← Search

Cristina Vasconcelos

2 accepted papers

2022

Proper Reuse of Image Classification Features Improves Object Detection

CVPR 2022oral

A common practice in transfer learning is to initialize the downstream model weights by pre-training on a data-abundant upstream task. In object detection specifically,the feature backbone is typically initialized with ImageNet classifier weights and fine-tuned on the object detection task. Recent w…

Cited by 35PDFcodeScholar
2021

Impact of Aliasing on Generalization in Deep Convolutional Networks

ICCV 2021poster

We investigate the impact of aliasing on generalization in Deep Convolutional Networks and show that data augmentation schemes alone are unable to prevent it due to structural limitations in widely used architectures. Drawing insights from frequency analysis theory, we take a closer look at Resnet a…

Cited by 47PDFScholar