Related papers: Incremental Few-Shot Adaptation for Non-Prehensile…

We introduce SubGD, a novel few-shot learning method which is based on the recent finding that stochastic gradient descent updates tend to live in a low-dimensional parameter subspace. In experimental and theoretical analyses, we show that…

Large-scale pre-trained models have achieved remarkable success in language and image tasks, leading an increasing number of studies to explore the application of pre-trained image models, such as CLIP, in the domain of few-shot action…

Existing works in few-shot action recognition mostly fine-tune a pre-trained image model and design sophisticated temporal alignment modules at feature level. However, simply fully fine-tuning the pre-trained model could cause overfitting…

Robotic tasks which involve uncertainty--due to variation in goal, environment configuration, or confidence in task model--may require human input to instruct or adapt the robot. In tasks with physical contact, several existing methods for…

Unlike traditional robotic hands, underactuated compliant hands are challenging to model due to inherent uncertainties. Consequently, pose estimation of a grasped object is usually performed based on visual perception. However, visual…

Learning and generalizing from limited examples, i,e, few-shot learning, is of core importance to many real-world vision applications. A principal way of achieving few-shot learning is to realize an embedding where samples from different…

This paper proposes a technique to manipulate an object with a nonholonomic mobile robot by pushing, which is a nonprehensile manipulation motion primitive. Such a primitive involves unilateral constraints associated with the friction…

Integrating image and text data through multi-modal learning has emerged as a new approach in medical imaging research, following its successful deployment in computer vision. While considerable efforts have been dedicated to establishing…

Magnetic microrobots can be navigated by an external magnetic field to autonomously move within living organisms with complex and unstructured environments. Potential applications include drug delivery, diagnostics, and therapeutic…

Few-shot learning, which aims at extracting new concepts rapidly from extremely few examples of novel classes, has been featured into the meta-learning paradigm recently. Yet, the key challenge of how to learn a generalizable classifier…

Remote Sensing Vision-Language Models (RSVLMs) have shown remarkable potential thanks to large-scale pretraining, achieving strong zero-shot performance on various tasks. However, their ability to generalize in low-data regimes, such as…

We present a principled method for motion prediction via dynamic simulation for rigid bodies in intermittent contact with each other where the contact region is a planar non-convex contact patch. Such methods are useful in planning and…

Design of robots at the small scale is a trial-and-error based process, which is costly and time-consuming. There are no good dynamic simulation tools to predict the motion or performance of a microrobot as it moves against a substrate. At…

Dense object tracking, the ability to localize specific object points with pixel-level accuracy, is an important computer vision task with numerous downstream applications in robotics. Existing approaches either compute dense keypoint…

Imitation learning is a promising approach to help robots acquire dexterous manipulation capabilities without the need for a carefully-designed reward or a significant computational effort. However, existing imitation learning approaches…

This paper proposes a combined optimization and learning method for impact-friendly, non-prehensile catching of objects at non-zero velocity. Through a constrained Quadratic Programming problem, the method generates optimal trajectories up…

Modeling dynamical systems plays a crucial role in capturing and understanding complex physical phenomena. When physical models are not sufficiently accurate or hardly describable by analytical formulas, one can use generic function…

Large-scale multimodal representation learning successfully optimizes for zero-shot transfer at test time. Yet the standard pretraining paradigm (contrastive learning on large amounts of image-text data) does not explicitly encourage…

Sampling-based Model Predictive Control (MPC) is a flexible control framework that can reason about non-smooth dynamics and cost functions. Recently, significant work has focused on the use of machine learning to improve the performance of…

New classes of sounds constantly emerge with a few samples, making it challenging for models to adapt to dynamic acoustic environments. This challenge motivates us to address the new problem of few-shot class-incremental audio…