相关论文: What the Weight?! A Unified Framework for Zero-Sho…

We present a novel method for jointly learning compositional and non-compositional phrase embeddings by adaptively weighting both types of embeddings using a compositionality scoring function. The scoring function is used to quantify the…

Humans are capable of abstracting various tasks as different combinations of multiple attributes. This perspective of compositionality is vital for human rapid learning and adaption since previous experiences from related tasks can be…

Systematic generalization refers to the capacity to understand and generate novel combinations from known components. Despite recent progress by large language models (LLMs) across various domains, these models often fail to extend their…

Vision and language models (VLMs) such as CLIP have showcased remarkable zero-shot recognition abilities yet face challenges in visio-linguistic compositionality, particularly in linguistic comprehension and fine-grained image-text…

Machine Unlearning is an emerging paradigm for selectively removing the impact of training datapoints from a network. Unlike existing methods that target a limited subset or a single class, our framework unlearns all classes in a single…

In this work we study locality and compositionality in the context of learning representations for Zero Shot Learning (ZSL). In order to well-isolate the importance of these properties in learned representations, we impose the additional…

This paper studies the problem of Generalized Zero-shot Learning (G-ZSL), whose goal is to classify instances belonging to both seen and unseen classes at the test time. We propose a novel space decomposition method to solve G-ZSL. Some…

Hybrid ensemble, an essential branch of ensembles, has flourished in the regression field, with studies confirming diversity's importance. However, previous ensembles consider diversity in the sub-model training stage, with limited…

Learning compact and interpretable representations is a very natural task, which has not been solved satisfactorily even for simple binary datasets. In this paper, we review various ways of composing experts for binary data and argue that…

In recent years, large language models (LLMs) have achieved strong performance on benchmark tasks, especially in zero or few-shot settings. However, these benchmarks often do not adequately address the challenges posed in the real-world,…

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…

Compositional Zero-Shot Learning (CZSL) aims to recognize unseen combinations of seen attributes and objects. Current CLIP-based methods in CZSL, despite their advancements, often fail to effectively understand and link the attributes and…

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…

We introduce compositional soft prompting (CSP), a parameter-efficient learning technique to improve the zero-shot compositionality of large-scale pretrained vision-language models (VLMs) like CLIP. We develop CSP for compositional…

We present a new approach and a novel architecture, termed WSNet, for learning compact and efficient deep neural networks. Existing approaches conventionally learn full model parameters independently and then compress them via ad hoc…

Recent developments in pre-trained neural language modeling have led to leaps in accuracy on commonsense question-answering benchmarks. However, there is increasing concern that models overfit to specific tasks, without learning to utilize…

This paper proposes a novel model for recognizing images with composite attribute-object concepts, notably for composite concepts that are unseen during model training. We aim to explore the three key properties required by the task ---…

Compositional Zero-Shot Learning (CZSL) is a critical task in computer vision that enables models to recognize unseen combinations of known attributes and objects during inference, addressing the combinatorial challenge of requiring…

Understanding why a model makes a certain prediction can be as crucial as the prediction's accuracy in many applications. However, the highest accuracy for large modern datasets is often achieved by complex models that even experts struggle…

Fine-tuning large pre-trained language models on downstream tasks has become the de-facto learning paradigm in NLP. However, conventional approaches fine-tune all the parameters of the pre-trained model, which becomes prohibitive as the…