English
Related papers

Related papers: Rethinking the backbone architecture for tiny obje…

200 papers

Most object detection frameworks use backbone architectures originally designed for image classification, conventionally with pre-trained parameters on ImageNet. However, image classification and object detection are essentially different…

Computer Vision and Pattern Recognition · Computer Science 2022-06-20 Harim Jung , Myeong-Seok Oh , Cheoljong Yang , Seong-Whan Lee

Recent advancements in LiDAR-based 3D object detection have significantly accelerated progress toward the realization of fully autonomous driving in real-world environments. Despite achieving high detection performance, most of the…

Computer Vision and Pattern Recognition · Computer Science 2025-10-23 Adwait Chandorkar , Hasan Tercan , Tobias Meisen

General object detectors use powerful backbones that uniformly extract features from images for enabling detection of a vast amount of object types. However, utilization of such backbones in object detection applications developed for…

Computer Vision and Pattern Recognition · Computer Science 2021-08-04 Alexandra Dana , Maor Shutman , Yotam Perlitz , Ran Vitek , Tomer Peleg , Roy J Jevnisek

Many real-world applications require recognition models that are robust to different operational conditions and modalities, but at the same time run on small embedded devices, with limited hardware. While for normal size models,…

Computer Vision and Pattern Recognition · Computer Science 2026-01-21 Srikanth Muralidharan , Heitor R. Medeiros , Masih Aminbeidokhti , Eric Granger , Marco Pedersoli

Though tremendous strides have been made in object recognition, one of the remaining open challenges is detecting small objects. We explore three aspects of the problem in the context of finding small faces: the role of scale invariance,…

Computer Vision and Pattern Recognition · Computer Science 2017-04-18 Peiyun Hu , Deva Ramanan

In contemporary computer vision applications, particularly image classification, architectural backbones pre-trained on large datasets like ImageNet are commonly employed as feature extractors. Despite the widespread use of these…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Pranav Jeevan , Amit Sethi

Object Detection is the task of classification and localization of objects in an image or video. It has gained prominence in recent years due to its widespread applications. This article surveys recent developments in deep learning based…

Computer Vision and Pattern Recognition · Computer Science 2021-05-13 Syed Sahil Abbas Zaidi , Mohammad Samar Ansari , Asra Aslam , Nadia Kanwal , Mamoona Asghar , Brian Lee

Recent CNN based object detectors, no matter one-stage methods like YOLO, SSD, and RetinaNe or two-stage detectors like Faster R-CNN, R-FCN and FPN are usually trying to directly finetune from ImageNet pre-trained models designed for image…

Computer Vision and Pattern Recognition · Computer Science 2018-04-20 Zeming Li , Chao Peng , Gang Yu , Xiangyu Zhang , Yangdong Deng , Jian Sun

A common practice in transfer learning is to initialize the downstream model weights by pre-training on a data-abundant upstream task. In object detection specifically, the feature backbone is typically initialized with Imagenet classifier…

Computer Vision and Pattern Recognition · Computer Science 2022-06-28 Cristina Vasconcelos , Vighnesh Birodkar , Vincent Dumoulin

Object detectors are usually equipped with backbone networks designed for image classification. It might be sub-optimal because of the gap between the tasks of image classification and object detection. In this work, we present DetNAS to…

Computer Vision and Pattern Recognition · Computer Science 2020-01-01 Yukang Chen , Tong Yang , Xiangyu Zhang , Gaofeng Meng , Xinyu Xiao , Jian Sun

Recently, Neural architecture search has achieved great success on classification tasks for mobile devices. The backbone network for object detection is usually obtained on the image classification task. However, the architecture which is…

Computer Vision and Pattern Recognition · Computer Science 2022-11-08 Haichao Zhang , Jiashi Li , Xin Xia , Kuangrong Hao , Xuefeng Xiao

Tiny object detection has gained considerable attention in the research community owing to the frequent occurrence of tiny objects in numerous critical real-world scenarios. However, convolutional neural networks (CNNs) used as the backbone…

Computer Vision and Pattern Recognition · Computer Science 2023-10-24 Jinlai Ning , Michael Spratling

This paper shows the effectiveness of 2D backbone scaling and pretraining for pillar-based 3D object detectors. Pillar-based methods mainly employ randomly initialized 2D convolution neural network (ConvNet) for feature extraction and fail…

Computer Vision and Pattern Recognition · Computer Science 2023-11-30 Weixin Mao , Tiancai Wang , Diankun Zhang , Junjie Yan , Osamu Yoshie

Visual object detection has achieved unprecedented ad-vance with the rise of deep convolutional neural networks.However, detecting tiny objects (for example tiny per-sons less than 20 pixels) in large-scale images remainsnot well…

Computer Vision and Pattern Recognition · Computer Science 2019-12-24 Xuehui Yu , Yuqi Gong , Nan Jiang , Qixiang Ye , Zhenjun Han

The task of detecting 3D objects in traffic scenes has a pivotal role in many real-world applications. However, the performance of 3D object detection is lower than that of 2D object detection due to the lack of powerful 3D feature…

Computer Vision and Pattern Recognition · Computer Science 2019-09-17 Xuesong Li , Jose Guivant , Ngaiming Kwok , Yongzhi Xu , Ruowei Li , Hongkun Wu

In conventional object detection frameworks, a backbone body inherited from image recognition models extracts deep latent features and then a neck module fuses these latent features to capture information at different scales. As the…

Computer Vision and Pattern Recognition · Computer Science 2022-06-23 Yiqi Jiang , Zhiyu Tan , Junyan Wang , Xiuyu Sun , Ming Lin , Hao Li

Transformers have become the dominant model in natural language processing, owing to their ability to pretrain on massive amounts of data, then transfer to smaller, more specific tasks via fine-tuning. The Vision Transformer was the first…

Computer Vision and Pattern Recognition · Computer Science 2020-12-21 Josh Beal , Eric Kim , Eric Tzeng , Dong Huk Park , Andrew Zhai , Dmitry Kislyuk

While object detection is a common problem in computer vision, it is even more challenging when dealing with aerial satellite images. The variety in object scales and orientations can make them difficult to identify. In addition, there can…

Computer Vision and Pattern Recognition · Computer Science 2022-02-08 Ahmed Elhagry , Mohamed Saeed

An increasing number of applications in computer vision, specially, in medical imaging and remote sensing, become challenging when the goal is to classify very large images with tiny informative objects. Specifically, these classification…

Computer Vision and Pattern Recognition · Computer Science 2021-12-07 Fanjie Kong , Ricardo Henao

The main challenge for small object detection algorithms is to ensure accuracy while pursuing real-time performance. The RT-DETR model performs well in real-time object detection, but performs poorly in small object detection accuracy. In…

Computer Vision and Pattern Recognition · Computer Science 2024-01-17 Ji Huang , Hui Wang
‹ Prev 1 2 3 10 Next ›