Related papers: VICE: Variational Interpretable Concept Embeddings

While personalized text-to-image generation has enabled the learning of a single concept from multiple images, a more practical yet challenging scenario involves learning multiple concepts within a single image. However, existing works…

Variational inference (VI) is a computationally efficient and scalable methodology for approximate Bayesian inference. It strikes a balance between accuracy of uncertainty quantification and practical tractability. It excels at generative…

Conceptual spaces are geometric representations of conceptual knowledge, in which entities correspond to points, natural properties correspond to convex regions, and the dimensions of the space correspond to salient features. While…

Modern deep neural networks remain challenging to interpret due to the opacity of their latent representations, impeding model understanding, debugging, and debiasing. Concept Embedding Models (CEMs) address this by mapping inputs to…

Deep vision models often rely on biases learned from spurious correlations in datasets. To identify these biases, methods that interpret high-level, human-understandable concepts are more effective than those relying primarily on low-level…

Reward and representation learning are two long-standing challenges for learning an expanding set of robot manipulation skills from sensory observations. Given the inherent cost and scarcity of in-domain, task-specific robot data, learning…

The performance of many network learning applications crucially hinges on the success of network embedding algorithms, which aim to encode rich network information into low-dimensional vertex-based vector representations. This paper…

Providing interpretability of deep-learning models to non-experts, while fundamental for a responsible real-world usage, is challenging. Attribution maps from xAI techniques, such as Integrated Gradients, are a typical example of a…

We propose a novel probabilistic model for visual question answering (Visual QA). The key idea is to infer two sets of embeddings: one for the image and the question jointly and the other for the answers. The learning objective is to learn…

Edge detection (ED) is a fundamental perceptual process in computer vision, forming the structural basis for high-level reasoning tasks such as segmentation, recognition, and scene understanding. Despite substantial progress achieved by…

Embedding spaces contain interpretable dimensions indicating gender, formality in style, or even object properties. This has been observed multiple times. Such interpretable dimensions are becoming valuable tools in different areas of…

This work introduces VERSE, a methodology for analyzing and improving Vision-Language Models applied to Visually-rich Document Understanding by exploring their visual embedding space. VERSE enables the visualization of latent…

To study how mental object representations are related to behavior, we estimated sparse, non-negative representations of objects using human behavioral judgments on images representative of 1,854 object categories. These representations…

Word vector embeddings have been shown to contain and amplify biases in data they are extracted from. Consequently, many techniques have been proposed to identify, mitigate, and attenuate these biases in word representations. In this paper,…

People naturally bring their prior beliefs to bear on how they interpret the new information, yet few formal models exist for accounting for the influence of users' prior beliefs in interactions with data presentations like visualizations.…

Scalable and effective exploration remains a key challenge in reinforcement learning (RL). While there are methods with optimality guarantees in the setting of discrete state and action spaces, these methods cannot be applied in…

In this work, we introduce a novel deep learning architecture, Variable Length Embeddings (VLEs), an autoregressive model that can produce a latent representation composed of an arbitrary number of tokens. As a proof of concept, we…

Towards human-level visual understanding, visual commonsense generation has been introduced to generate commonsense inferences beyond images. However, current research on visual commonsense generation has overlooked an important human…

Many modern unsupervised or semi-supervised machine learning algorithms rely on Bayesian probabilistic models. These models are usually intractable and thus require approximate inference. Variational inference (VI) lets us approximate a…

VAEs, or variational autoencoders, are autoencoders that explicitly learn the distribution of the input image space rather than assuming no prior information about the distribution. This allows it to classify similar samples close to each…