Related papers: Focus-Consistent Multi-Level Aggregation for Compo…

Federated learning is an effective way of extracting insights from different user devices while preserving the privacy of users. However, new classes with completely unseen data distributions can stream across any device in a federated…

Compositional Zero-Shot Learning (CZSL) aims to recognize novel concepts formed by known states and objects during training. Existing methods either learn the combined state-object representation, challenging the generalization of unseen…

Compositional Zero-Shot Learning (CZSL) aims to recognize unseen state-object combinations by leveraging known combinations. Existing studies basically rely on the cross-modal alignment capabilities of CLIP but tend to overlook its…

Few-shot segmentation (FSS) aims to segment objects of unseen classes given only a few annotated support images. Most existing methods simply stitch query features with independent support prototypes and segment the query image by feeding…

Zero-shot classification of image scenes which can recognize the image scenes that are not seen in the training stage holds great promise of lowering the dependence on large numbers of labeled samples. To address the zero-shot image scene…

Zero-shot learning (ZSL) has been shown to be a promising approach to generalizing a model to categories unseen during training by leveraging class attributes, but challenges still remain. Recently, methods using generative models to combat…

The Few-Shot Segmentation (FSS) aims to accomplish the novel class segmentation task with a few annotated images. Current FSS research based on meta-learning focus on designing a complex interaction mechanism between the query and support…

Zero-shot learning (ZSL) extends the conventional image classification technique to a more challenging situation where the test image categories are not seen in the training samples. Most studies on ZSL utilize side information such as…

Foundation models have attracted widespread attention across domains due to their powerful zero-shot classification capabilities. This work is motivated by two key observations: (1) \textit{Vision-Language Models} (VLMs), such as CLIP,…

Low-Rank Adaptation (LoRA) has emerged as a widely adopted technique in text-to-image models, enabling precise rendering of multiple distinct elements, such as characters and styles, in multi-concept image generation. However, current…

Recently, few-shot learning (FSL) has become a popular task that aims to recognize new classes from only a few labeled examples and has been widely applied in fields such as natural science, remote sensing, and medical images. However, most…

Zero-shot learning (ZSL) aims at recognizing unseen classes with knowledge transferred from seen classes. This is typically achieved by exploiting a semantic feature space (FS) shared by both seen and unseen classes, i.e., attributes or…

Aligning features from different modalities, is one of the most fundamental challenges for cross-modal tasks. Although pre-trained vision-language models can achieve a general alignment between image and text, they often require…

Real-world applications of machine learning models often confront data distribution shifts, wherein discrepancies exist between the training and test data distributions. In the common multi-domain multi-class setup, as the number of classes…

Object Referring Analysis (ORA), commonly known as referring expression comprehension, requires the identification and localization of specific objects in an image based on natural descriptions. Unlike generic object detection, ORA requires…

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…

We consider the problem of referring image segmentation. Given an input image and a natural language expression, the goal is to segment the object referred by the language expression in the image. Existing works in this area treat the…

Recent methods for long-tailed instance segmentation still struggle on rare object classes with few training data. We propose a simple yet effective method, Feature Augmentation and Sampling Adaptation (FASA), that addresses the data…

Compositional Zero-Shot Learning (CZSL) aims to learn semantic primitives (attributes and objects) from seen compositions and recognize unseen attribute-object compositions. Existing CZSL datasets focus on single attributes, neglecting the…

Most methods tackle zero-shot video classification by aligning visual-semantic representations within seen classes, which limits generalization to unseen classes. To enhance model generalizability, this paper presents an end-to-end…