CVApr 19, 2022

Modeling Missing Annotations for Incremental Learning in Object Detection

arXiv:2204.08766v240 citationsh-index: 22Has Code
Originality Incremental advance
AI Analysis

This work solves the problem of forgetting old classes in incremental object detection for AI systems needing to adapt over time, representing an incremental improvement over existing methods.

The paper tackles catastrophic forgetting in incremental object detection by addressing missing annotations for old classes, proposing a modified knowledge distillation approach that outperforms state-of-the-art methods on Pascal-VOC and extends to instance segmentation.

Despite the recent advances in the field of object detection, common architectures are still ill-suited to incrementally detect new categories over time. They are vulnerable to catastrophic forgetting: they forget what has been already learned while updating their parameters in absence of the original training data. Previous works extended standard classification methods in the object detection task, mainly adopting the knowledge distillation framework. However, we argue that object detection introduces an additional problem, which has been overlooked. While objects belonging to new classes are learned thanks to their annotations, if no supervision is provided for other objects that may still be present in the input, the model learns to associate them to background regions. We propose to handle these missing annotations by revisiting the standard knowledge distillation framework. Our approach outperforms current state-of-the-art methods in every setting of the Pascal-VOC dataset. We further propose an extension to instance segmentation, outperforming the other baselines. Code can be found here: https://github.com/fcdl94/MMA

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes