paper-with-me

Papers

Deeply Unsupervised Patch Re-Identification for Pre-training Object Detectors

2021-03-08 · Jian Ding, Enze Xie, Hang Xu, Chenhan Jiang, Zhenguo Li, Ping Luo, Gui-Song Xia

Unsupervised pre-training aims at learning transferable features that are beneficial for downstream tasks. However, most state-of-the-art unsupervised methods concentrate on learning global representations for image-level classification tasks instead of discriminative local region representations, which limits their transferability to region-level downstream tasks, such as object detection. To improve the transferability of pre-trained features to object detection, we present Deeply Unsupervised Patch Re-ID (DUPR), a simple yet effective method for unsupervised visual representation learning. The patch Re-ID task treats individual patch as a pseudo-identity and contrastively learns its correspondence in two views, enabling us to obtain discriminative local features for object detection. Then the proposed patch Re-ID is performed in a deeply unsupervised manner, appealing to object detection, which usually requires multilevel feature maps. Extensive experiments demonstrate that DUPR outperforms state-of-the-art unsupervised pre-trainings and even the ImageNet supervised pre-training on various downstream tasks related to object detection.

📄 PDF Abstract BibTeX arXiv:2103.04814

Code (0)

등록된 구현이 없습니다.

Tasks

Objectobject-detectionObject DetectionRepresentation LearningUnsupervised Pre-training

Methods 이 논문이 사용한 방법론

RPN A Region Proposal Network, or RPN, is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Random Gaussian Blur Random Gaussian Blur is an image data augmentation technique where we randomly blur the image using a Gaussian distribution. Image Source:…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Batch Normalization 설명 없음
MoCo 설명 없음

Similar Papers 제목 키워드 기반

Short Range Correlation Transformer for Occluded Person Re-Identification

2022-01-04 · Yunbin Zhao, Songhao Zhu, Dongsheng Wang, Zhiwei Liang

Occluded person re-identification is one of the challenging areas of computer vision, which faces problems such as inefficient feature representation and low recognition accuracy. Convolutional neural network pays more a…

Occluded Person Re-IdentificationPerson Re-Identification

Patch-Based Discriminative Feature Learning for Unsupervised Person Re-Identification

2019-06-01 · CVPR 2019 6 · Qize Yang, Hong-Xing Yu, Ancong Wu, Wei-Shi Zheng

While discriminative local features have been shown effective in solving the person re-identification problem, they are limited to be trained on fully pairwise labelled data which is expensive to obtain. In this work, we…

Person Re-IdentificationUnsupervised Person Re-Identification

Unsupervised Salience Learning for Person Re-identification

2013-06-01 · CVPR 2013 6 · Rui Zhao, Wanli Ouyang, Xiaogang Wang

Human eyes can recognize person identities based on some small salient regions. However, such valuable salient information is often hidden when computing similarities of images with existing approaches. Moreover, many ex…

Patch MatchingPerson Re-Identification

Unleashing Potential of Unsupervised Pre-Training With Intra-Identity Regularization for Person Re-Identification

2022-01-01 · CVPR 2022 1 · Zizheng Yang, Xin Jin, Kecheng Zheng, Feng Zhao

Existing person re-identification (ReID) methods typically directly load the pre-trained ImageNet weights for initialization. However, as a fine-grained classification task, ReID is more challenging and exists a larg…

Contrastive LearningPerson Re-IdentificationRepresentation LearningUnsupervised Pre-training

Pseudo-Pair based Self-Similarity Learning for Unsupervised Person Re-identification

2022-07-09 · Lin Wu, Deyin Liu, Wenying Zhang, Dapeng Chen 외

Person re-identification (re-ID) is of great importance to video surveillance systems by estimating the similarity between a pair of cross-camera person shorts. Current methods for estimating such similarity require a la…

Person Re-IdentificationUnsupervised Person Re-Identification