Related papers: Composition-Incremental Learning for Compositional…
The learning objective of vision-language approach of CLIP does not effectively account for the noisy many-to-many correspondences found in web-harvested image captioning datasets, which contributes to its compute and data inefficiency. To…
Compositionality of semantic concepts in image synthesis and analysis is appealing as it can help in decomposing known and generatively recomposing unknown data. For instance, we may learn concepts of changing illumination, geometry or…
Training a referring expression comprehension (ReC) model for a new visual domain requires collecting referring expressions, and potentially corresponding bounding boxes, for images in the domain. While large-scale pre-trained models are…
Compositional Natural Language Inference has been explored to assess the true abilities of neural models to perform NLI. Yet, current evaluations assume models to have full access to all primitive inferences in advance, in contrast to…
Compositional generalization is a crucial property in artificial intelligence, enabling models to handle novel combinations of known components. While most deep learning models lack this capability, certain models succeed in specific tasks,…
This study presents a novel approach to Generative Class Incremental Learning (GCIL) by introducing the forgetting mechanism, aimed at dynamically managing class information for better adaptation to streaming data. GCIL is one of the hot…
The ability to continuously expand knowledge over time and utilize it to rapidly generalize to new tasks is a key feature of human linguistic intelligence. Existing models that pursue rapid generalization to new tasks (e.g., few-shot…
Few-shot image classification consists of two consecutive learning processes: 1) In the meta-learning stage, the model acquires a knowledge base from a set of training classes. 2) During meta-testing, the acquired knowledge is used to…
Recurrent neural networks have recently been used for learning to describe images using natural language. However, it has been observed that these models generalize poorly to scenes that were not observed during training, possibly depending…
Large vision-language models (LVLMs) offer a novel capability for performing in-context learning (ICL) in Visual QA. When prompted with a few demonstrations of image-question-answer triplets, LVLMs have demonstrated the ability to discern…
With the growing interest in pretrained vision-language models like CLIP, recent research has focused on adapting these models to downstream tasks. Despite achieving promising results, most existing methods require labeled data for all…
Compositional actions consist of dynamic (verbs) and static (objects) concepts. Humans can easily recognize unseen compositions using the learned concepts. For machines, solving such a problem requires a model to recognize unseen actions…
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…
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) investigates compositional generalization capacity to recognize unknown state-object pairs based on learned primitive concepts. Existing CZSL methods typically derive primitives features through a…
Many tasks in control, robotics, and planning can be specified using desired goal configurations for various entities in the environment. Learning goal-conditioned policies is a natural paradigm to solve such tasks. However, current…
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…
Few-shot class-incremental learning (FSCIL) aims to design machine learning algorithms that can continually learn new concepts from a few data points, without forgetting knowledge of old classes. The difficulty lies in that limited data…
Complementary recommendations, which aim at providing users product suggestions that are supplementary and compatible with their obtained items, have become a hot topic in both academia and industry in recent years. %However, it is…
Image-text representation learning forms a cornerstone in vision-language models, where pairs of images and textual descriptions are contrastively aligned in a shared embedding space. Since visual and textual concepts are naturally…