133 papers with code • 11 benchmarks • 16 datasets
The idea of Domain Generalization is to learn from one or multiple training domains, to extract a domain-agnostic model which can be applied to an unseen domain
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.
Ranked #2 on Semantic Object Interaction Classification on VLOG
We propose AugMix, a data processing technique that is simple to implement, adds limited computational overhead, and helps models withstand unforeseen corruptions.
Ranked #7 on Domain Generalization on ImageNet-R
Regional dropout strategies have been proposed to enhance the performance of convolutional neural network classifiers.
Ranked #3 on Image Captioning on COCO
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.
Ranked #7 on Domain Generalization on ImageNet-A
Vision Transformers (ViTs) and MLPs signal further efforts on replacing hand-wired features or inductive biases with general-purpose neural architectures.
Ranked #1 on Domain Generalization on ImageNet-R (Top 1 Accuracy metric)
Convolutional neural networks are capable of learning powerful representational spaces, which are necessary for tackling complex learning tasks.
Ranked #3 on Semi-Supervised Image Classification on STL-10
Theoretically, we provide a connection of two recent methods, Jacobian Regularization and Virtual Adversarial Training, under this framework.
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.
Ranked #17 on Person Re-Identification on MSMT17
Few-shot classification aims to learn a classifier to recognize unseen classes during training with limited labeled examples.
Convolutional Neural Networks (CNNs) are commonly thought to recognise objects by learning increasingly complex representations of object shapes.
Ranked #6 on Domain Generalization on ImageNet-R (using extra training data)