Continual Object Detection via Prototypical Task Correlation Guided Gating Mechanism

by   Binbin Yang, et al.

Continual learning is a challenging real-world problem for constructing a mature AI system when data are provided in a streaming fashion. Despite recent progress in continual classification, the researches of continual object detection are impeded by the diverse sizes and numbers of objects in each image. Different from previous works that tune the whole network for all tasks, in this work, we present a simple and flexible framework for continual object detection via pRotOtypical taSk corrElaTion guided gaTing mechAnism (ROSETTA). Concretely, a unified framework is shared by all tasks while task-aware gates are introduced to automatically select sub-models for specific tasks. In this way, various knowledge can be successively memorized by storing their corresponding sub-model weights in this system. To make ROSETTA automatically determine which experience is available and useful, a prototypical task correlation guided Gating Diversity Controller(GDC) is introduced to adaptively adjust the diversity of gates for the new task based on class-specific prototypes. GDC module computes class-to-class correlation matrix to depict the cross-task correlation, and hereby activates more exclusive gates for the new task if a significant domain gap is observed. Comprehensive experiments on COCO-VOC, KITTI-Kitchen, class-incremental detection on VOC and sequential learning of four tasks show that ROSETTA yields state-of-the-art performance on both task-based and class-based continual object detection.


page 1

page 3

page 8


Continual Object Detection: A review of definitions, strategies, and challenges

The field of Continual Learning investigates the ability to learn consec...

CLAD: A realistic Continual Learning benchmark for Autonomous Driving

In this paper we describe the design and the ideas motivating a new Cont...

Taxonomic Class Incremental Learning

The problem of continual learning has attracted rising attention in rece...

nVFNet-RDC: Replay and Non-Local Distillation Collaboration for Continual Object Detection

Continual Learning (CL) focuses on developing algorithms with the abilit...

Exemplar-free Online Continual Learning

Targeted for real world scenarios, online continual learning aims to lea...

Re-examining Distillation For Continual Object Detection

Training models continually to detect and classify objects, from new cla...

Seeing BDD100K in dark: Single-Stage Night-time Object Detection via Continual Fourier Contrastive Learning

Despite tremendous improvements in state-of-the-art object detectors, ad...

Please sign up or login with your details

Forgot password? Click here to reset