DeepAI AI Chat
Log In Sign Up

Scale Normalized Image Pyramids with AutoFocus for Object Detection

02/10/2021
by   Bharat Singh, et al.
0

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.

READ FULL TEXT

page 2

page 4

page 7

page 8

page 10

page 11

page 16

page 18

12/04/2018

AutoFocus: Efficient Multi-Scale Inference

This paper describes AutoFocus, an efficient multi-scale inference algor...
09/17/2022

Understanding the Impact of Image Quality and Distance of Objects to Object Detection Performance

Deep learning has made great strides for object detection in images. The...
11/22/2017

An Analysis of Scale Invariance in Object Detection - SNIP

An analysis of different techniques for recognizing and detecting object...
12/16/2012

Visual Objects Classification with Sliding Spatial Pyramid Matching

We present a method for visual object classification using only a single...
05/23/2018

SNIPER: Efficient Multi-Scale Training

We present SNIPER, an algorithm for performing efficient multi-scale tra...
09/05/2019

Detector With Focus: Normalizing Gradient In Image Pyramid

An image pyramid can extend many object detection algorithms to solve de...
12/24/2015

Adaptive Object Detection Using Adjacency and Zoom Prediction

State-of-the-art object detection systems rely on an accurate set of reg...