Related papers: SASep: Saliency-Aware Structured Separation of Geo…

Open-Set Object Detection (OSOD) is crucial for autonomous driving, where perception systems must recognize and localize both known and previously unseen objects in complex, dynamic environments. While recent approaches deliver promising…

Sparse Autoencoders (SAEs) have demonstrated significant success in interpreting Large Language Models (LLMs) by decomposing dense representations into sparse, semantic components. However, their potential for analyzing Vision Transformers…

Recent advances in self-supervised learning (SSL) for point clouds have substantially improved 3D scene understanding without human annotations. Existing approaches emphasize semantic awareness by enforcing feature consistency across…

The primary assumption of conventional supervised learning or classification is that the test samples are drawn from the same distribution as the training samples, which is called closed set learning or classification. In many practical…

Low-level 3D representations, such as point clouds, meshes, NeRFs and 3D Gaussians, are commonly used for modeling 3D objects and scenes. However, cognitive studies indicate that human perception operates at higher levels and interprets 3D…

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…

Zero-Shot Learning (ZSL) targets at recognizing unseen categories by leveraging auxiliary information, such as attribute embedding. Despite the encouraging results achieved, prior ZSL approaches focus on improving the discriminant power of…

Fine-grained open-set recognition (FineOSR) aims to recognize images belonging to classes with subtle appearance differences while rejecting images of unknown classes. A recent trend in OSR shows the benefit of generative models to…

3D Gaussian Splatting is renowned for its high-fidelity reconstructions and real-time novel view synthesis, yet its lack of semantic understanding limits object-level perception. In this work, we propose ObjectGS, an object-aware framework…

Image segmentation beyond predefined categories is a key challenge in remote sensing, where novel and unseen classes often emerge during inference. Open-vocabulary image Segmentation addresses these generalization issues in traditional…

This study investigates an application of a new probabilistic interpretation of a softmax output to Open-Set Recognition (OSR). Softmax is a mechanism wildly used in classification and object recognition. However, a softmax mechanism forces…

In the realm of automated robotic surgery and computer-assisted interventions, understanding robotic surgical activities stands paramount. Existing algorithms dedicated to surgical activity recognition predominantly cater to pre-defined…

As a consequence of an ever-increasing number of service robots, there is a growing demand for highly accurate real-time 3D object recognition. Considering the expansion of robot applications in more complex and dynamic environments,it is…

Open-set Semi-supervised Learning (OSSL) holds a realistic setting that unlabeled data may come from classes unseen in the labeled set, i.e., out-of-distribution (OOD) data, which could cause performance degradation in conventional SSL…

We propose a novel 3D point cloud segmentation framework named SASO, which jointly performs semantic and instance segmentation tasks. For semantic segmentation task, inspired by the inherent correlation among objects in spatial context, we…

Real-world scenarios pose several challenges to deep learning based computer vision techniques despite their tremendous success in research. Deeper models provide better performance, but are challenging to deploy and knowledge distillation…

Clustering is a fundamental unsupervised representation learning task with wide application in computer vision and pattern recognition. Deep clustering utilizes deep neural networks to learn latent representation, which is suitable for…

This paper addresses the semantic instance segmentation task in the open-set conditions, where input images can contain known and unknown object classes. The training process of existing semantic instance segmentation methods requires…

Recent Salient Object Detection (SOD) systems are mostly based on Convolutional Neural Networks (CNNs). Specifically, Deeply Supervised Saliency (DSS) system has shown it is very useful to add short connections to the network and…

Recovering 3D geometry and textures of individual objects is crucial for many robotics applications, such as manipulation, pose estimation, and autonomous driving. However, decomposing a target object from a complex background is…