Related papers: GAIA: A Transfer Learning System of Object Detecti…

Face recognition in unconstrained environments such as surveillance, video, and web imagery must contend with extreme variation in pose, blur, illumination, and occlusion, where conventional visual quality metrics fail to predict whether…

Detecting out-of-distribution (OOD) samples plays a key role in open-world and safety-critical applications such as autonomous systems and healthcare. Recently, self-supervised representation learning techniques (via contrastive learning…

The prior self-supervised learning researches mainly select image-level instance discrimination as pretext task. It achieves a fantastic classification performance that is comparable to supervised learning methods. However, with degraded…

Collecting operationally realistic data to inform machine learning models can be costly. Before collecting new data, it is helpful to understand where a model is deficient. For example, object detectors trained on images of rare objects may…

Technological advancements have led to the rise of wearable devices with sensors that continuously monitor user activities, generating vast amounts of unlabeled data. This data is challenging to interpret, and manual annotation is…

Robotic autonomy in open-world environments is fundamentally limited by insufficient data diversity and poor cross-embodiment generalization. Existing robotic datasets are often limited in scale and task coverage, while relatively large…

In conventional distributed learning over a network, multiple agents collaboratively build a common machine learning model. However, due to the underlying non-i.i.d. data distribution among agents, the unified learning model becomes…

When your robot grasps an object using dexterous hands or grippers, it should understand the Task-Oriented Affordances of the Object(TOAO), as different tasks often require attention to specific parts of the object. To address this…

Nowadays, a huge number of images are available. However, retrieving a required image for an ordinary user is a challenging task in computer vision systems. During the past two decades, many types of research have been introduced to improve…

Large-scale pre-training followed by downstream fine-tuning is an effective solution for transferring deep-learning-based models. Since finetuning all possible pre-trained models is computational costly, we aim to predict the…

In recent years, artificial intelligence (AI) based on deep learning (DL) has sparked tremendous global interest. DL is widely used today and has expanded into various interesting areas. It is becoming more popular in cross-subject…

Power dispatch is essential for providing stable, cost-effective, and eco-friendly electricity to society. However, traditional methods falter as power systems grow in scale and complexity, struggling with multitasking, swift…

Vision, as an inexpensive yet information rich sensor, is commonly used for perception on autonomous mobile robots. Unfortunately, accurate vision-based perception requires a number of assumptions about the environment to hold -- some…

Object detection is an important part in the field of computer vision, and the effect of object detection is directly determined by the regression accuracy of the prediction box. As the key to model training, IoU (Intersection over Union)…

Diffusion models have attracted significant attention due to the remarkable ability to create content and generate data for tasks like image classification. However, the usage of diffusion models to generate the high-quality object…

Geothermal field development typically involves complex processes that require multi-disciplinary expertise in each process. Thus, decision-making often demands the integration of geological, geophysical, reservoir engineering, and…

We present the Deep-learning Transient Astronomical Object (Deep-TAO), a dataset of 1,249,079 annotated images from the Catalina Real-time Transient Survey, including 3,807 transient and 12,500 non-transient sequences. Deep-TAO has been…

Zero-Input AI (ZIA) introduces a novel framework for human-computer interaction by enabling proactive intent prediction without explicit user commands. It integrates gaze tracking, bio-signals (EEG, heart rate), and contextual data (time,…

Prevalent human-object interaction (HOI) detection approaches typically leverage large-scale visual-linguistic models to help recognize events involving humans and objects. Though promising, models trained via contrastive learning on…

We introduce Diffusion Augmented Agents (DAAG), a novel framework that leverages large language models, vision language models, and diffusion models to improve sample efficiency and transfer learning in reinforcement learning for embodied…