CoNe: Contrast Your Neighbours for Supervised Image Classification

by   Mingkai Zheng, et al.

Image classification is a longstanding problem in computer vision and machine learning research. Most recent works (e.g. SupCon , Triplet, and max-margin) mainly focus on grouping the intra-class samples aggressively and compactly, with the assumption that all intra-class samples should be pulled tightly towards their class centers. However, such an objective will be very hard to achieve since it ignores the intra-class variance in the dataset. (i.e. different instances from the same class can have significant differences). Thus, such a monotonous objective is not sufficient. To provide a more informative objective, we introduce Contrast Your Neighbours (CoNe) - a simple yet practical learning framework for supervised image classification. Specifically, in CoNe, each sample is not only supervised by its class center but also directly employs the features of its similar neighbors as anchors to generate more adaptive and refined targets. Moreover, to further boost the performance, we propose ``distributional consistency" as a more informative regularization to enable similar instances to have a similar probability distribution. Extensive experimental results demonstrate that CoNe achieves state-of-the-art performance across different benchmark datasets, network architectures, and settings. Notably, even without a complicated training recipe, our CoNe achieves 80.8\% Top-1 accuracy on ImageNet with ResNet-50, which surpasses the recent Timm training recipe (80.4\%). Code and pre-trained models are available at \href{}{}.


page 2

page 13


SimMatch: Semi-supervised Learning with Similarity Matching

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

SimMatchV2: Semi-Supervised Learning with Graph Consistency

Semi-Supervised image classification is one of the most fundamental prob...

Effectiveness of Optimization Algorithms in Deep Image Classification

Adam is applied widely to train neural networks. Different kinds of Adam...

ReMarNet: Conjoint Relation and Margin Learning for Small-Sample Image Classification

Despite achieving state-of-the-art performance, deep learning methods ge...

Shuffle Instances-based Vision Transformer for Pancreatic Cancer ROSE Image Classification

The rapid on-site evaluation (ROSE) technique can signifi-cantly acceler...

JEM++: Improved Techniques for Training JEM

Joint Energy-based Model (JEM) is a recently proposed hybrid model that ...

A Unified View of cGANs with and without Classifiers

Conditional Generative Adversarial Networks (cGANs) are implicit generat...

Please sign up or login with your details

Forgot password? Click here to reset