Related papers: D-CODA: Diffusion for Coordinated Dual-Arm Data Au…

The performance of leaning-based perception algorithms suffer when deployed in out-of-distribution and underrepresented environments. Outdoor robots are particularly susceptible to rapid changes in visual scene appearance due to dynamic…

Diffusion generative models have demonstrated remarkable success in visual domains such as image and video generation. They have also recently emerged as a promising approach in robotics, especially in robot manipulations. Diffusion models…

Bimanual manipulation is essential in robotics, yet developing foundation models is extremely challenging due to the inherent complexity of coordinating two robot arms (leading to multi-modal action distributions) and the scarcity of…

In this paper, we present an effective data augmentation framework leveraging the Large Language Model (LLM) and Diffusion Model (DM) to tackle the challenges inherent in data-scarce scenarios. Recently, DMs have opened up the possibility…

Single-Domain Generalized Object Detection~(S-DGOD) aims to train on a single source domain for robust performance across a variety of unseen target domains by taking advantage of an object detector. Existing S-DGOD approaches often rely on…

Recent work has demonstrated the potential of diffusion models in robot bimanual skill learning. However, existing methods ignore the learning of posture-dependent task features, which are crucial for adapting dual-arm configurations to…

The robustness of visual navigation policies trained through imitation often hinges on the augmentation of the training image-action pairs. Traditionally, this has been done by collecting data from multiple cameras, by using standard data…

Dexterous manipulation with contact-rich interactions is crucial for advanced robotics. While recent diffusion-based planning approaches show promise for simple manipulation tasks, they often produce unrealistic ghost states (e.g., the…

Robots that can operate autonomously in a human living environment are necessary to have the ability to handle various tasks flexibly. One crucial element is coordinated bimanual movements that enable functions that are difficult to perform…

Prevailing Dataset Distillation (DD) methods leveraging generative models confront two fundamental limitations. First, despite pioneering the use of diffusion models in DD and delivering impressive performance, the vast majority of…

Active learning effectively collects data instances for training deep learning models when the labeled dataset is limited and the annotation cost is high. Besides active learning, data augmentation is also an effective technique to enlarge…

Cross-modal transfer learning is used to improve multi-modal classification models (e.g., for human activity recognition in human-robot collaboration). However, existing methods require paired sensor data at both training and inference,…

Data augmentation is a key element in training high-dimensional models. In this approach, one synthesizes new observations by applying pre-specified transformations to the original training data; e.g.~new images are formed by rotating old…

Artificial neural networks, especially recent diffusion-based models, have shown remarkable superiority in gaming, control, and QA systems, where the training tasks' datasets are usually static. However, in real-world applications, such as…

It is challenging to train a robust object detector under the supervised learning setting when the annotated data are scarce. Thus, previous approaches tackling this problem are in two categories: semi-supervised learning models that…

Few-shot object detection (FSOD) for optical remote sensing images aims to detect rare objects with only a few annotated bounding boxes. The limited training data makes it difficult to represent the data distribution of realistic remote…

We introduce ControlAugment (Ctrl-A), an automated data augmentation algorithm for image-vision tasks, which incorporates principles from control theory for online adjustment of augmentation strength distributions during model training.…

This work introduces DiffuseLoco, a framework for training multi-skill diffusion-based policies for dynamic legged locomotion from offline datasets, enabling real-time control of diverse skills on robots in the real world. Offline learning…

Data augmentation is one of the most prevalent tools in deep learning, underpinning many recent advances, including those from classification, generative models, and representation learning. The standard approach to data augmentation…

Despite remarkable progress in image generation models, generating realistic hands remains a persistent challenge due to their complex articulation, varying viewpoints, and frequent occlusions. We present FoundHand, a large-scale…