English
Related papers

Related papers: Bridging the Gap Between Anchor-based and Anchor-f…

200 papers

Visual object tracking is an important application of computer vision. Recently, Siamese based trackers have achieved good accuracy. However, most of Siamese based trackers are not efficient, as they exhaustively search potential object…

Computer Vision and Pattern Recognition · Computer Science 2020-06-16 Shengyun Peng , Yunxuan Yu , Kun Wang , Lei He

Contrastive learning is commonly used as a method of self-supervised learning with the "anchor" and "positive" being two random augmentations of a given input image, and the "negative" is the set of all other images. However, the…

Computer Vision and Pattern Recognition · Computer Science 2022-08-16 Rishab Balasubramanian , Kunal Rathore

Though quite challenging, leveraging large-scale unlabeled or partially labeled data in learning systems (e.g., model/classifier training) has attracted increasing attentions due to its fundamental importance. To address this problem, many…

Computer Vision and Pattern Recognition · Computer Science 2019-01-15 Keze Wang , Liang Lin , Xiaopeng Yan , Ziliang Chen , Dongyu Zhang , Lei Zhang

Semi-supervised object detection (SSOD) aims to facilitate the training and deployment of object detectors with the help of a large amount of unlabeled data. Though various self-training based and consistency-regularization based SSOD…

Computer Vision and Pattern Recognition · Computer Science 2022-04-18 Binghui Chen , Pengyu Li , Xiang Chen , Biao Wang , Lei Zhang , Xian-Sheng Hua

Pedestrian detection benefits from deep learning technology and gains rapid development in recent years. Most of detectors follow general object detection frame, i.e. default boxes and two-stage process. Recently, anchor-free and one-stage…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Wenhao Wang , Jusheng Zhang

Most existing object detectors suffer from class imbalance problems that hinder balanced performance. In particular, anchor free object detectors have to solve the background imbalance problem due to detection in a per-pixel prediction…

Computer Vision and Pattern Recognition · Computer Science 2020-12-29 Hopyong Gil , Sangwoo Park , Yusang Park , Wongoo Han , Juyean Hong , Juneyoung Jung

In this paper, we aim to improve the performance of a deep learning model towards image classification tasks, proposing a novel anchor-based training methodology, named \textit{Online Anchor-based Training} (OAT). The OAT method, guided by…

Computer Vision and Pattern Recognition · Computer Science 2024-06-19 Maria Tzelepi , Vasileios Mezaris

State-of-the-art object detection systems rely on an accurate set of region proposals. Several recent methods use a neural network architecture to hypothesize promising object locations. While these approaches are computationally efficient,…

Computer Vision and Pattern Recognition · Computer Science 2016-04-12 Yongxi Lu , Tara Javidi , Svetlana Lazebnik

This paper presents adaptive conformal selection (ACS), an interactive framework for model-free selection with guaranteed error control. Building on conformal selection (Jin and Cand\`es, 2023b), ACS generalizes the approach to support…

Methodology · Statistics 2025-07-22 Yu Gui , Ying Jin , Yash Nair , Zhimei Ren

Incremental learning requires a model to continually learn new tasks from streaming data. However, traditional fine-tuning of a well-trained deep neural network on a new task will dramatically degrade performance on the old task -- a…

Computer Vision and Pattern Recognition · Computer Science 2021-01-01 Can Peng , Kun Zhao , Sam Maksoud , Meng Li , Brian C. Lovell

Current anchor-free object detectors label all the features that spatially fall inside a predefined central region of a ground-truth box as positive. This approach causes label noise during training, since some of these positively labeled…

Computer Vision and Pattern Recognition · Computer Science 2020-08-17 Nermin Samet , Samet Hicsonmez , Emre Akbas

Label assignment plays a significant role in modern object detection models. Detection models may yield totally different performances with different label assignment strategies. For anchor-based detection models, the IoU (Intersection over…

Computer Vision and Pattern Recognition · Computer Science 2022-09-20 Tianxiao Zhang , Bo Luo , Ajay Sharda , Guanghui Wang

Existing anchor-base oriented object detection methods have achieved amazing results, but these methods require some manual preset boxes, which introduces additional hyperparameters and calculations. The existing anchor-free methods usually…

Computer Vision and Pattern Recognition · Computer Science 2021-12-02 Zhonghua Li , Biao Hou , Zitong Wu , Licheng Jiao , Bo Ren , Chen Yang

It is a common practice to exploit pyramidal feature representation to tackle the problem of scale variation in object instances. However, most of them still predict the objects in a certain range of scales based solely or mainly on a…

Computer Vision and Pattern Recognition · Computer Science 2020-12-10 Zehui Gong , Dong Li

Deep Metric Learning (DML) serves to learn an embedding function to project semantically similar data into nearby embedding space and plays a vital role in many applications, such as image retrieval and face recognition. However, the…

Computer Vision and Pattern Recognition · Computer Science 2022-08-02 Lizhao Liu , Shangxin Huang , Zhuangwei Zhuang , Ran Yang , Mingkui Tan , Yaowei Wang

State-of-the-art object detectors rely on regressing and classifying an extensive list of possible anchors, which are divided into positive and negative samples based on their intersection-over-union (IoU) with corresponding groundtruth…

Computer Vision and Pattern Recognition · Computer Science 2020-06-01 Hengduo Li , Zuxuan Wu , Chen Zhu , Caiming Xiong , Richard Socher , Larry S. Davis

Discriminative features are critical for machine learning applications. Most existing deep learning approaches, however, rely on convolutional neural networks (CNNs) for learning features, whose discriminant power is not explicitly…

Computer Vision and Pattern Recognition · Computer Science 2018-04-24 Fusheng Hao , Jun Cheng , Lei Wang , Xinchao Wang , Jianzhong Cao , Xiping Hu , Dapeng Tao

Modern object detectors rely heavily on rectangular bounding boxes, such as anchors, proposals and the final predictions, to represent objects at various recognition stages. The bounding box is convenient to use but provides only a coarse…

Computer Vision and Pattern Recognition · Computer Science 2019-08-20 Ze Yang , Shaohui Liu , Han Hu , Liwei Wang , Stephen Lin

During the last years, we have seen significant advances in the object detection task, mainly due to the outperforming results of convolutional neural networks. In this vein, anchor-based models have achieved the best results. However,…

Computer Vision and Pattern Recognition · Computer Science 2023-09-06 Lukas Pavez , Jose M. Saavedra Rondo

Anchor-free detectors basically formulate object detection as dense classification and regression. For popular anchor-free detectors, it is common to introduce an individual prediction branch to estimate the quality of localization. The…

Computer Vision and Pattern Recognition · Computer Science 2022-09-30 Hu Su , Yonghao He , Rui Jiang , Jiabin Zhang , Wei Zou , Bin Fan