Authors:
Leonardo Joao
1
;
2
;
Matheus Cerqueira
1
;
Barbara Benato
1
and
Alexandre Falcao
1
Affiliations:
1
Institute of Computing, State University of Campinas, Campinas, 13083-872, São Paulo, Brazil
;
2
LIGM, Univ. Gustave-Eiffel, Marne-la-Valée, F-77454, France
Keyword(s):
Marker-Based-Normalization, Flim, Z-Score-Normalization, Object-Detection.
Abstract:
Successful methods for object detection in multiple image domains are based on convolutional networks. However, such approaches require large annotated image sets for network training. One can build object detectors by exploring a recent methodology, Feature Learning from Image Markers (FLIM), that considerably reduces human effort in data annotation. In FLIM, the encoder’s filters are estimated among image patches extracted from scribbles drawn by the user on discriminative regions of a few representative images. The filters are meant to create feature maps in which the object is activated or deactivated. This task depends on a z-score normalization using the scribbles’ statistics, named marker-based normalization (MBN). An adaptive decoder (point-wise convolution with activation) finds its parameters for each image and outputs a saliency map for object detection. This encoder-decoder network is trained without backpropagation. This work investigates the effect of MBN on the network
’s results. We detach the scribble sets for filter estimation and MBN, introduce a bot that draws scribbles with distinct ratios of object-and-background samples, and evaluate the impact of five different ratios on three datasets through six quantitative metrics and feature projection analysis. The experiments suggest that scribble detachment and MBN with object oversampling are beneficial.
(More)