Related papers: Stronger, Fewer, & Superior: Harnessing Vision Fou…

Detecting glass regions is a challenging task due to the inherent ambiguity in their transparency and reflective characteristics. Current solutions in this field remain rooted in conventional deep learning paradigms, requiring the…

Single Domain Generalization (SDG) for object detection aims to train a model on a single source domain that can generalize effectively to unseen target domains. While recent methods like CLIP-based semantic augmentation have shown promise,…

Deep neural object detection or segmentation networks are commonly trained with pristine, uncompressed data. However, in practical applications the input images are usually deteriorated by compression that is applied to efficiently transmit…

Recent advancements in video semantic segmentation have made substantial progress by exploiting temporal correlations. Nevertheless, persistent challenges, including redundant computation and the reliability of the feature propagation…

Deep neural networks have shown exemplary performance on semantic scene understanding tasks on source domains, but due to the absence of style diversity during training, enhancing performance on unseen target domains using only single…

Vision foundation models have attracted significant attention for their ability to leverage large-scale unlabeled visual data. This advantage is particularly important in remote sensing, where data acquisition is costly and annotation often…

The rapid advancement of generative models has introduced serious risks, including deepfake techniques for facial synthesis and editing. Traditional approaches rely on training classifiers and enhancing generalizability through various…

The adoption of neural network models in medical imaging has been constrained by strict privacy regulations, limited data availability, high acquisition costs, and demographic biases. Deep generative models offer a promising solution by…

Vision foundation models have demonstrated exceptional generalization capabilities in segmentation tasks for both generic and specialized images. However, a performance gap persists between foundation models and task-specific, specialized…

Pretrained vision foundation models deliver strong performance across tasks with limited fine-tuning. However, their Vision Transformer (ViT) backbones impose high inference costs, limiting deployment on resource-constrained devices. In…

Pre-trained vision models (PVMs) have demonstrated remarkable adaptability across a wide range of downstream vision tasks, showcasing exceptional performance. However, as these models scale to billions or even trillions of parameters,…

Foundation models are rapidly transforming Earth Observation data mining by enabling generalizable and scalable solutions for key tasks such as scene classification and semantic segmentation. While most efforts in the geospatial domain have…

Representation of semantic context and local details is the essential issue for building modern semantic segmentation models. However, the interrelationship between semantic context and local details is not well explored in previous works.…

Despite the impressive performance of Multi-view Stereo (MVS) approaches given plenty of training samples, the performance degradation when generalizing to unseen domains has not been clearly explored yet. In this work, we focus on the…

Large-scale foundation models have become the mainstream deep learning method, while in civil engineering, the scale of AI models is strictly limited. In this work, a vision foundation model is introduced for crack segmentation. Two…

In recent years generative models of visual data have made a great progress, and now they are able to produce images of high quality and diversity. In this work we study representations learnt by a GAN generator. First, we show that these…

Fine-tuning pretrained models is a common practice in domain generalization (DG) tasks. However, fine-tuning is usually computationally expensive due to the ever-growing size of pretrained models. More importantly, it may cause over-fitting…

Generalized zero-shot learning (GZSL) has achieved significant progress, with many efforts dedicated to overcoming the problems of visual-semantic domain gap and seen-unseen bias. However, most existing methods directly use feature…

Purpose: The purpose of this study is to investigate the robustness of a commonly-used convolutional neural network for image segmentation with respect to visually-subtle adversarial perturbations, and suggest new methods to make these…

Foundation models and their checkpoints have significantly advanced deep learning, boosting performance across various applications. However, fine-tuned models often struggle outside their specific domains and exhibit considerable…