BING: Binarized Normed Gradients for Objectness Estimation at 300fps

TLDR

Training a generic objectness measure to generate candidate windows speeds up classical sliding‑window detection. The authors aim to create a fast generic objectness estimator by resizing windows to 8×8 and using binarized normed gradients as a 64‑dimensional feature. They implement BING by computing binarized normed gradients on 8×8 windows and evaluating them with simple atomic operations such as ADD and BITWISE SHIFT. On PASCAL VOC 2007, BING achieves 96.2 % detection rate with 1,000 proposals at 300 fps, and can reach 99.5 % by increasing proposals and color spaces.

Abstract

Training a generic objectness measure to produce a small set of candidate object windows, has been shown to speed up the classical sliding window object detection paradigm. We observe that generic objects with well-defined closed boundary can be discriminated by looking at the norm of gradients, with a suitable resizing of their corresponding image windows in to a small fixed size. Based on this observation and computational reasons, we propose to resize the window to 8 × 8 and use the norm of the gradients as a simple 64D feature to describe it, for explicitly training a generic objectness measure. We further show how the binarized version of this feature, namely binarized normed gradients (BING), can be used for efficient objectness estimation, which requires only a few atomic operations (e.g. ADD, BITWISE SHIFT, etc.). Experiments on the challenging PASCAL VOC 2007 dataset show that our method efficiently (300fps on a single laptop CPU) generates a small set of category-independent, high quality object windows, yielding 96.2% object detection rate (DR) with 1, 000 proposals. Increasing the numbers of proposals and color spaces for computing BING features, our performance can be further improved to 99.5% DR.