相关论文: Meta-Learning via Classifier(-free) Diffusion Guid…

Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order to learn how to adapt a base-learner to a new task for which…

Zero-shot Learning (ZSL) is a transfer learning technique which aims at transferring knowledge from seen classes to unseen classes. This knowledge transfer is possible because of underlying semantic space which is common to seen and unseen…

Classifier-free guidance is a key component for enhancing the performance of conditional generative models across diverse tasks. While it has previously demonstrated remarkable improvements for the sample quality, it has only been…

Few-shot learning focuses on learning a new visual concept with very limited labelled examples. A successful approach to tackle this problem is to compare the similarity between examples in a learned metric space based on convolutional…

Diffusion models have shown remarkable performance on many generative tasks. Despite recent success, most diffusion models are restricted in that they only allow linear transformation of the data distribution. In contrast, broader family of…

Despite the remarkable generation capabilities of Diffusion Models (DMs), conducting training and inference remains computationally expensive. Previous works have been devoted to accelerating diffusion sampling, but achieving data-efficient…

Few-shot classification consists of learning a predictive model that is able to effectively adapt to a new class, given only a few annotated samples. To solve this challenging problem, meta-learning has become a popular paradigm that…

Zero shot learning in Image Classification refers to the setting where images from some novel classes are absent in the training data but other information such as natural language descriptions or attribute vectors of the classes are…

We present a domain adaptation based generative framework for zero-shot learning. Our framework addresses the problem of domain shift between the seen and unseen class distributions in zero-shot learning and minimizes the shift by…

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…

Typical diffusion models are trained to accept a particular form of conditioning, most commonly text, and cannot be conditioned on other modalities without retraining. In this work, we propose a universal guidance algorithm that enables…

Meta-learning provides a promising way for learning to efficiently learn and achieves great success in many applications. However, most meta-learning literature focuses on dealing with tasks from a same domain, making it brittle to…

Diffusion models (DMs) can generate realistic images with text guidance using large-scale datasets. However, they demonstrate limited controllability in the output space of the generated images. We propose a novel learning method for…

We develop an approach for text-to-image generation that embraces additional retrieval images, driven by a combination of implicit visual guidance loss and generative objectives. Unlike most existing text-to-image generation methods which…

We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning problems, including classification,…

While developments in machine learning led to impressive performance gains on big data, many human subjects data are, in actuality, small and sparsely labeled. Existing methods applied to such data often do not easily generalize to…

Convolutional neural networks are able to learn realistic image priors from numerous training samples in low-level image generation and restoration. We show that, for high-level image recognition tasks, we can further reconstruct…

Contemporary deep learning techniques have made image recognition a reasonably reliable technology. However training effective photo classifiers typically takes numerous examples which limits image recognition's scalability and…

Recent breakthroughs in text-to-image diffusion models have significantly advanced the generation of high-fidelity, photo-realistic images from textual descriptions. Yet, these models often struggle with interpreting spatial arrangements…

Semantic segmentation is a computer vision task where classification is performed at a pixel level. Due to this, the process of labeling images for semantic segmentation is time-consuming and expensive. To mitigate this cost there has been…