Related papers: Semantic-Aware Implicit Template Learning via Part…

Semantic segmentation has made tremendous progress in recent years. However, satisfying performance highly depends on a large number of pixel-level annotations. Therefore, in this paper, we focus on the semi-supervised segmentation problem…

An unsupervised shape analysis is proposed to learn concepts reflecting shape commonalities. Our approach is two-fold: i) a spatial topology analysis of point cloud segment constellations within objects is used in which constellations are…

Semi-supervised learning has attracted much attention in medical image segmentation due to challenges in acquiring pixel-wise image annotations, which is a crucial step for building high-performance deep learning methods. Most existing…

Semantic parsing aims to map natural language utterances onto machine interpretable meaning representations, aka programs whose execution against a real-world environment produces a denotation. Weakly-supervised semantic parsers are trained…

Recent advances in image-level self-supervised learning (SSL) have made significant progress, yet learning dense representations for patches remains challenging. Mainstream methods encounter an over-dispersion phenomenon that patches from…

Deep neural networks suffer from the major limitation of catastrophic forgetting old tasks when learning new ones. In this paper we focus on class incremental continual learning in semantic segmentation, where new categories are made…

Learning dense correspondences across deformable 3D shapes remains a long-standing challenge due to structural variability, non-isometric deformation, and inconsistent topology. Existing methods typically trade off generalization, geometric…

Latent representation learned from multi-layered neural networks via hierarchical feature abstraction enables recent success of deep learning. Under the deep learning framework, generalization performance highly depends on the learned…

Extracting structured representations from raw visual data is an important and long-standing challenge in machine learning. Recently, techniques for unsupervised learning of object-centric representations have raised growing interest. In…

Detecting semantic parts of an object is a challenging task in computer vision, particularly because it is hard to construct large annotated datasets due to the difficulty of annotating semantic parts. In this paper we present an approach…

In recent years, deep saliency models have made significant progress in predicting human visual attention. However, the mechanisms behind their success remain largely unexplained due to the opaque nature of deep neural networks. In this…

Parametric 3D models have formed a fundamental role in modeling deformable objects, such as human bodies, faces, and hands; however, the construction of such parametric models requires significant manual intervention and domain expertise.…

Automated surface-anomaly detection using machine learning has become an interesting and promising area of research, with a very high and direct impact on the application domain of visual inspection. Deep-learning methods have become the…

Object parts serve as crucial intermediate representations in various downstream tasks, but part-level representation learning still has not received as much attention as other vision tasks. Previous research has established that Vision…

Recently, there have been efforts to improve the performance in sign language recognition by designing self-supervised learning methods. However, these methods capture limited information from sign pose data in a frame-wise learning manner,…

Recent domain generalized semantic segmentation (DGSS) studies have achieved notable improvements by distilling semantic knowledge from Vision-Language Models (VLMs). However, they overlook the semantic misalignment between visual and…

Many 3D tasks such as pose alignment, animation, motion transfer, and 3D reconstruction rely on establishing correspondences between 3D shapes. This challenge has recently been approached by pairwise matching of semantic features from…

Deep Learning has greatly advanced the performance of semantic segmentation, however, its success relies on the availability of large amounts of annotated data for training. Hence, many efforts have been devoted to domain adaptive semantic…

Existing 3D semantic segmentation methods rely on point-wise or voxel-wise feature descriptors to output segmentation predictions. However, these descriptors are often supervised at point or voxel level, leading to segmentation models that…

Deep learning architectures exhibit a critical drop of performance due to catastrophic forgetting when they are required to incrementally learn new tasks. Contemporary incremental learning frameworks focus on image classification and object…