Related papers: Robust Embodied Perception in Dynamic Environments…

Object detection is an essential task for autonomous robots operating in dynamic and changing environments. A robot should be able to detect objects in the presence of sensor noise that can be induced by changing lighting conditions for…

Disentangled representation learning strives to extract the intrinsic factors within observed data. Factorizing these representations in an unsupervised manner is notably challenging and usually requires tailored loss functions or specific…

Practitioners often face the challenge of deploying prediction models in new environments with shifted distributions of covariates and responses. With observational data, such shifts are often driven by unobserved confounding, and can in…

Deep learning models have achieved great success on various vision challenges, but a well-trained model would face drastic performance degradation when applied to unseen data. Since the model is sensitive to domain shift, unsupervised…

Traditional deep learning-based visual imitation learning techniques require a large amount of demonstration data for model training, and the pre-trained models are difficult to adapt to new scenarios. To address these limitations, we…

We propose a novel robotic system that can improve its perception during deployment. Contrary to the established approach of learning semantics from large datasets and deploying fixed models, we propose a framework in which semantic models…

We study the problem of multimodal physical scene understanding, where an embodied agent needs to find fallen objects by inferring object properties, direction, and distance of an impact sound source. Previous works adopt feed-forward…

Despite significant advancements in image generation using advanced generative frameworks, cross-image integration of content and style remains a key challenge. Current generative models, while powerful, frequently depend on vague textual…

Learning contextual and spatial environmental representations enhances autonomous vehicle's hazard anticipation and decision-making in complex scenarios. Recent perception systems enhance spatial understanding with sensor fusion but often…

Machine learning systems may encounter unexpected problems when the data distribution changes in the deployment environment. A major reason is that certain combinations of domains and labels are not observed during training but appear in…

Most standard learning approaches lead to fragile models which are prone to drift when sequentially trained on samples of a different nature - the well-known "catastrophic forgetting" issue. In particular, when a model consecutively learns…

The quest for incremental unified multimodal anomaly detection seeks to empower a single model with the ability to systematically detect anomalies across all categories and support incremental learning to accommodate emerging…

Learning physical dynamics in a series of non-stationary environments is a challenging but essential task for model-based reinforcement learning (MBRL) with visual inputs. It requires the agent to consistently adapt to novel tasks without…

Diffusion models achieve state-of-the-art image generation but remain computationally costly due to iterative denoising. Latent-space models like Stable Diffusion reduce overhead yet lose fine detail, while retrieval-augmented methods…

Imitation learning has emerged as a crucial ap proach for acquiring visuomotor skills from demonstrations, where designing effective observation encoders is essential for policy generalization. However, existing methods often struggle to…

Foundation model-based semantic transmission has recently shown great potential in wireless image communication. However, existing methods exhibit two major limitations: (i) they overlook the varying importance of semantic components for…

The focus in machine learning has branched beyond training classifiers on a single task to investigating how previously acquired knowledge in a source domain can be leveraged to facilitate learning in a related target domain, known as…

In this paper, we present methods for two types of metacognitive tasks in an AI system: rapidly expanding a neural classification model to accommodate a new category of object, and recognizing when a novel object type is observed instead of…

While deep learning surpasses human-level performance in narrow and specific vision tasks, it is fragile and over-confident in classification. For example, minor transformations in perspective, illumination, or object deformation in the…

Infrared and visible image fusion plays a critical role in enhancing scene perception by combining complementary information from different modalities. Despite recent advances, achieving high-quality image fusion with lightweight models…