PreDet: Large-scale weakly supervised pre-training for detection

By Vignesh Ramanathan, Rui Wang, Dhruv Kumar Mahajan. 2021

14 citations recorded by the source corpus.

State-of-the-art object detection approaches typically rely on pre-trained classification models to achieve better performance and faster convergence. We hypothesize that classification pre-training strives to achieve translation invariance, and consequently ignores the localization aspect of the problem. We propose a new large-scale pre-training strategy for detection, where noisy class labels are available for all images, but not bounding-boxes. In this setting, we augment standard classification pre-training with a new detection-specific pretext task. Motivated by the noise-contrastive learning based self-supervised approaches, we design a task that forces bounding boxes with high-overlap to have similar representations in different views of an image, compared to non-overlapping boxes. We redesign Faster R-CNN modules to perform this task efficiently. Our experimental results show significant improvements over existing weakly-supervised and self-supervised pre-training approaches in both detection accuracy as well as fine-tuning speed.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Jianfeng Gao
  2. Jianwei Yang
  3. Lu Yuan
  4. Pengchuan Zhang
  5. Xiyang Dai
  6. Zhe Gan
  7. Lijuan Wang
  8. Liunian Harold Li

In Computer Vision and Pattern Recognition

  1. Jianfeng Gao
  2. Jianwei Yang
  3. Lu Yuan
  4. Luc Van Gool
  5. Dacheng Tao
  6. Trevor Darrell
  7. Xiaogang Wang
  8. Pengchuan Zhang

Citations in the corpus