Related papers: Detecting Unjustified Assumptions in Subclasses vi…
Robotic task instructions often involve a referred object that the robot must locate (ground) within the environment. While task intent understanding is an essential part of natural language understanding, less effort is made to resolve…
Easily programming behaviors is one major issue of a large and reconfigurable deployment in the Internet of Things. Such kind of devices often requires to externalize part of their behavior such as the sensing, the data aggregation or the…
Despite the recent advances in the field of object detection, common architectures are still ill-suited to incrementally detect new categories over time. They are vulnerable to catastrophic forgetting: they forget what has been already…
This paper addresses the challenging problem of open-vocabulary object detection (OVOD) where an object detector must identify both seen and unseen classes in test images without labeled examples of the unseen classes in training. A typical…
Object-centric representation learning aims to decompose visual scenes into fixed-size vectors called "slots" or "object files", where each slot captures a distinct object. Current state-of-the-art object-centric models have shown…
Causal representation learning has showed a variety of settings in which we can disentangle latent variables with identifiability guarantees (up to some reasonable equivalence class). Common to all of these approaches is the assumption that…
Language models (LMs) have achieved impressive accuracy across a variety of tasks but remain vulnerable to high-confidence misclassifications, also referred to as unknown unknowns (UUs). These UUs cluster into blind spots in the feature…
Object detection remains as one of the most notorious open problems in computer vision. Despite large strides in accuracy in recent years, modern object detectors have started to saturate on popular benchmarks raising the question of how…
Most of contemporary software systems are implemented using an object-oriented approach. Modeling phases -- during which software engineers analyze requirements to the future system using some modeling language -- are an important part of…
Out-of-distribution (OoD) inputs pose a persistent challenge to deep learning models, often triggering overconfident predictions on non-target objects. While prior work has primarily focused on refining scoring functions and adjusting…
EODECA (Engineered Ordinary Differential Equations as Classification Algorithm) is a novel approach at the intersection of machine learning and dynamical systems theory, presenting a unique framework for classification tasks [1]. This…
The alignment of language models with human preferences is vital for their application in real-world tasks. The problem is formulated as optimizing the model's policy to maximize the expected reward that reflects human preferences with…
Are existing object detection methods adequate for detecting text and visual elements in scientific plots which are arguably different than the objects found in natural images? To answer this question, we train and compare the accuracy of…
Logical frameworks based on intuitionistic or linear logics with higher-type quantification have been successfully used to give high-level, modular, and formal specifications of many important judgments in the area of programming languages…
A number of key scientific computing applications that are based upon tensor-product grid constructions, such as numerical weather prediction (NWP) and combustion simulations, require property-preserving interpolation. Essentially…
We propose active object languages as a development tool for formal system models of distributed systems. Additionally to a formalization based on a term rewriting system, we use established Software Engineering concepts, including software…
A more realistic object detection paradigm, Open-World Object Detection, has arisen increasing research interests in the community recently. A qualified open-world object detector can not only identify objects of known categories, but also…
Deep learning has proven to be a powerful tool for computer vision and has seen widespread adoption for numerous tasks. However, deep learning algorithms are known to be vulnerable to adversarial examples. These adversarial inputs are…
We develop a system to disambiguate object instances within the same class based on simple physical descriptions. The system takes as input a natural language phrase and a depth image containing a segmented object and predicts how similar…
A method of finding and classifying various components and objects in a design diagram, drawing, or planning layout is proposed. The method automatically finds the objects present in a legend table and finds their position, count and…