Related papers: A Semantically Disentangled Unified Model for Mult…

Anomaly detection (AD) is a machine learning task that identifies anomalies by learning patterns from normal training data. In many real-world scenarios, anomalies vary in severity, from minor anomalies with little risk to severe…

Reconstruction-based methods play an important role in unsupervised anomaly detection in images. Ideally, we expect a perfect reconstruction for normal samples and poor reconstruction for abnormal samples. Since the generalizability of deep…

Large-scale datasets with point-wise semantic and instance labels are crucial to 3D instance segmentation but also expensive. To leverage unlabeled data, previous semi-supervised 3D instance segmentation approaches have explored…

We learn a self-supervised, single-view 3D reconstruction model that predicts the 3D mesh shape, texture and camera pose of a target object with a collection of 2D images and silhouettes. The proposed method does not necessitate 3D…

The 3D weakly-supervised visual grounding task aims to localize oriented 3D boxes in point clouds based on natural language descriptions without requiring annotations to guide model learning. This setting presents two primary challenges:…

Large intra-class variation is the result of changes in multiple object characteristics. Images, however, only show the superposition of different variable factors such as appearance or shape. Therefore, learning to disentangle and…

Remote sensing image segmentation faces persistent challenges in distinguishing morphologically similar categories and adapting to diverse scene variations. While existing methods rely on implicit representation learning paradigms, they…

3D scene understanding is fundamental for embodied AI and robotics, supporting reliable perception for interaction and navigation. Recent approaches achieve zero-shot, open-vocabulary 3D semantic mapping by assigning embedding vectors to 2D…

To better address challenging issues of the irregularity and inhomogeneity inherently present in 3D point clouds, researchers have been shifting their focus from the design of hand-craft point feature towards the learning of 3D point…

Most existing methods for unsupervised industrial anomaly detection train a separate model for each object category. This kind of approach can easily capture the category-specific feature distributions, but results in high storage cost and…

We address the problem of discovering part segmentations of articulated objects without supervision. In contrast to keypoints, part segmentations provide information about part localizations on the level of individual pixels. Capturing both…

In this paper, we focus on Novel Class Discovery for Point Cloud Segmentation (3D-NCD), aiming to learn a model that can segment unlabeled (novel) 3D classes using only the supervision from labeled (base) 3D classes. The key to this task is…

Visual anomaly detection in multi-class settings poses significant challenges due to the diversity of object categories, the scarcity of anomalous examples, and the presence of camouflaged defects. In this paper, we propose PromptMAD, a…

We introduce the first comprehensive 3D dataset for the task of unsupervised anomaly detection and localization. It is inspired by real-world visual inspection scenarios in which a model has to detect various types of defects on…

Anomaly detection (AD) is a fundamental task of critical importance across numerous domains. Current systems increasingly operate in rapidly evolving environments that generate diverse yet interconnected data modalities -- such as time…

To ease the difficulty of acquiring annotation labels in 3D data, a common method is using unsupervised and open-vocabulary semantic segmentation, which leverage 2D CLIP semantic knowledge. In this paper, unlike previous research that…

Domain generalization in 3D segmentation is a critical challenge in deploying models to unseen environments. Current methods mitigate the domain shift by augmenting the data distribution of point clouds. However, the model learns global…

Deep learning techniques have become the to-go models for most vision-related tasks on 2D images. However, their power has not been fully realised on several tasks in 3D space, e.g., 3D scene understanding. In this work, we jointly address…

Dynamic graph anomaly detection (DGAD) is critical for many real-world applications but remains challenging due to the scarcity of labeled anomalies. Existing methods are either unsupervised or semi-supervised: unsupervised methods avoid…

Graph anomaly detection (GAD) is increasingly crucial in various applications, ranging from financial fraud detection to fake news detection. However, current GAD methods largely overlook the fairness problem, which might result in…