Related papers: Semantic Softmax Loss for Zero-Shot Learning
Few-shot learning is a fundamental and challenging problem since it requires recognizing novel categories from only a few examples. The objects for recognition have multiple variants and can locate anywhere in images. Directly comparing…
Zero-shot learning (ZSL) endeavors to transfer knowledge from seen categories to recognize unseen categories, which mostly relies on the semantic-visual interactions between image and attribute tokens. Recently, prompt learning has emerged…
Given semantic descriptions of object classes, zero-shot learning aims to accurately recognize objects of the unseen classes, from which no examples are available at the training stage, by associating them to the seen classes, from which…
Generative zero-shot learning (ZSL) synthesizes features for unseen classes, leveraging semantic conditions to transfer knowledge from seen classes. However, it also introduces two intrinsic challenges: (1) class-level attributes fails to…
Zero-shot learning (ZSL) aims to transfer knowledge from seen classes to unseen ones so that the latter can be recognised without any training samples. This is made possible by learning a projection function between a feature space and a…
We propose a novel framework called Semantics-Preserving Adversarial Embedding Network (SP-AEN) for zero-shot visual recognition (ZSL), where test images and their classes are both unseen during training. SP-AEN aims to tackle the inherent…
Zero-shot learning (ZSL) aims to recognize unseen classes by exploiting semantic descriptions shared between seen classes and unseen classes. Current methods show that it is effective to learn visual-semantic alignment by projecting…
Conventional centralised deep learning paradigms are not feasible when data from different sources cannot be shared due to data privacy or transmission limitation. To resolve this problem, federated learning has been introduced to transfer…
This paper investigates a challenging problem of zero-shot learning in the multi-label scenario (MLZSL), wherein, the model is trained to recognize multiple unseen classes within a sample (e.g., an image) based on seen classes and auxiliary…
Recent zero-shot learning (ZSL) approaches have integrated fine-grained analysis, i.e., fine-grained ZSL, to mitigate the commonly known seen/unseen domain bias and misaligned visual-semantics mapping problems, and have made profound…
This work is a systematical analysis on the so-called hard class problem in zero-shot learning (ZSL), that is, some unseen classes disproportionally affect the ZSL performances than others, as well as how to remedy the problem by detecting…
Compositional Zero-Shot Learning (CZSL) aims to recognize novel attribute-object compositions by leveraging knowledge from seen compositions. Current methods align textual prototypes with visual features via Vision-Language Models (VLMs),…
The key of zero-shot learning (ZSL) is how to find the information transfer model for bridging the gap between images and semantic information (texts or attributes). Existing ZSL methods usually construct the compatibility function between…
Zero-shot multi-label recognition (MLR) with Vision-Language Models (VLMs) faces significant challenges without training data, model tuning, or architectural modifications. Existing approaches require prompt tuning or architectural…
Zero-shot learning (ZSL) tackles the novel class recognition problem by transferring semantic knowledge from seen classes to unseen ones. Existing attention-based models have struggled to learn inferior region features in a single image by…
While there has been a number of studies on Zero-Shot Learning (ZSL) for 2D images, its application to 3D data is still recent and scarce, with just a few methods limited to classification. We present the first generative approach for both…
This paper introduces a novel framework for zero-shot learning (ZSL), i.e., to recognize new categories that are unseen during training, by using a multi-model and multi-alignment integration method. Specifically, we propose three…
We introduce the isoperimetric loss as a regularization criterion for learning the map from a visual representation to a semantic embedding, to be used to transfer knowledge to unknown classes in a zero-shot learning setting. We use a…
Zero-shot learning uses semantic attributes to connect the search space of unseen objects. In recent years, although the deep convolutional network brings powerful visual modeling capabilities to the ZSL task, its visual features have…
Zero-shot learning (ZSL) aims to discriminate images from unseen classes by exploiting relations to seen classes via their attribute-based descriptions. Since attributes are often related to specific parts of objects, many recent works…