Related papers: Hyperbolic Image-Text Representations
Image clustering, which involves grouping images into different clusters without labels, is a key task in unsupervised learning. Although previous deep clustering methods have achieved remarkable results, they only explore the intrinsic…
Representation learning is a key element of state-of-the-art deep learning approaches. It enables to transform raw data into structured vector space embeddings. Such embeddings are able to capture the distributional semantics of their…
Humans have an incredible ability to process and understand information from multiple sources such as images, video, text, and speech. Recent success of deep neural networks has enabled us to develop algorithms which give machines the…
Despite the abundance of multi-modal data, such as image-text pairs, there has been little effort in understanding the individual entities and their different roles in the construction of these data instances. In this work, we endeavour to…
Image-Text Retrieval (ITR) is challenging in bridging visual and lingual modalities. Contrastive learning has been adopted by most prior arts. Except for limited amount of negative image-text pairs, the capability of constrastive learning…
Document images are a ubiquitous source of data where the text is organized in a complex hierarchical structure ranging from fine granularity (e.g., words), medium granularity (e.g., regions such as paragraphs or figures), to coarse…
The linear representation hypothesis is the informal idea that semantic concepts are encoded as linear directions in the representation spaces of large language models (LLMs). Previous work has shown how to make this notion precise for…
Representing the semantics of words is a long-standing problem for the natural language processing community. Most methods compute word semantics given their textual context in large corpora. More recently, researchers attempted to…
Multi-step reasoning remains a central challenge for large language models: single-pass generation is efficient but lacks accuracy; tree-search methods explore multiple paths but are computation-heavy. We address this gap by distilling…
Various neuroimaging studies suffer from small sample size problem which often limit their reliability. Meta-analysis addresses this challenge by aggregating findings from different studies to identify consistent patterns of brain activity.…
Contrastive Language-Image Pre-training (CLIP) has been a celebrated method for training vision encoders to generate image/text representations facilitating various applications. Recently, CLIP has been widely adopted as the vision backbone…
Learning fine-grained embeddings from coarse labels is a challenging task due to limited label granularity supervision, i.e., lacking the detailed distinctions required for fine-grained tasks. The task becomes even more demanding when…
Two modalities are often used to convey information in a complementary and beneficial manner, e.g., in online news, videos, educational resources, or scientific publications. The automatic understanding of semantic correlations between text…
CLIP achieves strong zero-shot image-text retrieval by aligning global vision and text representations, yet it falls behind on fine-grained tasks even when fine-tuned on long, detailed captions. In this work, we propose $\beta$-CLIP, a…
Latent diffusion models such as Stable Diffusion achieve state-of-the-art results on text-to-image generation tasks. However, the extent to which these models have a semantic understanding of the images they generate is not well understood.…
Supervision for metric learning has long been given in the form of equivalence between human-labeled classes. Although this type of supervision has been a basis of metric learning for decades, we argue that it hinders further advances in…
Temporal knowledge graph (TKG) reasoning predicts future events based on historical data, but it's challenging due to the complex semantic and hierarchical information involved. Existing Euclidean models excel at capturing semantics but…
Neural embeddings have been used with great success in Natural Language Processing (NLP). They provide compact representations that encapsulate word similarity and attain state-of-the-art performance in a range of linguistic tasks. The…
Models for image representation learning are typically designed for either recognition or generation. Various forms of contrastive learning help models learn to convert images to embeddings that are useful for classification, detection, and…
Contrastive Language-Image Pre-Training (CLIP) is highly instrumental in machine learning applications within a large variety of domains. We investigate the geometry of this embedding, which is still not well understood. We examine the raw…