paper-with-me

Papers

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, Dit-yan Yeung

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 leverages unlabeled data only for representation learning, might be a promising way to improve model performance. Existing SSL methods, however, usually rely on the single-centric-object guarantee, which may not be applicable for multi-instance datasets such as street scenes. To alleviate this limitation, we raise two issues to solve: (1) how to define positive samples for cross-view consistency and (2) how to measure similarity in multi-instance circumstances. We first adopt an IoU threshold during random cropping to transfer global-inconsistency to local-consistency. Then, we propose two feature alignment methods to enable 2D feature maps for multi-instance similarity measurement. Additionally, we adopt intra-image clustering with self-attention for further mining intra-image similarity and translation-invariance. Experiments show that, when pre-trained on Waymo dataset, our method called Multi-instance Siamese Network (MultiSiam) remarkably improves generalization ability and achieves state-of-the-art transfer performance on autonomous driving benchmarks, including Cityscapes and BDD100K, while existing SSL counterparts like MoCo, MoCo-v2, and BYOL show significant performance drop. By pre-training on SODA10M, a large-scale autonomous driving dataset, MultiSiam exceeds the ImageNet pre-trained MoCo-v2, demonstrating the potential of domain-specific pre-training. Code will be available at https://github.com/KaiChen1998/MultiSiam.

📄 PDF Abstract BibTeX arXiv:2108.12178

Code (1)

kaichen1998/multisiam 공식 구현 pytorch

Tasks

Autonomous DrivingImage ClusteringRepresentation LearningSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

Batch Normalization 설명 없음
BYOL 설명 없음
InfoNCE 설명 없음
MoCo 설명 없음
Siamese Network 설명 없음

Similar Papers 제목 키워드 기반

MultiSiam: A Multiple Input Siamese Network For Social Media Text Classification And Duplicate Text Detection

2024-01-06 · Sudhanshu Bhoi, Swapnil Markhedkar, Shruti Phadke, Prashant Agrawal

Social media accounts post increasingly similar content, creating a chaotic experience across platforms, which makes accessing desired information difficult. These posts can be organized by categorizing and grouping dupl…

text-classificationText ClassificationText Detection

Ladder Siamese Network: a Method and Insights for Multi-level Self-Supervised Learning

2022-11-25 · Ryota Yoshihashi, Shuhei Nishimura, Dai Yonebayashi, Yuya Otsuka 외

Siamese-network-based self-supervised learning (SSL) suffers from slow convergence and instability in training. To alleviate this, we propose a framework to exploit intermediate self-supervisions in each stage of deep ne…

Self-Supervised Learning

Semi-Supervised Learning using Siamese Networks

2021-09-02 · Attaullah Sahito, Eibe Frank, Bernhard Pfahringer

Neural networks have been successfully used as classification models yielding state-of-the-art results when trained on a large number of labeled samples. These models, however, are more difficult to train successfully fo…

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

Exploring Siamese Networks in Self-Supervised Fast MRI Reconstruction

2025-01-18 · Liyan Sun, Shaocong Yu, Chi Zhang, Xinghao Ding

Reconstructing MR images using deep neural networks from undersampled k-space data without using fully sampled training references offers significant value in practice, which is a self-supervised regression problem calli…

MRI ReconstructionSelf-Supervised Learning