Augmentation Pathways Network for Visual Recognition

by   Yalong Bai, et al.

Data augmentation is practically helpful for visual recognition, especially at the time of data scarcity. However, such success is only limited to quite a few light augmentations (e.g., random crop, flip). Heavy augmentations (e.g., gray, grid shuffle) are either unstable or show adverse effects during training, owing to the big gap between the original and augmented images. This paper introduces a novel network design, noted as Augmentation Pathways (AP), to systematically stabilize training on a much wider range of augmentation policies. Notably, AP tames heavy data augmentations and stably boosts performance without a careful selection among augmentation policies. Unlike traditional single pathway, augmented images are processed in different neural paths. The main pathway handles light augmentations, while other pathways focus on heavy augmentations. By interacting with multiple paths in a dependent manner, the backbone network robustly learns from shared visual patterns among augmentations, and suppresses noisy patterns at the same time. Furthermore, we extend AP to a homogeneous version and a heterogeneous version for high-order scenarios, demonstrating its robustness and flexibility in practical usage. Experimental results on ImageNet benchmarks demonstrate the compatibility and effectiveness on a much wider range of augmentations (e.g., Crop, Gray, Grid Shuffle, RandAugment), while consuming fewer parameters and lower computational costs at inference time. Source code:


Parallel Grid Pooling for Data Augmentation

Convolutional neural network (CNN) architectures utilize downsampling la...

TinaFace: Strong but Simple Baseline for Face Detection

Face detection has received intensive attention in recent years. Many wo...

How to Train Your Robust Human Pose Estimator: Pay Attention to the Constraint Cue

Both appearance cue and constraint cue are important in human pose estim...

PP-YOLOE: An evolved version of YOLO

In this report, we present PP-YOLOE, an industrial state-of-the-art obje...

MetaAugment: Sample-Aware Data Augmentation Policy Learning

Automated data augmentation has shown superior performance in image reco...

Membership Inference with Privately Augmented Data Endorses the Benign while Suppresses the Adversary

Membership inference (MI) in machine learning decides whether a given ex...

Please sign up or login with your details

Forgot password? Click here to reset