Speeding-up Object Detection Training for Robotics with FALKON

03/23/2018
by   Elisa Maiettini, et al.
0

Latest deep learning methods for object detection provided remarkable performance boost, but have limits when used in robotic applications. One of the most relevant issues is the long training time, which is due to the large size and unbalance of the associated training sets, characterized by few positive and tons of negative (i.e. background) examples. Proposed approaches, either based on end-to-end learning by back-propagation [22], or standard kernel methods trained with Hard Negatives Mining on top of deep features [8], proved to be effective, but prohibitively slow for on-line applications. In this paper we propose a novel pipeline for object detection that overcomes this problem and provides comparable performance, with a 60x training speedup. Our pipeline combines (i) the Region Proposal Network and the deep feature extractor from [22] to efficiently select candidate RoIs and encode them into powerful representations, with (ii) the recently proposed FALKON [23] algorithm, a novel kernel-based method that allows to quickly train on millions of points. We address the size and unbalance of training data by exploiting the stochastic subsampling intrinsic into the method, combined with a novel, fast, bootstrapping approach. We assess the effectiveness of the approach in a standard computer vision setting (PASCAL VOC 2007 [5]) and demonstrate its applicability to a real robotic scenario as represented by the iCubWorld Transformations [18] dataset.

READ FULL TEXT

page 3

page 7

research
07/16/2021

Weakly-Supervised Object Detection Learning through Human-Robot Interaction

Reliable perception and efficient adaptation to novel conditions are pri...
research
11/25/2020

Fast Region Proposal Learning for Object Detection for Robotics

Object detection is a fundamental task for robots to operate in unstruct...
research
11/25/2020

Fast Object Segmentation Learning with Kernel-based Methods for Robotics

Object segmentation is a key component in the visual system of a robot t...
research
03/14/2017

Geometry-Based Region Proposals for Real-Time Robot Detection of Tabletop Objects

We present a novel object detection pipeline for localization and recogn...
research
08/05/2017

Optimizing Region Selection for Weakly Supervised Object Detection

Training object detectors with only image-level annotations is very chal...
research
11/21/2020

Rethinking Transformer-based Set Prediction for Object Detection

DETR is a recently proposed Transformer-based method which views object ...
research
02/10/2020

Advances in Deep Space Exploration via Simulators Deep Learning

The StarLight program conceptualizes fast interstellar travel via small ...

Please sign up or login with your details

Forgot password? Click here to reset