English

Scale Normalized Image Pyramids with AutoFocus for Object Detection

Computer Vision and Pattern Recognition 2021-02-11 v1 Artificial Intelligence

Abstract

We present an efficient foveal framework to perform object detection. A scale normalized image pyramid (SNIP) is generated that, like human vision, only attends to objects within a fixed size range at different scales. Such a restriction of objects' size during training affords better learning of object-sensitive filters, and therefore, results in better accuracy. However, the use of an image pyramid increases the computational cost. Hence, we propose an efficient spatial sub-sampling scheme which only operates on fixed-size sub-regions likely to contain objects (as object locations are known during training). The resulting approach, referred to as Scale Normalized Image Pyramid with Efficient Resampling or SNIPER, yields up to 3 times speed-up during training. Unfortunately, as object locations are unknown during inference, the entire image pyramid still needs processing. To this end, we adopt a coarse-to-fine approach, and predict the locations and extent of object-like regions which will be processed in successive scales of the image pyramid. Intuitively, it's akin to our active human-vision that first skims over the field-of-view to spot interesting regions for further processing and only recognizes objects at the right resolution. The resulting algorithm is referred to as AutoFocus and results in a 2.5-5 times speed-up during inference when used with SNIP.

Keywords

Cite

@article{arxiv.2102.05646,
  title  = {Scale Normalized Image Pyramids with AutoFocus for Object Detection},
  author = {Bharat Singh and Mahyar Najibi and Abhishek Sharma and Larry S. Davis},
  journal= {arXiv preprint arXiv:2102.05646},
  year   = {2021}
}

Comments

Accepted in T-PAMI 2021

R2 v1 2026-06-23T23:02:46.385Z