Related papers: Task-Level Contrastiveness for Cross-Domain Few-Sh…
Few-shot learning, a challenging task in machine learning, aims to learn a classifier adaptable to recognize new, unseen classes with limited labeled examples. Meta-learning has emerged as a prominent framework for few-shot learning. Its…
Few-shot learning is a challenging problem that has attracted more and more attention recently since abundant training samples are difficult to obtain in practical applications. Meta-learning has been proposed to address this issue, which…
Few-shot semantic segmentation aims to segment novel-class objects in a query image with only a few annotated examples in support images. Most of advanced solutions exploit a metric learning framework that performs segmentation through…
Few-shot classification is a challenging task which aims to formulate the ability of humans to learn concepts from limited prior data and has drawn considerable attention in machine learning. Recent progress in few-shot classification has…
Contrastive learning is a well-established paradigm in representation learning. The standard framework of contrastive learning minimizes the distance between "similar" instances and maximizes the distance between dissimilar ones in the…
Existing meta-learning based few-shot learning (FSL) methods typically adopt an episodic training strategy whereby each episode contains a meta-task. Across episodes, these tasks are sampled randomly and their relationships are ignored. In…
Few-shot segmentation enables the model to recognize unseen classes with few annotated examples. Most existing methods adopt prototype learning architecture, where support prototype vectors are expanded and concatenated with query features…
Meta-learning and other approaches to few-shot learning are widely studied for image recognition, and are increasingly applied to other vision tasks such as pose estimation and dense prediction. This naturally raises the question of whether…
Learning novel classes from a very few labeled samples has attracted increasing attention in machine learning areas. Recent research on either meta-learning based or transfer-learning based paradigm demonstrates that gaining information on…
Multimodal few-shot learning is challenging due to the large domain gap between vision and language modalities. Existing methods are trying to communicate visual concepts as prompts to frozen language models, but rely on hand-engineered…
Many contrastive and meta-learning approaches learn representations by identifying common features in multiple views. However, the formalism for these approaches generally assumes features to be shared across views to be captured…
During the past decade, deep neural networks have led to fast-paced progress and significant achievements in computer vision problems, for both academia and industry. Yet despite their success, state-of-the-art image classification…
Contrastive representation learning has emerged as a promising technique for continual learning as it can learn representations that are robust to catastrophic forgetting and generalize well to unseen future tasks. Previous work in…
Real-world classification tasks are frequently required to work in an open-set setting. This is especially challenging for few-shot learning problems due to the small sample size for each known category, which prevents existing open-set…
Meta-learning algorithms are able to learn a new task using previously learned knowledge, but they often require a large number of meta-training tasks which may not be readily available. To address this issue, we propose a method for…
Multimodal contrastive learning is a methodology for linking different data modalities; the canonical example is linking image and text data. The methodology is typically framed as the identification of a set of encoders, one for each…
The ability to learn new concepts with small amounts of data is a critical aspect of intelligence that has proven challenging for deep learning methods. Meta-learning has emerged as a promising technique for leveraging data from previous…
Contrastive learning is among the most successful methods for visual representation learning, and its performance can be further improved by jointly performing clustering on the learned representations. However, existing methods for joint…
We introduce a novel approach to unsupervised and semi-supervised domain adaptation for semantic segmentation. Unlike many earlier methods that rely on adversarial learning for feature alignment, we leverage contrastive learning to bridge…
Recent self-supervised contrastive methods have been able to produce impressive transferable visual representations by learning to be invariant to different data augmentations. However, these methods implicitly assume a particular set of…