English
Related papers

Related papers: Evaluating Large-Vocabulary Object Detectors: The …

200 papers

Image retrieval can be formulated as a ranking problem where the goal is to order database images by decreasing similarity to the query. Recent deep models for image retrieval have outperformed traditional methods by leveraging…

Computer Vision and Pattern Recognition · Computer Science 2019-06-19 Jerome Revaud , Jon Almazan , Rafael Sampaio de Rezende , Cesar Roberto de Souza

Existing object detection methods are bounded in a fixed-set vocabulary by costly labeled data. When dealing with novel categories, the model has to be retrained with more bounding box annotations. Natural language supervision is an…

Computer Vision and Pattern Recognition · Computer Science 2022-11-29 Chuang Lin , Peize Sun , Yi Jiang , Ping Luo , Lizhen Qu , Gholamreza Haffari , Zehuan Yuan , Jianfei Cai

An examination of object recognition challenge leaderboards (ILSVRC, PASCAL-VOC) reveals that the top-performing classifiers typically exhibit small differences amongst themselves in terms of error rate/mAP. To better differentiate the top…

Computer Vision and Pattern Recognition · Computer Science 2016-11-28 Ravi Kiran Sarvadevabhatla , Shanthakumar Venkatraman , R. Venkatesh Babu

Do you want to improve 1.0 AP for your object detector without any inference cost and any change to your detector? Let us tell you such a recipe. It is surprisingly simple: train your detector for an extra 12 epochs using cyclical learning…

Computer Vision and Pattern Recognition · Computer Science 2021-03-15 Haoyang Zhang , Ying Wang , Feras Dayoub , Niko Sünderhauf

Currently, the state-of-the-art image classification algorithms outperform the best available object detector by a big margin in terms of average precision. We, therefore, propose a simple yet principled approach that allows us to leverage…

Computer Vision and Pattern Recognition · Computer Science 2016-04-08 Miao Sun , Tony X. Han , Zhihai He

The 2D object detection in clean images has been a well studied topic, but its vulnerability against adversarial attack is still worrying. Existing work has improved robustness of object detectors by adversarial training, at the same time,…

Computer Vision and Pattern Recognition · Computer Science 2021-08-27 Weipeng Xu , Hongcheng Huang , Shaoyou Pan

A fundamental limitation of object detectors is that they suffer from "spatial bias", and in particular perform less satisfactorily when detecting objects near image borders. For a long time, there has been a lack of effective ways to…

Computer Vision and Pattern Recognition · Computer Science 2024-06-04 Zhaohui Zheng , Yuming Chen , Qibin Hou , Xiang Li , Ping Wang , Ming-Ming Cheng

We introduce Probabilistic Object Detection, the task of detecting objects in images and accurately quantifying the spatial and semantic uncertainties of the detections. Given the lack of methods capable of assessing such probabilistic…

Computer Vision and Pattern Recognition · Computer Science 2020-01-31 David Hall , Feras Dayoub , John Skinner , Haoyang Zhang , Dimity Miller , Peter Corke , Gustavo Carneiro , Anelia Angelova , Niko Sünderhauf

Correctness of instance segmentation constitutes counting the number of objects, correctly localizing all predictions and classifying each localized prediction. Average Precision is the de-facto metric used to measure all these constituents…

Computer Vision and Pattern Recognition · Computer Science 2023-03-21 Rohit Jena , Lukas Zhornyak , Nehal Doiphode , Pratik Chaudhari , Vivek Buch , James Gee , Jianbo Shi

Object detectors often experience a drop in performance when new environmental conditions are insufficiently represented in the training data. This paper studies how to automatically fine-tune a pre-existing object detector while exploring…

Computer Vision and Pattern Recognition · Computer Science 2023-02-22 Gianluca Scarpellini , Stefano Rosa , Pietro Morerio , Lorenzo Natale , Alessio Del Bue

Mean Average Precision (mAP) is the primary evaluation measure for object detection. Although object detection has a broad range of applications, mAP evaluates detectors in terms of the performance of ranked instance retrieval. Such the…

Computer Vision and Pattern Recognition · Computer Science 2022-03-29 Mayu Otani , Riku Togashi , Yuta Nakashima , Esa Rahtu , Janne Heikkilä , Shin'ichi Satoh

Probabilities or confidence values produced by artificial intelligence (AI) and machine learning (ML) models often do not reflect their true accuracy, with some models being under or over confident in their predictions. For example, if a…

Machine Learning · Computer Science 2025-04-28 Richard Oliver Lane

Vision-language models (VLMs) offer flexible object detection through natural language prompts but suffer from performance variability depending on prompt phrasing. In this paper, we introduce a method for automated prompt refinement using…

Computer Vision and Pattern Recognition · Computer Science 2025-05-15 Lucas Choi , Ross Greer

High-accuracy and low-latency 3D object detection is essential for autonomous driving systems. While previous studies on 3D object detection often evaluate performance based on mean average precision (mAP) and latency, they typically fail…

Robotics · Computer Science 2025-07-02 Satoshi Tanaka , Koji Minoda , Fumiya Watanabe , Takamasa Horibe

Designing metrics for evaluating instance segmentation revolves around comprehensively considering object detection and segmentation accuracy. However, other important properties, such as sensitivity, continuity, and equality, are…

Computer Vision and Pattern Recognition · Computer Science 2023-09-12 Long Chen , Yuli Wu , Johannes Stegmaier , Dorit Merhof

Open-vocabulary object detection (OVOD) aims at localizing and recognizing visual objects from novel classes unseen at the training time. Whereas, empirical studies reveal that advanced detectors generally assign lower scores to those novel…

Computer Vision and Pattern Recognition · Computer Science 2024-04-15 Yanhao Zheng , Kai Liu

Recent object detection and instance segmentation tasks mainly focus on datasets with a relatively small set of categories, e.g. Pascal VOC with 20 classes and COCO with 80 classes. The new large vocabulary dataset LVIS brings new…

Computer Vision and Pattern Recognition · Computer Science 2019-11-13 Jingru Tan , Changbao Wang , Quanquan Li , Junjie Yan

Despite great progress in object detection, most existing methods work only on a limited set of object categories, due to the tremendous human effort needed for bounding-box annotations of training data. To alleviate the problem, recent…

Computer Vision and Pattern Recognition · Computer Science 2022-07-14 Mingfei Gao , Chen Xing , Juan Carlos Niebles , Junnan Li , Ran Xu , Wenhao Liu , Caiming Xiong

Annotation errors are a challenge not only during training of machine learning models, but also during their evaluation. Label variations and inaccuracies in datasets often manifest as contradictory examples that deviate from established…

Computer Vision and Pattern Recognition · Computer Science 2025-01-23 David Tschirschwitz , Volker Rodehorst

Object detection has been expanded from a limited number of categories to open vocabulary. Moving forward, a complete intelligent vision system requires understanding more fine-grained object descriptions, object parts. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2023-05-19 Peize Sun , Shoufa Chen , Chenchen Zhu , Fanyi Xiao , Ping Luo , Saining Xie , Zhicheng Yan