|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
We propose AugMix, a data processing technique that is simple to implement, adds limited computational overhead, and helps models withstand unforeseen corruptions.
#2 best model for Domain Generalization on ImageNet-C
We also find that mixup reduces the memorization of corrupt labels, increases the robustness to adversarial examples, and stabilizes the training of generative adversarial networks.
#3 best model for Domain Generalization on ImageNet-A
This work considers the problem of domain shift in person re-identification. Being trained on one dataset, a re-identification model usually performs much worse on unseen data.
#3 best model for Person Re-Identification on MSMT17
Few-shot classification aims to learn a classifier to recognize unseen classes during training with limited labeled examples.
#4 best model for Few-Shot Image Classification on Mini-ImageNet-CUB 5-way (5-shot)
Regional dropout strategies have been proposed to enhance the performance of convolutional neural network classifiers.
SOTA for Image Captioning on COCO
Convolutional Neural Networks (CNNs) are commonly thought to recognise objects by learning increasingly complex representations of object shapes.
#3 best model for Domain Generalization on ImageNet-R (using extra training data)
Convolutional neural networks are capable of learning powerful representational spaces, which are necessary for tackling complex learning tasks.
#3 best model for Semi-Supervised Image Classification on STL-10
Then we propose a new dataset called ImageNet-P which enables researchers to benchmark a classifier's robustness to common perturbations.
#4 best model for Domain Generalization on ImageNet-C