VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges

Abstract

We present the first edition of "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" challenges. We offer four data-impaired challenges, where models are trained from scratch, and we reduce the number of training samples to a fraction of the full set. Furthermore, to encourage data efficient solutions, we prohibited the use of pre-trained models and other transfer learning techniques. The majority of top ranking solutions make heavy use of data augmentation, model ensembling, and novel and efficient network architectures to achieve significant performance increases compared to the provided baselines.

References in corpus (10)

• YOLOv4: Optimal Speed and Accuracy of Object Detection
• UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
• An Empirical Study of Spatial Attention Mechanisms in Deep Networks
• A Competitive Method to VIPriors Object Detection Challenge
• Data-Efficient Deep Learning Method for Image Classification Using Data Augmentation, Focal Cosine Loss, and Ensemble
• Challenge report:VIPriors Action Recognition Challenge
• Edge-Preserving Guided Semantic Segmentation for VIPriors Challenge
• VIPriors Object Detection Challenge
• 2nd Place Solution to ECCV 2020 VIPriors Object Detection Challenge
• A Technical Report for VIPriors Image Classification Challenge