Related papers: SCANet: Correcting LEGO Assembly Errors with Self-…

A key requirement for leveraging supervised deep learning methods is the availability of large, labeled datasets. Unfortunately, in the context of RGB-D scene understanding, very little data is available -- current datasets cover a small…

Long-range and short-range temporal modeling are two complementary and crucial aspects of video recognition. Most of the state-of-the-arts focus on short-range spatio-temporal modeling and then average multiple snippet-level predictions to…

Despite the great progress made by deep CNNs in image semantic segmentation, they typically require a large number of densely-annotated images for training and are difficult to generalize to unseen object categories. Few-shot segmentation…

This paper studies the problem of fixing malfunctional 3D objects. While previous works focus on building passive perception models to learn the functionality from static 3D objects, we argue that functionality is reckoned with respect to…

Robotic peg-in-hole assembly represents a critical area of investigation in robotic automation. The fusion of reinforcement learning (RL) and deep neural networks (DNNs) has yielded remarkable breakthroughs in this field. However, existing…

Standard modern machine-learning-based imaging methods have faced challenges in medical applications due to the high cost of dataset construction and, thereby, the limited labeled training data available. Additionally, upon deployment,…

Accurate medical image segmentation is of utmost importance for enabling automated clinical decision procedures. However, prevailing supervised deep learning approaches for medical image segmentation encounter significant challenges due to…

Few-shot segmentation models excel in metal defect detection due to their rapid generalization ability to new classes and pixel-level segmentation, rendering them ideal for addressing data scarcity issues and achieving refined object…

The task of reassembly is a significant challenge across multiple domains, including archaeology, genomics, and molecular docking, requiring the precise placement and orientation of elements to reconstruct an original structure. In this…

We tackle the problem of sequential brick assembly with LEGO bricks to create combinatorial 3D structures. This problem is challenging since this brick assembly task encompasses the characteristics of combinatorial optimization problems. In…

High-resolution medical images can provide more detailed information for better diagnosis. Conventional medical image super-resolution relies on a single task which first performs the extraction of the features and then upscaling based on…

We introduce SELECT (Scene tExt Label Errors deteCTion), a novel approach that leverages multi-modal training to detect label errors in real-world scene text datasets. Utilizing an image-text encoder and a character-level tokenizer, SELECT…

The most established method of reconstructing neural circuits from animals involves slicing tissue very thin, then taking mosaics of electron microscope (EM) images. To trace neurons across different images and through different sections,…

Surface cracks in infrastructure can lead to severe deterioration and expensive maintenance if not efficiently repaired. Manual repair methods are labor-intensive, time-consuming, and imprecise. While advancements in robotic perception and…

Deep convolutional neural networks have proved effective in segmenting lesions and anatomies in various medical imaging modalities. However, in the presence of small sample size and domain shift problems, these models often produce masks…

The ability to detect failures and anomalies are fundamental requirements for building reliable systems for computer vision applications, especially safety-critical applications of semantic segmentation, such as autonomous driving and…

Advances in deep learning techniques have allowed recent work to reconstruct the shape of a single object given only one RBG image as input. Building on common encoder-decoder architectures for this task, we propose three extensions: (1)…

In robot automated assembly, snap assembly precision and efficiency directly determine overall production quality. As a core prerequisite, snap detection and localization critically affect subsequent assembly success. Traditional visual…

With the rapid development of AI hardware accelerators, applying deep learning-based algorithms to solve various low-level vision tasks on mobile devices has gradually become possible. However, two main problems still need to be solved:…

Due to the complicated nanoscale structures of current integrated circuits(IC) builds and low error tolerance of IC image segmentation tasks, most existing automated IC image segmentation approaches require human experts for visual…