A New Knowledge Distillation for Incremental Object Detection

By Li Chen, Chunyan Yu, Lvcai Chen. 2019

60 citations recorded by the source corpus.

Nowadays, the Convolutional Neural Network is successfully applied to the images object detection. When new classes of object emerges, it is popular to adapt the convolutional neural network based detection model through a retraining process with the new classes of samples. Unfortunately, the adapted model can only detect the new classes of objects, but cannot identify the old classes of objects, which is called catastrophic forgetting, also occurring in incremental classification tasks. Knowledge distillation has achieved good results in incremental learning for classification tasks. Due to the dual tasks within object detection, object classification and location at the same time, a straightforward migration of knowledge distillation method cannot provide a satisfactory result in incremental learning for object detection tasks. Hence, this paper propose a new knowledge distillation for incremental object detection, which introduces a new object detection distillation loss, a loss not only for classification results but also for location results of the predicted bounding boxes, not only for all final detected regions of interest but also for all intermediate regions proposal. Furthermore, to avoid forgetting learned knowledge from old datasets, this paper not only employs hint learning to retain the characteristic information of the initial model, but also innovatively uses confidence loss to extract the confidence information of the initial model. A series of experiment results on the PASCAL VOC 2007 dataset verify the effectiveness of the proposed method.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Efficiency & Compression

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Efficiency & Compression

Citations in the corpus

Static-Dynamic Co-Teaching for Class-Incremental 3D Object Detection (2021, background): “Many deep learning-based approaches (Li, Zhang, and Xia 2016; Chen et al. 2017; Beltrán et al. 2018; Yan, Mao, and Li 2018; Yang, Luo, and Urtasun 2018; Zeng et al. 2018; Zhou and Tuzel 2018; Chen et al. 2019; Lang et al. 2019; Qi et al. 2019; Shi, Wang, and Li 2019; Yang et al. 2019; Zhou et al. 20”
Bridging Non Co-occurrence with Unlabeled In-the-wild Data for Incremental Object Detection (2021, neutral): “Recently, several incremental learning methods [40, 27, 4, 10, 20, 31] are proposed to overcome catastrophic forgetting in the object detection task.”
Towards Open World Object Detection (2021, background): “The prevalent approaches [61, 28, 18, 7] use knowledge distillation [21]”
Online Continual Learning in Image Classification: An Empirical Survey (2021, methodology): “Most methods leverage KD [40] to alleviate CF, and the main differences between the methods are the base object detector and distillation parts in the network [126, 127, 128, 129].”
Incremental Object Detection via Meta-Learning (2020, positive): “To this end, knowledge distillation [5] has been utilized as a de facto solution [6], [7], [8], [9].”
A Survey on Few-Shot Class-Incremental Learning (2023, background): “There are also some researchers (Chen et al., 2019; Liu et al., 2020b; Shmelkov et al., 2017) who study the problem of incremental target detection from the perspective of IL.”
Incremental Detection of Remote Sensing Objects With Feature Pyramid and Knowledge Distillation (2020, methodology): “In addition to measuring the discrepancy of feature maps between two models, [21] computes the difference of classiﬁcation and regression outputs in RPN by using knowledge distillation.”
3rd Continual Learning Workshop Challenge on Egocentric Category and Instance Level Object Understanding (2022, background): “[83], the learning of each new experience is regularized by distilling knowledge from a saved version of the model trained on the previous experiences.”
Class-Incremental Learning: A Survey (2023, background): “Other works also apply knowledge distillation on the region proposal networks [263], [264], [265].”
Continual Detection Transformer for Incremental Object Detection (2023, methodology): “, FasterRCNN [42] and GFL [25]) by adding KD terms on the intermediate feature maps [12,55,58] and region proposal networks [7, 14, 37].”
Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection (2023, methodology): “While most studies in incremental learning are based on image classification [2, 31, 34, 50], recently it has been studied in the context of object detection [7, 9, 22, 48, 55] and semantic segmentation [13, 20, 64].”