VIPriors 1: Visual Inductive Priors for Data-Efficient Deep Learning Challenges
arXiv:2103.03768
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 (22)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- YOLOv4: Optimal Speed and Accuracy of Object Detection
- mixup: Beyond Empirical Risk Minimization
- Deep Residual Learning for Image Recognition
- UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild
- In Defense of the Triplet Loss for Person Re-Identification
- When Does Label Smoothing Help?
- AutoAugment: Learning Augmentation Policies from Data
- Weighted boxes fusion: Ensembling boxes from different object detection models
- Rank Pooling for Action Recognition
- GridMask Data Augmentation
- Bag of Tricks for Image Classification with Convolutional Neural Networks
- An Empirical Study of Spatial Attention Mechanisms in Deep Networks
- NBDT: Neural-Backed Decision Trees
- A Competitive Method to VIPriors Object Detection Challenge
- EfficientSeg: An Efficient Semantic Segmentation Network
- Data-Efficient Deep Learning Method for Image Classification Using Data Augmentation, Focal Cosine Loss, and Ensemble
- Edge-Preserving Guided Semantic Segmentation for VIPriors Challenge
- Challenge report:VIPriors Action Recognition Challenge
- VIPriors Object Detection Challenge
- A Technical Report for VIPriors Image Classification Challenge
- 2nd Place Solution to ECCV 2020 VIPriors Object Detection Challenge
Cited by in corpus (5)
- TCLR: Temporal Contrastive Learning for Video Representation
- DeepSportradar-v1: Computer Vision Dataset for Sports Understanding with High Quality Annotations
- Image Classification with Small Datasets: Overview and Benchmark
- Genetic Programming-Based Evolutionary Deep Learning for Data-Efficient Image Classification
- A Strong Baseline for the VIPriors Data-Efficient Image Classification Challenge