paper-with-me

Papers

InsCon:Instance Consistency Feature Representation via Self-Supervised Learning

2022-03-15 · Junwei Yang, Ke Zhang, Zhaolin Cui, Jinming Su, Junfeng Luo, Xiaolin Wei

Feature representation via self-supervised learning has reached remarkable success in image-level contrastive learning, which brings impressive performances on image classification tasks. While image-level feature representation mainly focuses on contrastive learning in single instance, it ignores the objective differences between pretext and downstream prediction tasks such as object detection and instance segmentation. In order to fully unleash the power of feature representation on downstream prediction tasks, we propose a new end-to-end self-supervised framework called InsCon, which is devoted to capturing multi-instance information and extracting cell-instance features for object recognition and localization. On the one hand, InsCon builds a targeted learning paradigm that applies multi-instance images as input, aligning the learned feature between corresponding instance views, which makes it more appropriate for multi-instance recognition tasks. On the other hand, InsCon introduces the pull and push of cell-instance, which utilizes cell consistency to enhance fine-grained feature representation for precise boundary localization. As a result, InsCon learns multi-instance consistency on semantic feature representation and cell-instance consistency on spatial feature representation. Experiments demonstrate the method we proposed surpasses MoCo v2 by 1.1% AP^{bb} on COCO object detection and 1.0% AP^{mk} on COCO instance segmentation using Mask R-CNN R50-FPN network structure with 90k iterations, 2.1% APbb on PASCAL VOC objection detection using Faster R-CNN R50-C4 network structure with 24k iterations.

📄 PDF Abstract BibTeX arXiv:2203.07688

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive Learningimage-classificationImage ClassificationInstance Segmentationobject-detectionObject DetectionObject RecognitionSelf-Supervised LearningSemantic Segmentation

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음
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…
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 $x$…
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…
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…
RoIPool 설명 없음
Random Gaussian Blur Random Gaussian Blur is an image data augmentation technique where we randomly blur the image using a Gaussian distribution. Image Source:…

Similar Papers 제목 키워드 기반

Learning Multiscale Consistency for Self-supervised Electron Microscopy Instance Segmentation

2023-08-19 · Yinda Chen, Wei Huang, Xiaoyu Liu, Shiyu Deng 외

Instance segmentation in electron microscopy (EM) volumes is tough due to complex shapes and sparse annotations. Self-supervised learning helps but still struggles with intricate visual patterns in EM. To address this, w…

Contrastive LearningInstance SegmentationSegmentationSelf-Supervised Learning+1

Self-Supervised Image Representation Learning with Geometric Set Consistency

2022-03-29 · CVPR 2022 1 · Nenglun Chen, Lei Chu, Hao Pan, Yan Lu 외

We propose a method for self-supervised image representation learning under the guidance of 3D geometric consistency. Our intuition is that 3D geometric consistency priors such as smooth regions and surface discontinuiti…

Contrastive LearningInstance Segmentationobject-detectionObject Detection+3

MultiSiam: Self-supervised Multi-instance Siamese Representation Learning for Autonomous Driving

2021-08-27 · ICCV 2021 10 · Kai Chen, Lanqing Hong, Hang Xu, Zhenguo Li 외

Autonomous driving has attracted much attention over the years but turns out to be harder than expected, probably due to the difficulty of labeled data collection for model training. Self-supervised learning (SSL), which…

Autonomous DrivingImage ClusteringRepresentation LearningSelf-Supervised Learning

Self-Supervised Consistent Quantization for Fully Unsupervised Image Retrieval

2022-06-20 · Guile Wu, Chao Zhang, Stephan Liwicki

Unsupervised image retrieval aims to learn an efficient retrieval system without expensive data annotations, but most existing methods rely heavily on handcrafted feature descriptors or pre-trained feature extractors. To…

Contrastive LearningImage RetrievalQuantizationRetrieval

Learning the Relation between Similarity Loss and Clustering Loss in Self-Supervised Learning

2023-01-08 · Jidong Ge, Yuxiang Liu, Jie Gui, Lanting Fang 외

Self-supervised learning enables networks to learn discriminative features from massive data itself. Most state-of-the-art methods maximize the similarity between two augmentations of one image based on contrastive learn…

ClusteringContrastive LearningRelationSelf-Supervised Learning