Related papers: Self-Attention with State-Object Weighted Combinat…

Generalized compositional zero-shot learning means to learn composed concepts of attribute-object pairs in a zero-shot fashion, where a model is trained on a set of seen concepts and tested on a combined set of seen and unseen concepts.…

Food recognition has gained significant attention, but the rapid emergence of new dishes requires methods for recognizing unseen food categories, motivating Zero-Shot Food Learning (ZSFL). We propose the task of Compositional Zero-Shot Food…

Humans can easily tell if an attribute (also called state) is realistic, i.e., feasible, for an object, e.g. fire can be hot, but it cannot be wet. In Open-World Compositional Zero-Shot Learning, when all possible state-object combinations…

Recent progress towards learning from limited supervision has encouraged efforts towards designing models that can recognize novel classes at test time (generalized zero-shot learning or GZSL). GZSL approaches assume knowledge of all…

We study the problem of compositional zero-shot learning for object-attribute recognition. Prior works use visual features extracted with a backbone network, pre-trained for object classification and thus do not capture the subtly distinct…

Zero-shot learning, the task of learning to recognize new classes not seen during training, has received considerable attention in the case of 2D image classification. However, despite the increasing ubiquity of 3D sensors, the…

Generalized zero shot learning (GZSL) is defined by a training process containing a set of visual samples from seen classes and a set of semantic samples from seen and unseen classes, while the testing process consists of the classification…

The knowledge encapsulated in a model is the core factor determining its final performance on downstream tasks. Much research in NLP has focused on efficient methods for storing and adapting different types of knowledge, e.g., in dedicated…

Generalised zero-shot learning (GZSL) methods aim to classify previously seen and unseen visual classes by leveraging the semantic information of those classes. In the context of GZSL, semantic information is non-visual data such as a text…

Generative zero-shot learning (ZSL) methods typically synthesize visual features for unseen classes using predefined semantic attributes, followed by training a fully supervised classification model. While effective, these methods require…

Parts represent a basic unit of geometric and semantic similarity across different objects. We argue that part knowledge should be composable beyond the observed object classes. Towards this, we present 3D Compositional Zero-shot Learning…

Zero-shot learning (ZSL) aims to recognize classes that do not have samples in the training set. One representative solution is to directly learn an embedding function associating visual features with corresponding class semantics for…

Open World Compositional Zero-Shot Learning (OW-CZSL) is known to be an extremely challenging task, which aims to recognize unseen compositions formed from seen attributes and objects without any prior assumption of the output space. In…

Learning compositional representation is a key aspect of object-centric learning as it enables flexible systematic generalization and supports complex visual reasoning. However, most of the existing approaches rely on auto-encoding…

Compositional zero-shot learning aims to recognize unseen compositions of seen visual primitives of object classes and their states. While all primitives (states and objects) are observable during training in some combination, their complex…

Compositional Zero-Shot Learning (CZSL) aims to transfer knowledge from seen state-object pairs to novel unseen pairs. In this process, visual bias caused by the diverse interrelationship of state-object combinations blurs their visual…

Quantization is a key technique to reduce network size and computational complexity by representing the network parameters with a lower precision. Traditional quantization methods rely on access to original training data, which is often…

In compositional zero-shot learning, the goal is to recognize unseen compositions (e.g. old dog) of observed visual primitives states (e.g. old, cute) and objects (e.g. car, dog) in the training set. This is challenging because the same…

This paper describes LOCL (Learning Object Attribute Composition using Localization) that generalizes composition zero shot learning to objects in cluttered and more realistic settings. The problem of unseen Object Attribute (OA)…

Zero-shot recognition (ZSR) aims to recognize target-domain data instances of unseen classes based on the models learned from associated pairs of seen-class source and target domain data. One of the key challenges in ZSR is the relative…