Search Results for author:
Found 4 papers, 4 papers with code
Combining Metric Learning and Attention Heads For Accurate and Efficient Multilabel Image Classification
Although transformer-based heads are considered to achieve better results than graph-based branches, we argue that with the proper training strategy, graph-based methods can demonstrate just a small accuracy drop, while spending less computational resources on inference.
Ranked #2 on
Multi-Label Classification
on NUS-WIDE
Towards Efficient and Data Agnostic Image Classification Training Pipeline for Embedded Systems
Nowadays deep learning-based methods have achieved a remarkable progress at the image classification task among a wide range of commonly used datasets (ImageNet, CIFAR, SVHN, Caltech 101, SUN397, etc.).
Open Images V5 Text Annotation and Yet Another Mask Text Spotter
A large scale human-labeled dataset plays an important role in creating high quality deep learning models.
Building Computationally Efficient and Well-Generalizing Person Re-Identification Models with Metric Learning
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 #31 on
Person Re-Identification
on MSMT17
