SimMatchV2: Semi-Supervised Learning with Graph Consistency

by   Mingkai Zheng, et al.

Semi-Supervised image classification is one of the most fundamental problem in computer vision, which significantly reduces the need for human labor. In this paper, we introduce a new semi-supervised learning algorithm - SimMatchV2, which formulates various consistency regularizations between labeled and unlabeled data from the graph perspective. In SimMatchV2, we regard the augmented view of a sample as a node, which consists of a label and its corresponding representation. Different nodes are connected with the edges, which are measured by the similarity of the node representations. Inspired by the message passing and node classification in graph theory, we propose four types of consistencies, namely 1) node-node consistency, 2) node-edge consistency, 3) edge-edge consistency, and 4) edge-node consistency. We also uncover that a simple feature normalization can reduce the gaps of the feature norm between different augmented views, significantly improving the performance of SimMatchV2. Our SimMatchV2 has been validated on multiple semi-supervised learning benchmarks. Notably, with ResNet-50 as our backbone and 300 epochs of training, SimMatchV2 achieves 71.9\% and 76.2\% Top-1 Accuracy with 1\% and 10\% labeled examples on ImageNet, which significantly outperforms the previous methods and achieves state-of-the-art performance. Code and pre-trained models are available at \href{}{}.


page 1

page 2

page 3

page 4


SimMatch: Semi-supervised Learning with Similarity Matching

Learning with few labeled data has been a longstanding problem in the co...

Semi-supervised Image Classification with Grad-CAM Consistency

Consistency training, which exploits both supervised and unsupervised le...

CoNe: Contrast Your Neighbours for Supervised Image Classification

Image classification is a longstanding problem in computer vision and ma...

Semi-supervised learning of hierarchical representations of molecules using neural message passing

With the rapid increase of compound databases available in medicinal and...

Hierarchical Dynamic Image Harmonization

Image harmonization is a critical task in computer vision, which aims to...

Automated Cleanup of the ImageNet Dataset by Model Consensus, Explainability and Confident Learning

The convolutional neural networks (CNNs) trained on ILSVRC12 ImageNet we...

SAT: Improving Semi-Supervised Text Classification with Simple Instance-Adaptive Self-Training

Self-training methods have been explored in recent years and have exhibi...

Please sign up or login with your details

Forgot password? Click here to reset