Incremental Deep Learning for Robust Object Detection in Unknown Cluttered Environments

10/13/2018
by   Dong Kyun Shin, et al.
0

Object detection in streaming images is a major step in different detection-based applications, such as object tracking, action recognition, robot navigation, and visual surveillance applications. In mostcases, image quality is noisy and biased, and as a result, the data distributions are disturbed and imbalanced. Most object detection approaches, such as the faster region-based convolutional neural network (Faster RCNN), Single Shot Multibox Detector with 300x300 inputs (SSD300), and You Only Look Once version 2 (YOLOv2), rely on simple sampling without considering distortions and noise under real-world changing environments, despite poor object labeling. In this paper, we propose an Incremental active semi-supervised learning (IASSL) technology for unseen object detection. It combines batch-based active learning (AL) and bin-based semi-supervised learning (SSL) to leverage the strong points of AL's exploration and SSL's exploitation capabilities. A collaborative sampling method is also adopted to measure the uncertainty and diversity of AL and the confidence in SSL. Batch-based AL allows us to select more informative, confident, and representative samples with low cost. Bin-based SSL divides streaming image samples into several bins, and each bin repeatedly transfers the discriminative knowledge of convolutional neural network (CNN) deep learning to the next bin until the performance criterion is reached. IASSL can overcome noisy and biased labels in unknown, cluttered data distributions. We obtain superior performance, compared to state-of-the-art technologies such as Faster RCNN, SSD300, and YOLOv2.

READ FULL TEXT
research
06/21/2020

Semi-Supervised Object Detection with Sparsely Annotated Dataset

In training object detector based on convolutional neural networks, sele...
research
03/29/2021

Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection

In this paper, we delve into semi-supervised object detection where unla...
research
12/26/2019

SESS: Self-Ensembling Semi-Supervised 3D Object Detection

The performance of existing point cloud-based 3D object detection method...
research
09/14/2023

ALWOD: Active Learning for Weakly-Supervised Object Detection

Object detection (OD), a crucial vision task, remains challenged by the ...
research
11/21/2022

Plug and Play Active Learning for Object Detection

Annotating data for supervised learning is expensive and tedious, and we...
research
12/28/2020

Data-efficient Weakly-supervised Learning for On-line Object Detection under Domain Shift in Robotics

Several object detection methods have recently been proposed in the lite...
research
07/17/2019

Half a Percent of Labels is Enough: Efficient Animal Detection in UAV Imagery using Deep CNNs and Active Learning

We present an Active Learning (AL) strategy for re-using a deep Convolut...

Please sign up or login with your details

Forgot password? Click here to reset