Related papers: AdAM: Few-Shot Image Generation via Adaptation-Awa…

Existing few-shot image generation approaches typically employ fusion-based strategies, either on the image or the feature level, to produce new images. However, previous approaches struggle to synthesize high-frequency signals with fine…

The aim of few-shot learning (FSL) is to learn how to recognize image categories from a small number of training examples. A central challenge is that the available training examples are normally insufficient to determine which visual…

Existing few-shot learning (FSL) methods assume that there exist sufficient training samples from source classes for knowledge transfer to target classes with few training samples. However, this assumption is often invalid, especially when…

Cross-domain few-shot segmentation (CD-FSS) aims to segment objects of novel classes in new domains, which is often challenging due to the diverse characteristics of target domains and the limited availability of support data. Most CD-FSS…

Training generative models, such as GANs, on a target domain containing limited examples (e.g., 10) can easily result in overfitting. In this work, we seek to utilize a large source domain for pretraining and transfer the diversity…

Few-shot semantic segmentation (FSS) endeavors to segment unseen classes with only a few labeled samples. Current FSS methods are commonly built on the assumption that their training and application scenarios share similar domains, and…

The success of large language models has inspired the computer vision community to explore image segmentation foundation model that is able to zero/few-shot generalize through prompt engineering. Segment-Anything(SAM), among others, is the…

Few-shot learning problem focuses on recognizing unseen classes given a few labeled images. In recent effort, more attention is paid to fine-grained feature embedding, ignoring the relationship among different distance metrics. In this…

Few-shot learning presents a critical solution for cancer diagnosis in computational pathology (CPath), addressing fundamental limitations in data availability, particularly the scarcity of expert annotations and patient privacy…

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…

Training a generative adversarial network (GAN) with limited data has been a challenging task. A feasible solution is to start with a GAN well-trained on a large scale source domain and adapt it to the target domain with a few samples,…

Few-shot learning (FSL) requires a model to classify new samples after learning from only a few samples. While remarkable results are achieved in existing methods, the performance of embedding and metrics determines the upper limit of…

An old-school recipe for training a classifier is to (i) learn a good feature extractor and (ii) optimize a linear layer atop. When only a handful of samples are available per category, as in Few-Shot Adaptation (FSA), data are insufficient…

To mitigate the detection performance drop caused by domain shift, we aim to develop a novel few-shot adaptation approach that requires only a few target domain images with limited bounding box annotations. To this end, we first observe…

To generate new images for a given category, most deep generative models require abundant training images from this category, which are often too expensive to acquire. To achieve the goal of generation based on only a few images, we propose…

Images generated by most of generative models trained with limited data often exhibit deficiencies in either fidelity, diversity, or both. One effective solution to address the limitation is few-shot generative model adaption. However, the…

The task of Few-shot learning (FSL) aims to transfer the knowledge learned from base categories with sufficient labelled data to novel categories with scarce known information. It is currently an important research question and has great…

Despite excellent progress has been made, the performance of deep learning based algorithms still heavily rely on specific datasets, which are difficult to extend due to labor-intensive labeling. Moreover, because of the advancement of new…

The task of few-shot GAN adaptation aims to adapt a pre-trained GAN model to a small dataset with very few training images. While existing methods perform well when the dataset for pre-training is structurally similar to the target dataset,…

Recent studies have shown remarkable success in image-to-image translation for attribute transfer applications. However, most of existing approaches are based on deep learning and require an abundant amount of labeled data to produce good…