Related papers: Imagining Grounded Conceptual Representations from…
By pretraining to synthesize coherent images from perturbed inputs, generative models inherently learn to understand object boundaries and scene compositions. How can we repurpose these generative representations for general-purpose…
Object pose estimation is a fundamental task in computer vision and robotics, yet most methods require extensive, dataset-specific training. Concurrently, large-scale vision language models show remarkable zero-shot capabilities. In this…
Transformer-based models have dominated natural language processing and other areas in the last few years due to their superior (zero-shot) performance on benchmark datasets. However, these models are poorly understood due to their…
Object-centric representations using slots have shown the advances towards efficient, flexible and interpretable abstraction from low-level perceptual features in a compositional scene. Current approaches randomize the initial state of…
Human speakers can generate descriptions of perceptual concepts, abstracted from the instance-level. Moreover, such descriptions can be used by other speakers to learn provisional representations of those concepts. Learning and using…
While many methods for learning vector space embeddings have been proposed in the field of Natural Language Processing, these methods typically do not distinguish between categories and individuals. Intuitively, if individuals are…
Object pose estimation plays a vital role in embodied AI and computer vision, enabling intelligent agents to comprehend and interact with their surroundings. Despite the practicality of category-level pose estimation, current approaches…
The trade-off between accuracy and interpretability has long been a challenge in machine learning (ML). This tension is particularly significant for emerging interpretable-by-design methods, which aim to redesign ML algorithms for…
Few-shot learning remains challenging for meta-learning that learns a learning algorithm (meta-learner) from many related tasks. In this work, we argue that this is due to the lack of a good representation for meta-learning, and propose…
Spatial understanding is a fundamental problem with wide-reaching real-world applications. The representation of spatial knowledge is often modeled with spatial templates, i.e., regions of acceptability of two objects under an explicit…
Zero-shot learning extends the conventional object classification to the unseen class recognition by introducing semantic representations of classes. Existing approaches predominantly focus on learning the proper mapping function for…
Object manipulation requires accurate object pose estimation. In open environments, robots encounter unknown objects, which requires semantic understanding in order to generalize both to known categories and beyond. To resolve this…
Effective embodied exploration requires agents to accumulate and retain spatial knowledge over time. However, existing scene representations, such as discrete scene graphs or static view-based snapshots, lack \textit{post-hoc…
Any-shot image classification allows to recognize novel classes with only a few or even zero samples. For the task of zero-shot learning, visual attributes have been shown to play an important role, while in the few-shot regime, the effect…
People easily recognize new visual categories that are new combinations of known components. This compositional generalization capacity is critical for learning in real-world domains like vision and language because the long tail of new…
Object finding in clutter is a skill that requires perception of the environment and in many cases physical interaction. In robotics, interactive perception defines a set of algorithms that leverage actions to improve the perception of the…
Textual grounding is an important but challenging task for human-computer interaction, robotics and knowledge mining. Existing algorithms generally formulate the task as selection from a set of bounding box proposals obtained from deep net…
From the beginning of zero-shot learning research, visual attributes have been shown to play an important role. In order to better transfer attribute-based knowledge from known to unknown classes, we argue that an image representation with…
In real-world environments, AI systems often face unfamiliar scenarios without labeled data, creating a major challenge for conventional scene understanding models. The inability to generalize across unseen contexts limits the deployment of…
Generative object compositing emerges as a promising new avenue for compositional image editing. However, the requirement of object identity preservation poses a significant challenge, limiting practical usage of most existing methods. In…