learning. However, these CL methods fail to be directly adapted to multi-label image…

Few-shot object detection (FSOD) aims to classify and detect few images of novel categories. Existing meta-learning methods insufficiently exploit features between support and query images owing to structural limitations. We propose a…

Unsupervised anomaly detection (UAD) learns one-class classifiers exclusively with normal (i.e., healthy) images to detect any abnormal (i.e., unhealthy) samples that do not conform to the expected normal patterns. UAD has two main…

Reliable detection of anomalies is crucial when deploying machine learning models in practice, but remains challenging due to the lack of labeled data. To tackle this challenge, contrastive learning approaches are becoming increasingly…

Handling out-of-distribution (OOD) samples has become a major stake in the real-world deployment of machine learning systems. This work explores the use of self-supervised contrastive learning to the simultaneous detection of two types of…

Cross-modal attention mechanisms have been widely applied to the image-text matching task and have achieved remarkable improvements thanks to its capability of learning fine-grained relevance across different modalities. However, the…

Few-shot classification requires deep neural networks to learn generalized representations only from limited training images, which is challenging but significant in low-data regimes. Recently, CLIP-based methods have shown promising…

Learning good representations involves capturing the diverse ways in which data samples relate. Contrastive loss - an objective matching related samples - underlies methods from self-supervised to multimodal learning. Contrastive losses,…

Metric learning aims to build a distance metric typically by learning an effective embedding function that maps similar objects into nearby points in its embedding space. Despite recent advances in deep metric learning, it remains…

Few-shot video action recognition is an effective approach to recognizing new categories with only a few labeled examples, thereby reducing the challenges associated with collecting and annotating large-scale video datasets. Existing…

Context: Traditional software security analysis methods struggle to keep pace with the scale and complexity of modern codebases, requiring intelligent automation to detect, assess, and remediate vulnerabilities more efficiently and…

Graph Neural Networks (GNNs) have become popular in Graph Representation Learning (GRL). One fundamental application is few-shot node classification. Most existing methods follow the meta learning paradigm, showing the ability of fast…

Image copy detection (ICD) aims to determine whether a query image is an edited copy of any image from a reference set. Currently, there are very limited public benchmarks for ICD, while all overlook a critical challenge in real-world…

Most previous few-shot learning algorithms are based on meta-training with fake few-shot tasks as training samples, where large labeled base classes are required. The trained model is also limited by the type of tasks. In this paper we…

Humans exhibit a remarkable ability to learn quickly from a limited number of labeled samples, a capability that starkly contrasts with that of current machine learning systems. Unsupervised Few-Shot Learning (U-FSL) seeks to bridge this…

Model checking is a key technique for verifying safety-critical systems against formal specifications, where recent applications of deep learning have shown promise. However, while ubiquitous for vision and language domains, representation…

Contrastive Language-Image Pre-training (CLIP) provides a foundation model by integrating natural language into visual concepts, enabling zero-shot recognition on downstream tasks. It is usually expected that satisfactory overall accuracy…

We study multi-modal few-shot object detection (FSOD) in this paper, using both few-shot visual examples and class semantic information for detection, which are complementary to each other by definition. Most of the previous works on…