Related papers: Fidelity-Aware Data Composition for Robust Robot G…
Data augmentation is widely utilized as an effective technique to enhance the generalization performance of deep models. However, data augmentation may inevitably introduce distribution shifts and noises, which significantly constrain the…
Deep neural networks often produce overconfident predictions, undermining their reliability in safety-critical applications. This miscalibration is further exacerbated under distribution shift, where test data deviates from the training…
An important and unsolved problem in computer vision is to ensure that the algorithms are robust to changes in image domains. We address this problem in the scenario where we have access to images from the target domains but no annotations.…
Computer vision is difficult, partly because the desired mathematical function connecting input and output data is often complex, fuzzy and thus hard to learn. Coarse-to-fine (C2F) learning is a promising direction, but it remains unclear…
Robust and efficient learning remains a challenging problem in robotics, in particular with complex visual inputs. Inspired by human attention mechanism, with which we quickly process complex visual scenes and react to changes in the…
Recently, learning-based approaches show promising results in navigation tasks. However, the poor generalization capability and the simulation-reality gap prevent a wide range of applications. We consider the problem of improving the…
Virtual testing using synthetic data has become a cornerstone of autonomous vehicle (AV) safety assurance. Despite progress in improving visual realism through advanced simulators and generative AI, recent studies reveal that pixel-level…
The finding that very large networks can be trained efficiently and reliably has led to a paradigm shift in computer vision from engineered solutions to learning formulations. As a result, the research challenge shifts from devising…
In the age of big data, it is important for primary research data to follow the FAIR principles of findability, accessibility, interoperability, and reusability. Data harmonization enhances interoperability and reusability by aligning…
Diffusion Policy (DP) has attracted significant attention as an effective method for policy representation due to its capacity to model multi-distribution dynamics. However, current DPs are often based on a single visual modality (e.g., RGB…
Large behavior models have shown strong dexterous manipulation capabilities by extending imitation learning to large-scale training on multi-task robot data, yet their generalization remains limited by the insufficient robot data coverage.…
Personalizing diffusion models using limited data presents significant challenges, including overfitting, loss of prior knowledge, and degradation of text alignment. Overfitting leads to shifts in the noise prediction distribution,…
3D object detection serves as the core basis of the perception tasks in autonomous driving. Recent years have seen the rapid progress of multi-modal fusion strategies for more robust and accurate 3D object detection. However, current…
Training deep networks that generalize to a wide range of variations in test data is essential to building accurate and robust image classifiers. One standard strategy is to apply data augmentation to synthetically enlarge the training set.…
Imitation learning in robotics faces significant challenges in generalization due to the complexity of robotic environments and the high cost of data collection. We introduce RoCoDA, a novel method that unifies the concepts of invariance,…
Developing machine intelligence abilities in robots and autonomous systems is an expensive and time consuming process. Existing solutions are tailored to specific applications and are harder to generalize. Furthermore, scarcity of training…
Training models with robust group fairness properties is crucial in ethically sensitive application areas such as medical diagnosis. Despite the growing body of work aiming to minimise demographic bias in AI, this problem remains…
Compositional generalization-a key open challenge in modern machine learning-requires models to predict unknown combinations of known concepts. However, assessing compositional generalization remains a fundamental challenge due to the lack…
Imitation learning has emerged as a powerful paradigm in robot manipulation, yet its generalization capability remains constrained by object-specific dependencies in limited expert demonstrations. To address this challenge, we propose…
Diffusion models excel at short-horizon robot planning, yet scaling them to long-horizon tasks remains challenging due to computational constraints and limited training data. Existing compositional approaches stitch together short segments…