Hi Detector, What's Wrong with that Object? Identifying Irregular Object From Images by Modelling the Detection Score Distribution

02/14/2016
by   Peng Wang, et al.
0

In this work, we study the challenging problem of identifying the irregular status of objects from images in an "open world" setting, that is, distinguishing the irregular status of an object category from its regular status as well as objects from other categories in the absence of "irregular object" training data. To address this problem, we propose a novel approach by inspecting the distribution of the detection scores at multiple image regions based on the detector trained from the "regular object" and "other objects". The key observation motivating our approach is that for "regular object" images as well as "other objects" images, the region-level scores follow their own essential patterns in terms of both the score values and the spatial distributions while the detection scores obtained from an "irregular object" image tend to break these patterns. To model this distribution, we propose to use Gaussian Processes (GP) to construct two separate generative models for the case of the "regular object" and the "other objects". More specifically, we design a new covariance function to simultaneously model the detection score at a single region and the score dependencies at multiple regions. We finally demonstrate the superior performance of our method on a large dataset newly proposed in this paper.

READ FULL TEXT

page 2

page 4

page 10

research
03/24/2022

Focus-and-Detect: A Small Object Detection Framework for Aerial Images

Despite recent advances, object detection in aerial images is still a ch...
research
10/23/2014

Density-Based Region Search with Arbitrary Shape for Object Localization

Region search is widely used for object localization. Typically, the reg...
research
11/10/2017

Bayesian Gaussian models for interpolating large-dimensional data at misaligned areal units

Areal level spatial data are often large, sparse and may appear with geo...
research
09/26/2017

SURGE: Continuous Detection of Bursty Regions Over a Stream of Spatial Objects

With the proliferation of mobile devices and location-based services, co...
research
03/26/2019

Reconstruction of r-Regular Objects from Trinary Images

We study digital images of r-regular objects where a pixel is black if i...
research
02/08/2020

Exploring the Memorization-Generalization Continuum in Deep Learning

Human learners appreciate that some facts demand memorization whereas ot...
research
12/01/2022

Regret Loss of Prejudiced Algorithms

The behavior of predictive algorithms built on data generated by a preju...

Please sign up or login with your details

Forgot password? Click here to reset