Related papers: Diversity is Definitely Needed: Improving Model-Ag…
The recent wave of large-scale text-to-image diffusion models has dramatically increased our text-based image generation abilities. These models can generate realistic images for a staggering variety of prompts and exhibit impressive…
Recently, zero-shot multi-label classification has garnered considerable attention for its capacity to operate predictions on unseen labels without human annotations. Nevertheless, prevailing approaches often use seen classes as imperfect…
Zero-Shot Classification (ZSC) equips the learned model with the ability to recognize the visual instances from the novel classes via constructing the interactions between the visual and the semantic modalities. In contrast to the…
Zero-Shot learning has been shown to be an efficient strategy for domain adaptation. In this context, this paper builds on the recent work of Bucher et al. [1], which proposed an approach to solve Zero-Shot classification problems (ZSC) by…
Generative Zero-Shot Learning (ZSL) methods synthesize class-related features based on predefined class semantic prototypes, showcasing superior performance. However, this feature generation paradigm falls short of providing interpretable…
Zero-shot learning (ZSL) aims to train a model on seen classes and recognize unseen classes by knowledge transfer through shared auxiliary information. Recent studies reveal that documents from encyclopedias provide helpful auxiliary…
Zero-shot learning (ZSL) aims to transfer knowledge from seen classes to semantically related unseen classes, which are absent during training. The promising strategies for ZSL are to synthesize visual features of unseen classes conditioned…
Training deep generative models usually requires a large amount of data. To alleviate the data collection cost, the task of zero-shot GAN adaptation aims to reuse well-trained generators to synthesize images of an unseen target domain…
This paper addresses the task of learning an image clas-sifier when some categories are defined by semantic descriptions only (e.g. visual attributes) while the others are defined by exemplar images as well. This task is often referred to…
Zero-shot Learning (ZSL) enables classifiers to recognize classes unseen during training, commonly via generative two stage methods: (1) learn visual semantic correlations from seen classes; (2) synthesize unseen class features from…
With the availability of powerful text-to-image diffusion models, recent works have explored the use of synthetic data to improve image classification performances. These works show that it can effectively augment or even replace real data.…
Data augmentation for domain-specific image classification tasks often struggles to simultaneously address diversity, faithfulness, and label clarity of generated data, leading to suboptimal performance in downstream tasks. While existing…
Multi-modal foundation models such as CLIP have showcased impressive zero-shot capabilities. However, their applicability in resource-constrained environments is limited due to their large number of parameters and high inference time. While…
Recently, GAN inversion methods combined with Contrastive Language-Image Pretraining (CLIP) enables zero-shot image manipulation guided by text prompts. However, their applications to diverse real images are still difficult due to the…
Recent advancements in text-to-image generation models have dramatically enhanced the generation of photorealistic images from textual prompts, leading to an increased interest in personalized text-to-image applications, particularly in…
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…
Generating realistic synthetic microscopy images is critical for training deep learning models in label-scarce environments, such as cell counting with many cells per image. However, traditional domain adaptation methods often struggle to…
Cross-modality image segmentation aims to segment the target modalities using a method designed in the source modality. Deep generative models can translate the target modality images into the source modality, thus enabling cross-modality…
Zero-Shot image Anomaly Detection (ZSAD) aims to detect and localise anomalies without access to any normal training samples of the target data. While recent ZSAD approaches leverage additional modalities such as language to generate…
Inspired by strategies like Active Learning, it is intuitive that intelligently selecting the training classes from a dataset for Zero-Shot Learning (ZSL) can improve the performance of existing ZSL methods. In this work, we propose a…