Related papers: Automatic Inference of Relational Object Invariant…
Incorporating relational reasoning into neural networks has greatly expanded their capabilities and scope. One defining trait of relational reasoning is that it operates on a set of entities, as opposed to standard vector representations.…
This paper introduces an automatic affordance reasoning paradigm tailored to minimal semantic inputs, addressing the critical challenges of classifying and manipulating unseen classes of objects in household settings. Inspired by human…
Achieving the generalization of an invariant classifier from training domains to shifted test domains while simultaneously considering model fairness is a substantial and complex challenge in machine learning. Existing methods address the…
Although deep reinforcement learning has advanced significantly over the past several years, sample efficiency remains a major challenge. Careful choice of input representations can help improve efficiency depending on the structure present…
Focus in Explainable AI is shifting from explanations defined in terms of low-level elements, such as input features, to explanations encoded in terms of interpretable concepts learned from data. How to reliably acquire such concepts is,…
Image inpainting is an essential task for multiple practical applications like object removal and image editing. Deep GAN-based models greatly improve the inpainting performance in structures and textures within the hole, but might also…
This paper addresses the problem of Human Activity Recognition (HAR) using data from wearable inertial sensors. An important challenge in HAR is the model's generalization capabilities to new unseen individuals due to inter-subject…
"Thinking in pictures," [1] i.e., spatial-temporal reasoning, effortless and instantaneous for humans, is believed to be a significant ability to perform logical induction and a crucial factor in the intellectual history of technology…
Trustworthiness of artificially intelligent agents is vital for the acceptance of human-machine teaming in industrial manufacturing environments. Predictable behaviours and explainable (and understandable) rationale allow humans…
The binding problem in human cognition, concerning how the brain represents and connects objects within a fixed network of neural connections, remains a subject of intense debate. Most machine learning efforts addressing this issue in an…
We propose InNeRF360, an automatic system that accurately removes text-specified objects from 360-degree Neural Radiance Fields (NeRF). The challenge is to effectively remove objects while inpainting perceptually consistent content for the…
This paper lays a practical foundation for using abstract interpretation with an abstract domain that consists of sets of quantified first-order logic formulas. This abstract domain seems infeasible at first sight due to the complexity of…
Heretofore, neural networks with external memory are restricted to single memory with lossy representations of memory interactions. A rich representation of relationships between memory pieces urges a high-order and segregated relational…
Machine learning methods rely on data. However, gathering suitable data can be challenging due to availability constraints, cost, or the need for domain expertise. Expanding datasets with additional sources is a common response to limited…
While concept-based interpretability methods have traditionally focused on local explanations of neural network predictions, we propose a novel framework and interactive tool that extends these methods into the domain of mechanistic…
This paper introduces an innovative approach to open world recognition (OWR), where we leverage knowledge acquired from known objects to address the recognition of previously unseen objects. The traditional method of object modeling relies…
Understanding and mapping a new environment are core abilities of any autonomously navigating agent. While classical robotics usually estimates maps in a stand-alone manner with SLAM variants, which maintain a topological or metric…
The need for large amounts of training data in modern machine learning is one of the biggest challenges of the field. Compared to the brain, current artificial algorithms are much less capable of learning invariance transformations and…
Current deep reinforcement learning (RL) approaches incorporate minimal prior knowledge about the environment, limiting computational and sample efficiency. \textit{Objects} provide a succinct and causal description of the world, and many…
Interpretability benefits the theoretical understanding of representations. Existing word embeddings are generally dense representations. Hence, the meaning of latent dimensions is difficult to interpret. This makes word embeddings like a…