Related papers: Concept Decomposition for Visual Exploration and I…

Integration between biology and information science benefits both fields. Many related models have been proposed, such as computational visual cognition models, computational motor control models, integrations of both and so on. In general,…

Explicit concept space models have proven efficacy for text representation in many natural language and text mining applications. The idea is to embed textual structures into a semantic space of concepts which captures the main ideas,…

Neural network based models are a very powerful tool for creating word embeddings, the objective of these models is to group similar words together. These embeddings have been used as features to improve results in various applications such…

One major deficiency of most semantic representation techniques is that they usually model a word type as a single point in the semantic space, hence conflating all the meanings that the word can have. Addressing this issue by learning…

Existing fine-grained hashing methods typically lack code interpretability as they compute hash code bits holistically using both global and local features. To address this limitation, we propose ConceptHash, a novel method that achieves…

Distributed word vector spaces are considered hard to interpret which hinders the understanding of natural language processing (NLP) models. In this work, we introduce a new method to interpret arbitrary samples from a word vector space. To…

Word embeddings are a popular way to improve downstream performances in contemporary language modeling. However, the underlying geometric structure of the embedding space is not well understood. We present a series of explorations using…

We address the key question of how object part representations can be found from the internal states of CNNs that are trained for high-level tasks, such as object classification. This work provides a new unsupervised method to learn…

Dense captioning is a newly emerging computer vision topic for understanding images with dense language descriptions. The goal is to densely detect visual concepts (e.g., objects, object parts, and interactions between them) from images,…

Concept-based interpretability methods offer a lens into the internals of foundation models by decomposing their embeddings into high-level concepts. These concept representations are most useful when they are compositional, meaning that…

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Bisociative knowledge discovery is an approach that combines elements from two or more "incompatible" domains to generate creative solutions and insight. Inspired by Koestler's notion of bisociation, in this paper we propose a computational…

Text-to-image diffusion models have made significant advancements in generating high-quality, diverse images from text prompts. However, the inherent limitations of textual signals often prevent these models from fully capturing specific…

Exploring and understanding efficient image representations is a long-standing challenge in computer vision. While deep learning has achieved remarkable progress across image understanding tasks, its internal representations are often…

Finding an unsupervised decomposition of an image into individual objects is a key step to leverage compositionality and to perform symbolic reasoning. Traditionally, this problem is solved using amortized inference, which does not…

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…

We propose a novel approach to improve a visual-semantic embedding model by incorporating concept representations captured from an external structured knowledge base. We investigate its performance on image classification under both…

Empirical evidence shows that deep vision networks often represent concepts as directions in latent space with concept information written along directional components in the vector representation of the input. However, the mechanism to…

We are interested in aligning how people think about objects and what machines perceive, meaning by this the fact that object recognition, as performed by a machine, should follow a process which resembles that followed by humans when…

It is very attractive to formulate vision in terms of pattern theory \cite{Mumford2010pattern}, where patterns are defined hierarchically by compositions of elementary building blocks. But applying pattern theory to real world images is…