Related papers: Sequence-based Multimodal Apprenticeship Learning …

Human perception of the empirical world involves recognizing the diverse appearances, or 'modalities', of underlying objects. Despite the longstanding consideration of this perspective in philosophy and cognitive science, the study of…

Personal robots assisting humans must perform complex manipulation tasks that are typically difficult to specify in traditional motion planning pipelines, where multiple objectives must be met and the high-level context be taken into…

Robots could learn their own state and world representation from perception and experience without supervision. This desirable goal is the main focus of our field of interest, state representation learning (SRL). Indeed, a compact…

This paper presents SPeCiaL: a method for unsupervised pretraining of representations tailored for continual learning. Our approach devises a meta-learning objective that differentiates through a sequential learning process. Specifically,…

We present a new machine learning technique for training small resource-constrained predictors. Our algorithm, the Sparse Multiprototype Linear Learner (SMaLL), is inspired by the classic machine learning problem of learning $k$-DNF Boolean…

Most of the few-shot learning methods learn to transfer knowledge from datasets with abundant labeled data (i.e., the base set). From the perspective of class space on base set, existing methods either focus on utilizing all classes under a…

The Long Short-Term Memory (LSTM) networks have traditionally faced challenges in scaling and effectively capturing complex dependencies in visual tasks. The xLSTM architecture has emerged to address these limitations, incorporating…

Imagine a robot is shown new concepts visually together with spoken tags, e.g. "milk", "eggs", "butter". After seeing one paired audio-visual example per class, it is shown a new set of unseen instances of these objects, and asked to pick…

Semi-supervised action recognition aims to improve spatio-temporal reasoning ability with a few labeled data in conjunction with a large amount of unlabeled data. Albeit recent advancements, existing powerful methods are still prone to…

Simultaneous Localization and Mapping (SLAM)consists in the concurrent construction of a model of the environment (the map), and the estimation of the state of the robot moving within it. The SLAM community has made astonishing progress…

Malignant brain tumors have become an aggressive and dangerous disease that leads to death worldwide.Multi-modal MRI data is crucial for accurate brain tumor segmentation, but missing modalities common in clinical practice can severely…

Simultaneous localization and mapping (SLAM) is the process of constructing a global model of an environment from local observations of it; this is a foundational capability for mobile robots, supporting such core functions as planning,…

Model-agnostic meta-learners aim to acquire meta-learned parameters from similar tasks to adapt to novel tasks from the same distribution with few gradient updates. With the flexibility in the choice of models, those frameworks demonstrate…

With the evolution of various advanced driver assistance system (ADAS) platforms, the design of autonomous driving system is becoming more complex and safety-critical. The autonomous driving system simultaneously activates multiple ADAS…

Model-Agnostic Meta-Learning (MAML), a popular gradient-based meta-learning framework, assumes that the contribution of each task or instance to the meta-learner is equal. Hence, it fails to address the domain shift between base and novel…

Learning to reliably perceive and understand the scene is an integral enabler for robots to operate in the real-world. This problem is inherently challenging due to the multitude of object types as well as appearance changes caused by…

Though quite challenging, leveraging large-scale unlabeled or partially labeled images in a cost-effective way has increasingly attracted interests for its great importance to computer vision. To tackle this problem, many Active Learning…

Multimodal learning assumes all modality combinations of interest are available during training to learn cross-modal correspondences. In this paper, we challenge this modality-complete assumption for multimodal learning and instead strive…

In urban environments, the complex and uncertain intersection scenarios are challenging for autonomous driving. To ensure safety, it is crucial to develop an adaptive decision making system that can handle the interaction with other…

Sentence-level classification and sequential labeling are two fundamental tasks in language understanding. While these two tasks are usually modeled separately, in reality, they are often correlated, for example in intent classification and…