Related papers: Few-shot Novel Category Discovery

In this thesis, we develop theoretical, algorithmic and experimental contributions for Machine Learning with limited labels, and more specifically for the tasks of Image Classification and Object Detection in Computer Vision. In a first…

Different from the traditional semi-supervised learning paradigm that is constrained by the close-world assumption, Generalized Category Discovery (GCD) presumes that the unlabeled dataset contains new categories not appearing in the…

Generalized Category Discovery is a significant and complex task that aims to identify both known and undefined novel categories from a set of unlabeled data, leveraging another labeled dataset containing only known categories. The primary…

Clustering using neural networks has recently demonstrated promising performance in machine learning and computer vision applications. However, the performance of current approaches is limited either by unsupervised learning or their…

Few-shot image classification has emerged as a key challenge in the field of computer vision, highlighting the capability to rapidly adapt to new tasks with minimal labeled data. Existing methods predominantly rely on image-level features…

Few-shot learning aims at rapidly adapting to novel categories with only a handful of samples at test time, which has been predominantly tackled with the idea of meta-learning. However, meta-learning approaches essentially learn across a…

This paper addresses the problem of Rehearsal-Free Continual Category Discovery (RF-CCD), which focuses on continuously identifying novel class by leveraging knowledge from labeled data. Existing methods typically train from scratch,…

Domain adaptation for semantic segmentation across datasets consisting of the same categories has seen several recent successes. However, a more general scenario is when the source and target datasets correspond to non-overlapping label…

Conventional methods for object detection usually require substantial amounts of training data and annotated bounding boxes. If there are only a few training data and annotations, the object detectors easily overfit and fail to generalize.…

We propose a few-shot learning method for unsupervised feature selection, which is a task to select a subset of relevant features in unlabeled data. Existing methods usually require many instances for feature selection. However, sufficient…

New intent discovery is of great value to natural language processing, allowing for a better understanding of user needs and providing friendly services. However, most existing methods struggle to capture the complicated semantics of…

Few-shot learning aims to learn to generalize a classifier to novel classes with limited labeled data. Transductive inference that utilizes unlabeled test set to deal with low-data problem has been employed for few-shot learning in recent…

Humans are capable of learning new concepts from small numbers of examples. In contrast, supervised deep learning models usually lack the ability to extract reliable predictive rules from limited data scenarios when attempting to classify…

Even with the luxury of having abundant data, multi-label classification is widely known to be a challenging task to address. This work targets the problem of multi-label meta-learning, where a model learns to predict multiple labels within…

Meta-learning has emerged as a powerful training strategy for few-shot node classification, demonstrating its effectiveness in the transductive setting. However, the existing literature predominantly focuses on transductive few-shot node…

There has been a remarkable progress in learning a model which could recognise novel classes with only a few labeled examples in the last few years. Few-shot learning (FSL) for action recognition is a challenging task of recognising novel…

Few-shot object detection (FSOD) aims to detect objects using only a few examples. How to adapt state-of-the-art object detectors to the few-shot domain remains challenging. Object proposal is a key ingredient in modern object detectors.…

In this paper, we propose a deep invertible hybrid model which integrates discriminative and generative learning at a latent space level for semi-supervised few-shot classification. Various tasks for classifying new species from image data…

We introduce a new setting of Novel Class Discovery in Semantic Segmentation (NCDSS), which aims at segmenting unlabeled images containing new classes given prior knowledge from a labeled set of disjoint classes. In contrast to existing…

Existing object detectors often struggle to generalize across domains while adapting to emerging novel categories. Adaptive open-set object detection (AOOD) addresses this challenge by training on base categories in the source domain and…