相关论文: Composition-Incremental Learning for Compositional…

Few-shot class-incremental learning (FSCIL) is proposed to continually learn from novel classes with only a few samples after the (pre-)training on base classes with sufficient data. However, this remains a challenge. In contrast, humans…

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),…

People easily recognize new visual categories that are new combinations of known components. This compositional generalization capacity is critical for learning in real-world domains like vision and language because the long tail of new…

Compositional zero-shot learning (CZSL) refers to recognizing unseen compositions of known visual primitives, which is an essential ability for artificial intelligence systems to learn and understand the world. While considerable progress…

We tackle continual adaptation of vision-language models to new attributes, objects, and their compositions in Compositional Zero-Shot Learning (CZSL), while preventing forgetting of prior knowledge. Unlike classical continual learning…

Compositional Zero-Shot learning (CZSL) requires to recognize state-object compositions unseen during training. In this work, instead of assuming prior knowledge about the unseen compositions, we operate in the open world setting, where the…

Despite the rising prevalence of neural language models, recent empirical evidence suggests their deficiency in compositional generalization. One of the current de-facto solutions to this problem is compositional data augmentation, which…

Compositional Zero-Shot Learning (CZSL) aims to recognize novel compositions using knowledge learned from seen attribute-object compositions in the training set. Previous works mainly project an image and a composition into a common…

Most incremental learners excessively prioritize coarse classes of objects while neglecting various kinds of states (e.g. color and material) attached to the objects. As a result, they are limited in the ability to reason fine-grained…

Contrastive Language-Image Pretraining (CLIP) has demonstrated great zero-shot performance for matching images and text. However, it is still challenging to adapt vision-lanaguage pretrained models like CLIP to compositional image and text…

This work explores the zero-shot compositional learning ability of large pre-trained vision-language models(VLMs) within the prompt-based learning framework and propose a model (\textit{PromptCompVL}) to solve the compositonal zero-shot…

Compositional Zero-Shot learning (CZSL) aims to recognize unseen compositions of state and object visual primitives seen during training. A problem with standard CZSL is the assumption of knowing which unseen compositions will be available…

Open-World Compositional Zero-Shot Learning (OW-CZSL) addresses the challenge of recognizing novel compositions of known primitives and entities. Even though prior works utilize language knowledge for recognition, such approaches exhibit…

Compositional Zero-Shot Learning (CZSL) aims to recognize unseen attribute-object compositions by learning prior knowledge of seen primitives, \textit{i.e.}, attributes and objects. Learning generalizable compositional representations in…

In this paper, we study the problem of Compositional Zero-Shot Learning (CZSL), which is to recognize novel attribute-object combinations with pre-existing concepts. Recent researchers focus on applying large-scale Vision-Language…

Compositional zero-shot learning (CZSL) aims to recognize unseen attribute-object compositions by recombining primitives learned from seen pairs. Recent CZSL methods built on vision-language models (VLMs) typically adopt parameter-efficient…

Generic unstructured neural networks have been shown to struggle on out-of-distribution compositional generalization. Compositional data augmentation via example recombination has transferred some prior knowledge about compositionality to…

Compositional generalization is a basic and essential intellective capability of human beings, which allows us to recombine known parts readily. However, existing neural network based models have been proven to be extremely deficient in…

Continual learning aims at incrementally acquiring new knowledge while not forgetting existing knowledge. To overcome catastrophic forgetting, methods are either rehearsal-based, i.e., store data examples from previous tasks for data…

Pre-trained vision-language models (VLMs) have achieved promising success in many fields, especially with prompt learning paradigm. In this work, we propose GIP-COL (Graph-Injected Soft Prompting for COmpositional Learning) to better…