English
Related papers

Related papers: Bootstrap Your Object Detector via Mixed Training

200 papers

Object detectors tend to perform poorly in new or open domains, and require exhaustive yet costly annotations from fully labeled datasets. We aim at benefiting from several datasets with different categories but without additional…

Computer Vision and Pattern Recognition · Computer Science 2019-03-26 Alexandre Rame , Emilien Garreau , Hedi Ben-Younes , Charles Ollion

The ImageNet pre-training initialization is the de-facto standard for object detection. He et al. found it is possible to train detector from scratch(random initialization) while needing a longer training schedule with proper normalization…

Computer Vision and Pattern Recognition · Computer Science 2021-06-08 Yang Li , Hong Zhang , Yu Zhang

Recent strategies achieved ensembling "for free" by fitting concurrently diverse subnetworks inside a single base network. The main idea during training is that each subnetwork learns to classify only one of the multiple inputs…

Machine Learning · Computer Science 2021-08-25 Alexandre Rame , Remy Sun , Matthieu Cord

Object detection is a fundamental task for robots to operate in unstructured environments. Today, there are several deep learning algorithms that solve this task with remarkable performance. Unfortunately, training such systems requires…

Computer Vision and Pattern Recognition · Computer Science 2021-06-30 Federico Ceola , Elisa Maiettini , Giulia Pasquale , Lorenzo Rosasco , Lorenzo Natale

Current state-of-the-art object objectors are fine-tuned from the off-the-shelf networks pretrained on large-scale classification dataset ImageNet, which incurs some additional problems: 1) The classification and detection have different…

Computer Vision and Pattern Recognition · Computer Science 2019-05-07 Rui Zhu , Shifeng Zhang , Xiaobo Wang , Longyin Wen , Hailin Shi , Liefeng Bo , Tao Mei

Multiple object tracking (MOT) depends heavily on selection of true positive detected bounding boxes. However, this aspect of the problem is mostly overlooked or mitigated by employing two-stage association and utilizing low confidence…

Computer Vision and Pattern Recognition · Computer Science 2025-12-25 Vukašin Stanojević , Branimir Todorović

Usually, Neural Networks models are trained with a large dataset of images in homogeneous backgrounds. The issue is that the performance of the network models trained could be significantly degraded in a complex and heterogeneous…

Computer Vision and Pattern Recognition · Computer Science 2020-03-02 Vinorth Varatharasan , Hyo-Sang Shin , Antonios Tsourdos , Nick Colosimo

Deep SORT\cite{wojke2017simple} is a tracking-by-detetion approach to multiple object tracking with a detector and a RE-ID model. Both separately training and inference with the two model is time-comsuming. In this paper, we unify the…

Computer Vision and Pattern Recognition · Computer Science 2019-07-09 Yuhao Xu , Jiakui Wang

While pre-training on object detection tasks, such as Common Objects in Contexts (COCO) [1], could significantly boost the performance of cell segmentation, it still consumes on massive fine-annotated cell images [2] with bounding boxes,…

Computer Vision and Pattern Recognition · Computer Science 2023-10-09 Weibin Liao , Xuhong Li , Qingzhong Wang , Yanwu Xu , Zhaozheng Yin , Haoyi Xiong

Automatic X-ray prohibited item detection is vital for public safety. Existing deep learning-based methods all assume that the annotations of training X-ray images are correct. However, obtaining correct annotations is extremely hard if not…

Computer Vision and Pattern Recognition · Computer Science 2025-01-06 Ruikang Chen , Yan Yan , Jing-Hao Xue , Yang Lu , Hanzi Wang

Training with sparse annotations is known to reduce the performance of object detectors. Previous methods have focused on proxies for missing ground truth annotations in the form of pseudo-labels for unlabeled boxes. We observe that…

Computer Vision and Pattern Recognition · Computer Science 2023-08-29 Saksham Suri , Sai Saketh Rambhatla , Rama Chellappa , Abhinav Shrivastava

We propose a novel and flexible anchor mechanism named MetaAnchor for object detection frameworks. Unlike many previous detectors model anchors via a predefined manner, in MetaAnchor anchor functions could be dynamically generated from the…

Computer Vision and Pattern Recognition · Computer Science 2018-11-07 Tong Yang , Xiangyu Zhang , Zeming Li , Wenqiang Zhang , Jian Sun

Supervised 3D Object Detection models have been displaying increasingly better performance in single-domain cases where the training data comes from the same environment and sensor as the testing data. However, in real-world scenarios data…

Computer Vision and Pattern Recognition · Computer Science 2023-08-03 Louis Soum-Fontez , Jean-Emmanuel Deschaud , François Goulette

Top-performing computer vision models are powered by convolutional neural networks (CNNs). Training an accurate CNN highly depends on both the raw sensor data and their associated ground truth (GT). Collecting such GT is usually done…

Computer Vision and Pattern Recognition · Computer Science 2021-05-05 Jose L. Gómez , Gabriel Villalonga , Antonio M. López

Nowadays, Semi-Supervised Object Detection (SSOD) is a hot topic, since, while it is rather easy to collect images for creating a new dataset, labeling them is still an expensive and time-consuming task. One of the successful methods to…

Computer Vision and Pattern Recognition · Computer Science 2022-06-22 Leonardo Rossi , Akbar Karimi , Andrea Prati

This paper improves state-of-the-art visual object trackers that use online adaptation. Our core contribution is an offline meta-learning-based method to adjust the initial deep networks used in online adaptation-based tracking. The meta…

Computer Vision and Pattern Recognition · Computer Science 2018-03-21 Eunbyung Park , Alexander C. Berg

The performance of a model trained with noisy labels is often improved by simply \textit{retraining} the model with its \textit{own predicted hard labels} (i.e., 1/0 labels). Yet, a detailed theoretical characterization of this phenomenon…

We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance. The…

Computer Vision and Pattern Recognition · Computer Science 2018-01-25 Kaiming He , Georgia Gkioxari , Piotr Dollár , Ross Girshick

The application of cross-dataset training in object detection tasks is complicated because the inconsistency in the category range across datasets transforms fully supervised learning into semi-supervised learning. To address this problem,…

Computer Vision and Pattern Recognition · Computer Science 2022-04-04 Ze Chen , Zhihang Fu , Jianqiang Huang , Mingyuan Tao , Shengyu Li , Rongxin Jiang , Xiang Tian , Yaowu Chen , Xian-sheng Hua

One of the most important factors in training object recognition networks using convolutional neural networks (CNNs) is the provision of annotated data accompanying human judgment. Particularly, in object detection or semantic segmentation,…

Computer Vision and Pattern Recognition · Computer Science 2018-02-21 Min-Kook Choi , Jaehyeong Park , Jihun Jung , Heechul Jung , Jin-Hee Lee , Woong Jae Won , Woo Young Jung , Jincheol Kim , Soon Kwon
‹ Prev 1 3 4 5 6 7 10 Next ›