Related papers: INTERN: A New Learning Paradigm Towards General Vi…
Due to its perceptual limitations, an agent may have too little information about the state of the environment to act optimally. In such cases, it is important to keep track of the observation history to uncover hidden state. Recent deep…
Current meta-learning methods are constrained to narrow task distributions with fixed feature and label spaces, limiting applicability. Moreover, the current meta-learning literature uses key terms like "universal" and "general-purpose"…
Implicit Neural Representations (INRs) are powerful to parameterize continuous signals in computer vision. However, almost all INRs methods are limited to low-level tasks, e.g., image/video compression, super-resolution, and image…
This paper presents a comprehensive survey of vision-language (VL) intelligence from the perspective of time. This survey is inspired by the remarkable progress in both computer vision and natural language processing, and recent trends…
Learning to navigate in a visual environment following natural-language instructions is a challenging task, because the multimodal inputs to the agent are highly variable, and the training data on a new task is often limited. In this paper,…
Intrinsic decomposition from a single image is a highly challenging task, due to its inherent ambiguity and the scarcity of training data. In contrast to traditional fully supervised learning approaches, in this paper we propose learning…
Training general-purpose vision models on purely sequential visual data, eschewing linguistic inputs, has heralded a new frontier in visual understanding. These models are intended to not only comprehend but also seamlessly transit to…
The rise of generalist robotic policies has created an exponential demand for large-scale training data. However, on-robot data collection is labor-intensive and often limited to specific environments. In contrast, open-world images capture…
Over the past decade, deep learning research has been accelerated by increasingly powerful hardware, which facilitated rapid growth in the model complexity and the amount of data ingested. This is becoming unsustainable and therefore…
In minimally invasive surgery, clinical decisions depend on real-time visual interpretation, yet intraoperative perception varies substantially across surgeons and procedures. This variability limits consistent assessment, training, and the…
Traditional supervised learning aims to train a classifier in the closed-set world, where training and test samples share the same label space. In this paper, we target a more challenging and realistic setting: open-set learning (OSL),…
The rapid advancement of generative models has empowered modern AI systems to comprehend and produce highly sophisticated content, even achieving human-level performance in specific domains. However, these models are fundamentally…
Transfer learning enables to re-use knowledge learned on a source task to help learning a target task. A simple form of transfer learning is common in current state-of-the-art computer vision models, i.e. pre-training a model for image…
An important component for generalization in machine learning is to uncover underlying latent factors of variation as well as the mechanism through which each factor acts in the world. In this paper, we test whether 17 unsupervised, weakly…
Recent neural implicit representations (NIRs) have achieved great success in the tasks of 3D reconstruction and novel view synthesis. However, they require the images of a scene from different camera views to be available for one-time…
Omnidirectional vision, using 360-degree vision to understand the environment, has become increasingly critical across domains like robotics, industrial inspection, and environmental monitoring. Compared to traditional pinhole vision,…
Physics-Informed Neural Networks (PINNs) are Neural Network architectures trained to emulate solutions of differential equations without the necessity of solution data. They are currently ubiquitous in the scientific literature due to their…
Prompt learning is one of the most effective and trending ways to adapt powerful vision-language foundation models like CLIP to downstream datasets by tuning learnable prompt vectors with very few samples. However, although prompt learning…
Generalized Few-Shot Intent Detection (GFSID) is challenging and realistic because it needs to categorize both seen and novel intents simultaneously. Previous GFSID methods rely on the episodic learning paradigm, which makes it hard to…
Interest in Artificial Intelligence (AI) and its applications has seen unprecedented growth in the last few years. This success can be partly attributed to the advancements made in the sub-fields of AI such as machine learning, computer…