Related papers: Synergistic Perception and Generative Recompositio…
Generative AI (GenAI) has reshaped software system design by introducing foundation models as pre-trained subsystems that redefine architectures and operations. The emerging challenge is no longer model fine-tuning but context…
While modern visual generation models excel at creating aesthetically pleasing natural images, they struggle with producing or editing structured visuals like charts, diagrams, and mathematical figures, which demand composition planning,…
Learning discriminative task-specific features simultaneously for multiple distinct tasks is a fundamental problem in multi-task learning. Recent state-of-the-art models consider directly decoding task-specific features from one shared…
In computer vision, it is well-known that a lack of data diversity will impair model performance. In this study, we address the challenges of enhancing the dataset diversity problem in order to benefit various downstream tasks such as…
General aviation fault diagnosis and efficient maintenance are critical to flight safety; however, deploying deep learning models on resource-constrained edge devices poses dual challenges in computational capacity and interpretability.…
Curating datasets for object segmentation is a difficult task. With the advent of large-scale pre-trained generative models, conditional image generation has been given a significant boost in result quality and ease of use. In this paper,…
Some cognitive research has discovered that humans accomplish event segmentation as a side effect of event anticipation. Inspired by this discovery, we propose a simple yet effective end-to-end self-supervised learning framework for event…
Robots operating in unstructured environments often require accurate and consistent object-level representations. This typically requires segmenting individual objects from the robot's surroundings. While recent large models such as Segment…
Incomplete node features are ubiquitous in real-world scenarios such as user profiling and cold-start recommendation, which severely hinders the practical deployment of graph learning systems (e.g., GNNs). Existing solutions typically rely…
Restoring images affected by various types of degradation, such as noise, blur, or improper exposure, remains a significant challenge in computer vision. While recent trends favor complex monolithic all-in-one architectures, these models…
Visual recognition requires rich representations that span levels from low to high, scales from small to large, and resolutions from fine to coarse. Even with the depth of features in a convolutional network, a layer in isolation is not…
Face detection from low-light images is challenging due to limited photos and inevitable noise, which, to make the task even harder, are often spatially unevenly distributed. A natural solution is to borrow the idea from multi-exposure,…
Mask-guided matting networks have achieved significant improvements and have shown great potential in practical applications in recent years. However, simply learning matting representation from synthetic and lack-of-real-world-diversity…
Automated structural health monitoring is essential to prevent catastrophic infrastructure failures. Precise, pixel-level defect segmentation is needed to accurately assess structural integrity, but progress in defect segmentation for civil…
Few-Shot Industrial Visual Anomaly Detection (FS-IVAD) comprises a critical task in modern manufacturing settings, where automated product inspection systems need to identify rare defects using only a handful of normal/defect-free training…
Robust perception systems are essential for autonomous vehicle safety. To navigate in a complex urban environment, it is necessary precise sensors with reliable data. The task of understanding the surroundings is hard by itself; for…
Building properties, such as height, usage, and material, play a crucial role in spatial data infrastructures, supporting various urban applications. Despite their importance, comprehensive building attribute data remain scarce in many…
Computer vision models have known performance disparities across attributes such as gender and skin tone. This means during tasks such as classification and detection, model performance differs for certain classes based on the demographics…
This paper introduces a fast and efficient segmentation technique for 2D images and 3D point clouds of building facades. Facades of buildings are highly structured and consequently most methods that have been proposed for this problem aim…
Unsupervised Domain Adaptation (UDA) aims to solve the problem of label scarcity of the target domain by transferring the knowledge from the label rich source domain. Usually, the source domain consists of synthetic images for which the…