相关论文: Prototype Generation: Robust Feature Visualisation…

Different users find different images generated for the same prompt desirable. This gives rise to personalized image generation which involves creating images aligned with an individual's visual preference. Current generative models are,…

Making neural visual generative models controllable by logical reasoning systems is promising for improving faithfulness, transparency, and generalizability. We propose the Abductive visual Generation (AbdGen) approach to build such…

We demonstrate in this paper that a generative model can be designed to perform classification tasks under challenging settings, including adversarial attacks and input distribution shifts. Specifically, we propose a conditional variational…

Disentangled representations can be useful in many downstream tasks, help to make deep learning models more interpretable, and allow for control over features of synthetically generated images that can be useful in training other models…

Concept-based machine learning methods have increasingly gained importance due to the growing interest in making neural networks interpretable. However, concept annotations are generally challenging to obtain, making it crucial to leverage…

Autonomous systems face the intricate challenge of navigating unpredictable environments and interacting with external objects. The successful integration of robotic agents into real-world situations hinges on their perception capabilities,…

The convolutional neural networks (CNNs) have proven to be a powerful tool for discriminative learning. Recently researchers have also started to show interest in the generative aspects of CNNs in order to gain a deeper understanding of…

Perception is essential for the active interaction of physical agents with the external environment. The integration of multiple sensory modalities, such as touch and vision, enhances this perceptual process, creating a more comprehensive…

Modern vision models excel at general purpose downstream tasks. It is unclear, however, how they may be used for personalized vision tasks, which are both fine-grained and data-scarce. Recent works have successfully applied synthetic data…

There is a growing concern about typically opaque decision-making with high-performance machine learning algorithms. Providing an explanation of the reasoning process in domain-specific terms can be crucial for adoption in risk-sensitive…

We introduce the Unity Perception package which aims to simplify and accelerate the process of generating synthetic datasets for computer vision tasks by offering an easy-to-use and highly customizable toolset. This open-source package…

High-fidelity generative models are increasingly needed in privacy-sensitive scenarios, where access to data is severely restricted due to regulatory and copyright constraints. This scarcity hampers model development--ironically, in…

We propose a fast, model agnostic method for finding interpretable counterfactual explanations of classifier predictions by using class prototypes. We show that class prototypes, obtained using either an encoder or through class specific…

Automated rationale generation is an approach for real-time explanation generation whereby a computational model learns to translate an autonomous agent's internal state and action data representations into natural language. Training on…

Generative Adversarial Networks (GANs) advance face synthesis through learning the underlying distribution of observed data. Despite the high-quality generated faces, some minority groups can be rarely generated from the trained models due…

The accelerating advancement of generative models has introduced new challenges for detecting AI-generated images, especially in real-world scenarios where novel generation techniques emerge rapidly. Existing learning paradigms are likely…

We introduce UniToken, an auto-regressive generation model that encodes visual inputs through a combination of discrete and continuous representations, enabling seamless integration of unified visual understanding and image generation…

AI models have shown promise in many medical imaging tasks. However, our ability to explain what signals these models have learned is severely lacking. Explanations are needed in order to increase the trust in AI-based models, and could…

Deep generative models, such as Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs), have been employed widely in computational creativity research. However, such models discourage out-of-distribution generation to…

Recent research on robustness has revealed significant performance gaps between neural image classifiers trained on datasets that are similar to the test set, and those that are from a naturally shifted distribution, such as sketches,…