中文
相关论文

相关论文: Expanding Low-Density Latent Regions for Open-Set …

200 篇论文

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…

计算机视觉与模式识别 · 计算机科学 2022-08-23 Sepideh Esmaeilpour , Lei Shu , Bing Liu

Conventional camera-based 3D object detectors in autonomous driving are limited to recognizing a predefined set of objects, which poses a safety risk when encountering novel or unseen objects in real-world scenarios. To address this…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Zhuolin He , Xinrun Li , Jiacheng Tang , Shoumeng Qiu , Wenfu Wang , Xiangyang Xue , Jian Pu

Open world object detection aims at detecting objects that are absent in the object classes of the training data as unknown objects without explicit supervision. Furthermore, the exact classes of the unknown objects must be identified…

计算机视觉与模式识别 · 计算机科学 2022-12-07 Na Dong , Yongqiang Zhang , Mingli Ding , Gim Hee Lee

Open World Object Detection (OWOD) is a novel computer vision task with a considerable challenge, bridging the gap between classic object detection (OD) benchmarks and real-world object detection. In addition to detecting and classifying…

计算机视觉与模式识别 · 计算机科学 2023-03-22 Shuailei Ma , Yuefeng Wang , Ying Wei , Peihao Chen , Zhixiang Ye , Jiaqi Fan , Enming Zhang , Thomas H. Li

In this paper, we attempt to specialize the VLM model for OWOD tasks by distilling its open-world knowledge into a language-agnostic detector. Surprisingly, we observe that the combination of a simple \textbf{knowledge distillation}…

计算机视觉与模式识别 · 计算机科学 2024-04-02 Shuailei Ma , Yuefeng Wang , Ying Wei , Jiaqi Fan , Enming Zhang , Xinyu Sun , Peihao Chen

Deep learning has enabled remarkable advances in scene understanding, particularly in semantic segmentation tasks. Yet, current state of the art approaches are limited to a closed set of classes, and fail when facing novel elements, also…

计算机视觉与模式识别 · 计算机科学 2020-06-02 Nicolas Marchal , Charlotte Moraldo , Roland Siegwart , Hermann Blum , Cesar Cadena , Abel Gawel

Object detection is a pivotal task in computer vision that has received significant attention in previous years. Nonetheless, the capability of a detector to localise objects out of the training distribution remains unexplored. Whilst…

计算机视觉与模式识别 · 计算机科学 2024-07-23 Brian K. S. Isaac-Medina , Yona Falinie A. Gaus , Neelanjan Bhowmik , Toby P. Breckon

Most object detectors operate under a closed-world assumption, recognizing only the classes annotated in the training dataset and failing when encountering novel objects. Open-World Object Detection (OWOD) relaxes this assumption by…

计算机视觉与模式识别 · 计算机科学 2026-03-09 Yuchen Zhang , Yao Lu , Johannes Betz

Object detection methods trained on a fixed set of known classes struggle to detect objects of unknown classes in the open-world setting. Current fixes involve adding approximate supervision with pseudo-labels corresponding to candidate…

计算机视觉与模式识别 · 计算机科学 2024-10-11 Mısra Yavuz , Fatma Güney

Autonomous systems rely on accurate 3D object detection from LiDAR data, yet most detectors are limited to a predefined set of known classes, making them vulnerable to unexpected out-of-distribution (OOD) objects. In this work, we present…

计算机视觉与模式识别 · 计算机科学 2025-09-16 Louis Soum-Fontez , Jean-Emmanuel Deschaud , François Goulette

Humans have a natural instinct to identify unknown object instances in their environments. The intrinsic curiosity about these unknown instances aids in learning about them, when the corresponding knowledge is eventually available. This…

计算机视觉与模式识别 · 计算机科学 2021-05-11 K J Joseph , Salman Khan , Fahad Shahbaz Khan , Vineeth N Balasubramanian

Marine object detection has gained prominence in marine research, driven by the pressing need to unravel oceanic mysteries and enhance our understanding of invaluable marine ecosystems. There is a profound requirement to efficiently and…

计算机视觉与模式识别 · 计算机科学 2023-10-04 Liang Haixin , Zheng Ziqiang , Ma Zeyu , Sai-Kit Yeung

A more realistic object detection paradigm, Open-World Object Detection, has arisen increasing research interests in the community recently. A qualified open-world object detector can not only identify objects of known categories, but also…

计算机视觉与模式识别 · 计算机科学 2022-02-17 Shuo Yang , Peize Sun , Yi Jiang , Xiaobo Xia , Ruiheng Zhang , Zehuan Yuan , Changhu Wang , Ping Luo , Min Xu

Open-World Object Detection (OWOD) enriches traditional object detectors by enabling continual discovery and integration of unknown objects via human guidance. However, existing OWOD approaches frequently suffer from semantic confusion…

计算机视觉与模式识别 · 计算机科学 2025-10-02 Anay Majee , Amitesh Gangrade , Rishabh Iyer

Open-world object detection (OWOD) requires incrementally detecting known categories while reliably identifying unknown objects. Existing methods primarily focus on improving unknown recall, yet overlook interpretability, often leading to…

计算机视觉与模式识别 · 计算机科学 2026-02-25 Xueqiang Lv , Shizhou Zhang , Yinghui Xing , Di Xu , Peng Wang , Yanning Zhang

Autonomous vehicles that navigate in open-world environments may encounter previously unseen object classes. However, most existing LiDAR panoptic segmentation models rely on closed-set assumptions, failing to detect unknown object…

计算机视觉与模式识别 · 计算机科学 2025-09-04 Rohit Mohan , Julia Hindel , Florian Drews , Claudius Gläser , Daniele Cattaneo , Abhinav Valada

Open set recognition (OSR) is a critical aspect of machine learning, addressing the challenge of detecting novel classes during inference. Within the realm of deep learning, neural classifiers trained on a closed set of data typically…

计算机视觉与模式识别 · 计算机科学 2026-05-05 Jiawen Xu , Margret Keuper

Real-world object detection must operate in evolving environments where new classes emerge, domains shift, and unseen objects must be identified as "unknown": all without accessing prior data. We introduce Evolving World Object Detection…

计算机视觉与模式识别 · 计算机科学 2026-04-03 Munish Monga , Vishal Chudasama , Pankaj Wasnik , C. V. Jawahar

Semantic segmentation is a key technique that enables mobile robots to understand and navigate surrounding environments autonomously. However, most existing works focus on segmenting known objects, overlooking the identification of unknown…

计算机视觉与模式识别 · 计算机科学 2025-03-17 Wenbang Deng , Xieyuanli Chen , Qinghua Yu , Yunze He , Junhao Xiao , Huimin Lu

Robustness is a fundamental aspect for developing safe and trustworthy models, particularly when they are deployed in the open world. In this work we analyze the inherent capability of one-stage object detectors to robustly operate in the…

计算机视觉与模式识别 · 计算机科学 2025-02-06 Aitor Martinez-Seras , Javier Del Ser , Aitzol Olivares-Rad , Alain Andres , Pablo Garcia-Bringas