paper-with-me

Papers

Patch-level Representation Learning for Self-supervised Vision Transformers

2022-06-16 · CVPR 2022 1 · Sukmin Yun, Hankook Lee, Jaehyung Kim, Jinwoo Shin

Recent self-supervised learning (SSL) methods have shown impressive results in learning visual representations from unlabeled images. This paper aims to improve their performance further by utilizing the architectural advantages of the underlying neural network, as the current state-of-the-art visual pretext tasks for SSL do not enjoy the benefit, i.e., they are architecture-agnostic. In particular, we focus on Vision Transformers (ViTs), which have gained much attention recently as a better architectural choice, often outperforming convolutional networks for various visual tasks. The unique characteristic of ViT is that it takes a sequence of disjoint patches from an image and processes patch-level representations internally. Inspired by this, we design a simple yet effective visual pretext task, coined SelfPatch, for learning better patch-level representations. To be specific, we enforce invariance against each patch and its neighbors, i.e., each patch treats similar neighboring patches as positive samples. Consequently, training ViTs with SelfPatch learns more semantically meaningful relations among patches (without using human-annotated labels), which can be beneficial, in particular, to downstream tasks of a dense prediction type. Despite its simplicity, we demonstrate that it can significantly improve the performance of existing SSL methods for various visual tasks, including object detection and semantic segmentation. Specifically, SelfPatch significantly improves the recent self-supervised ViT, DINO, by achieving +1.3 AP on COCO object detection, +1.2 AP on COCO instance segmentation, and +2.9 mIoU on ADE20K semantic segmentation.

📄 PDF Abstract BibTeX arXiv:2206.07990

Code (1)

alinlab/selfpatch 공식 구현 pytorch

Tasks

Instance Segmentationobject-detectionObject DetectionRepresentation LearningSegmentationSelf-Supervised LearningSemantic Segmentation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
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 $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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…
Residual Connection 설명 없음
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…

Similar Papers 제목 키워드 기반

PASS: Patch-Aware Self-Supervision for Vision Transformer

2021-09-29 · Sukmin Yun, Hankook Lee, Jaehyung Kim, Jinwoo Shin

Recent self-supervised representation learning methods have shown impressive results in learning visual representations from unlabeled images. This paper aims to improve their performance further by utilizing the archite…

object-detectionObject DetectionRepresentation LearningSelf-Supervised Learning+1

Self-Supervised Pyramid Representation Learning for Multi-Label Visual Analysis and Beyond

2022-08-30 · Cheng-Yen Hsieh, Chih-Jung Chang, Fu-En Yang, Yu-Chiang Frank Wang

While self-supervised learning has been shown to benefit a number of vision tasks, existing techniques mainly focus on image-level manipulation, which may not generalize well to downstream tasks at patch or pixel levels.…

Instance SegmentationMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONobject-detection+4

Patch-Wise Self-Supervised Visual Representation Learning: A Fine-Grained Approach

2023-10-28 · Ali Javidani, Mohammad Amin Sadeghi, Babak Nadjar Araabi

Self-supervised visual representation learning traditionally focuses on image-level instance discrimination. Our study introduces an innovative, fine-grained dimension by integrating patch-level discrimination into these…

Copy Detectionimage-classificationImage ClassificationImage Retrieval+3

Masked Siamese Networks for Label-Efficient Learning

2022-04-14 · Mahmoud Assran, Mathilde Caron, Ishan Misra, Piotr Bojanowski 외

We propose Masked Siamese Networks (MSN), a self-supervised learning framework for learning image representations. Our approach matches the representation of an image view containing randomly masked patches to the repres…

image-classificationImage ClassificationSelf-Supervised Image ClassificationSelf-Supervised Learning+1

Pattern Integration and Enhancement Vision Transformer for Self-Supervised Learning in Remote Sensing

2024-11-09 · Kaixuan Lu, Ruiqian Zhang, Xiao Huang, Yuxing Xie 외

Recent self-supervised learning (SSL) methods have demonstrated impressive results in learning visual representations from unlabeled remote sensing images. However, most remote sensing images predominantly consist of sce…

Change DetectionLand Cover Classificationobject-detectionObject Detection+2