Incremental Deep Learning for Robust Object Detection in Unknown Cluttered Environments

Abstract

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 most cases, 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. FIGURE 8. Data model for IASSL: the root node consists of PASCAL VOC 2007 and 2012 and the local dataset. The local datasets are captured.

EER-ASSL: Combining Rollback Learning and Deep Learning for Rapid Adaptive Object Detection

“…AL and SSL combined together can improve the classification performance by exploiting both labeled and unlabeled data. Similar research has been conducted by Tong and Koller et al (2000) where they reduce the version space size for SVM [25]. Cohn et al (1996) minimize the estimated generalization error by the reduction of the variance components [26].…”

“…As a result, decreasing local training data has not much effect on the YOLOv2 model in our experiment. On the other hand, our EER-ASSL model already adapted the local data and if the composition data ratio is over 50 percent then the EER-ASSL outperforms other state-of-the-art methods that can be seen in the additional columns (10,90) and (25,75). The comparison of EER-ASSL, in terms of mAP, with state-of-the-art object detectors such as Faster RCNN, SSD 300, and YOLOv2 are shown in Table 2.…”

Hierarchical Open-Set Object Detection in Unseen Data

“…The main goal of our experiment was to identify the efficiency of our dynamic HFM tree model framework using ASSL [44]. To achieve this goal, we conducted several experiments on benchmark datasets, such as PASCAL VOC, MS COCO, and ILSVRC.…”

“…We retrained the CNN using the pool of samples, and the process was repeated until a convergence criterion was satisfied. The entire process and parameters are summarized in Algorithm 1 and [44]. while f not convergence, do 4:…”

Fast Two-Cycle Level Set Tracking With Interactive Superpixel Segmentation and Its Application in Image Retrieval

“…With the rapid development of information technology, computer vision technology has emerged as an active research field. Within this field, target tracking technology developed based on target detection [12], [13] is an important research topic. Kass et al first propose the Snake model, which takes control points of a certain shape as the template; the energy function is minimized through the elastic deformation of the template itself.…”