English
Related papers

Related papers: Hyp2Former: Hierarchy-Aware Hyperbolic Embeddings …

200 papers

Open-vocabulary image segmentation aims to partition an image into semantic regions according to arbitrary text descriptions. However, complex visual scenes can be naturally decomposed into simpler parts and abstracted at multiple levels of…

Computer Vision and Pattern Recognition · Computer Science 2023-12-22 Xudong Wang , Shufan Li , Konstantinos Kallidromitis , Yusuke Kato , Kazuki Kozuka , Trevor Darrell

Open-vocabulary object detection (OVD) aims to detect objects beyond the training annotations, where detectors are usually aligned to a pre-trained vision-language model, eg, CLIP, to inherit its generalizable recognition ability so that…

Computer Vision and Pattern Recognition · Computer Science 2025-03-14 Shenghao Fu , Junkai Yan , Qize Yang , Xihan Wei , Xiaohua Xie , Wei-Shi Zheng

Machine learning-based techniques open up many opportunities and improvements to derive deeper and more practical insights from data that can help businesses make informed decisions. However, the majority of these techniques focus on the…

Machine Learning · Computer Science 2024-05-10 Atefeh Mahdavi , Marco Carvalho

Recent advancements in deep learning have greatly enhanced 3D object recognition, but most models are limited to closed-set scenarios, unable to handle unknown samples in real-world applications. Open-set recognition (OSR) addresses this…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Jinfeng Xu , Xianzhi Li , Yuan Tang , Xu Han , Qiao Yu , Yixue Hao , Long Hu , Min Chen

Interpreting camera data is key for autonomously acting systems, such as autonomous vehicles. Vision systems that operate in real-world environments must be able to understand their surroundings and need the ability to deal with novel…

Computer Vision and Pattern Recognition · Computer Science 2024-03-13 Matteo Sodano , Federico Magistri , Lucas Nunes , Jens Behley , Cyrill Stachniss

Open-Vocabulary Semantic Segmentation (OVSS) has advanced with recent vision-language models (VLMs), enabling segmentation beyond predefined categories through various learning schemes. Notably, training-free methods offer scalable, easily…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Chanyoung Kim , Dayun Ju , Woojung Han , Ming-Hsuan Yang , Seong Jae Hwang

This paper presents a novel data-driven hierarchical approach to open set recognition (OSR) for robust perception in robotics and computer vision, utilizing constrained agglomerative clustering to automatically build a hierarchy of known…

Computer Vision and Pattern Recognition · Computer Science 2024-11-06 Andrew Hannum , Max Conway , Mario Lopez , André Harrison

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…

Computer Vision and Pattern Recognition · Computer Science 2026-02-25 Xueqiang Lv , Shizhou Zhang , Yinghui Xing , Di Xu , Peng Wang , Yanning Zhang

Deep neural networks have achieved impressive success in large-scale visual object recognition tasks with a predefined set of classes. However, recognizing objects of novel classes unseen during training still remains challenging. The…

Computer Vision and Pattern Recognition · Computer Science 2018-06-18 Kibok Lee , Kimin Lee , Kyle Min , Yuting Zhang , Jinwoo Shin , Honglak Lee

Object segmentation requires both object-level information and low-level pixel data. This presents a challenge for feedforward networks: lower layers in convolutional nets capture rich spatial information, while upper layers encode…

Computer Vision and Pattern Recognition · Computer Science 2016-07-28 Pedro O. Pinheiro , Tsung-Yi Lin , Ronan Collobert , Piotr Dollàr

Deep learning has led to remarkable strides in scene understanding with panoptic segmentation emerging as a key holistic scene interpretation task. However, the performance of panoptic segmentation is severely impacted in the presence of…

Computer Vision and Pattern Recognition · Computer Science 2023-10-19 Rohit Mohan , Kiran Kumaraswamy , Juana Valeria Hurtado , Kürsat Petek , Abhinav Valada

Semantic segmentation (SS) aims to classify each pixel into one of the pre-defined classes. This task plays an important role in self-driving cars and autonomous drones. In SS, many works have shown that most misclassified pixels are…

Computer Vision and Pattern Recognition · Computer Science 2023-05-29 Bike Chen , Wei Peng , Xiaofeng Cao , Juha Röning

Unsupervised object discovery aims to localize objects in images, while removing the dependence on annotations required by most deep learning-based methods. To address this problem, we propose a fully unsupervised, bottom-up approach, for…

Computer Vision and Pattern Recognition · Computer Science 2022-12-21 Sandra Kara , Hejer Ammar , Florian Chabot , Quoc-Cuong Pham

Traditional object detection methods operate under the closed-set assumption, where models can only detect a fixed number of objects predefined in the training set. Recent works on open vocabulary object detection (OVD) enable the detection…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Zizhao Li , Zhengkang Xiang , Joseph West , Kourosh Khoshelham

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…

Computer Vision and Pattern Recognition · Computer Science 2025-09-16 Louis Soum-Fontez , Jean-Emmanuel Deschaud , François Goulette

Detecting the openable parts of articulated objects is crucial for downstream applications in intelligent robotics, such as pulling a drawer. This task poses a multitasking challenge due to the necessity of understanding object categories…

Computer Vision and Pattern Recognition · Computer Science 2024-12-18 Siqi Li , Xiaoxue Chen , Haoyu Cheng , Guyue Zhou , Hao Zhao , Guanzhong Tian

Object manipulation requires accurate object pose estimation. In open environments, robots encounter unknown objects, which requires semantic understanding in order to generalize both to known categories and beyond. To resolve this…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Peter Hönig , Stefan Thalhammer , Jean-Baptiste Weibel , Matthias Hirschmanner , Markus Vincze

While today's robots are able to perform sophisticated tasks, they can only act on objects they have been trained to recognize. This is a severe limitation: any robot will inevitably see new objects in unconstrained settings, and thus will…

Robotics · Computer Science 2019-06-05 Massimiliano Mancini , Hakan Karaoguz , Elisa Ricci , Patric Jensfelt , Barbara Caputo

State-of-the-art Object Detection (OD) methods predominantly operate under a closed-world assumption, where test-time categories match those encountered during training. However, detecting and localizing unknown objects is crucial for…

Computer Vision and Pattern Recognition · Computer Science 2025-06-18 Daniel Montoya , Aymen Bouguerra , Alexandra Gomez-Villa , Fabio Arnez

Most real-world datasets consist of a natural hierarchy between classes or an inherent label structure that is either already available or can be constructed cheaply. However, most existing representation learning methods ignore this…

Machine Learning · Computer Science 2024-12-03 Aditya Sinha , Siqi Zeng , Makoto Yamada , Han Zhao