Class-Incremental learning (CIL) is the ability of artificial agents to
accommodate new classes as they appear in a stream. It is particularly
interesting in evolving environments where agents have limited access to memory
and computational resources. The main challenge of class-incremental learning
is catastrophic forgetting, the inability of neural networks to retain past
knowledge when learning a new one. Unfortunately, most existing
class-incremental object detectors are applied to two-stage algorithms such as
Faster-RCNN and rely on rehearsal memory to retain past knowledge. We believe
that the current benchmarks are not realistic, and more effort should be
dedicated to anchor-free and rehearsal-free object detection. In this context,
we propose MultIOD, a class-incremental object detector based on CenterNet. Our
main contributions are: (1) we propose a multihead feature pyramid and
multihead detection architecture to efficiently separate class representations,
(2) we employ transfer learning between classes learned initially and those
learned incrementally to tackle catastrophic forgetting, and (3) we use a
class-wise non-max-suppression as a post-processing technique to remove
redundant boxes. Without bells and whistles, our method outperforms a range of
state-of-the-art methods on two Pascal VOC datasets.

基于 CenterNet 的 MultIOD 是一种无需复习和复述的类增量目标检测器，通过多头特征金字塔和多头检测架构高效分离类别表示，利用迁移学习和类别非极大值抑制技术解决灾难性遗忘问题，并在两个 Pascal VOC 数据集上显著优于一系列最先进的方法。

MultIOD：免重复训练的多头增量目标检测器

MultIOD: Rehearsal-free Multihead Incremental Object Detector

Continual learning describes a setting where machine learning models learn
novel concepts from continuously shifting training data, while simultaneously
avoiding degradation of knowledge on previously seen classes (a phenomenon
known as the catastrophic forgetting problem) which may disappear from the
training data for extended periods of time. Current approaches for continual
learning of a single expanding task (aka class-incremental continual learning)
require extensive rehearsal of previously seen data to avoid this degradation
of knowledge. Unfortunately, rehearsal comes at a sharp cost to memory and
computation, and it may also violate data-privacy. Instead, we explore
combining knowledge distillation and parameter regularization in new ways to
achieve strong continual learning performance without rehearsal. Specifically,
we take a deep dive into common continual learning techniques: prediction
distillation, feature distillation, L2 parameter regularization, and EWC
parameter regularization. We first disprove the common assumption that
parameter regularization techniques fail for rehearsal-free continual learning
of a single, expanding task. Next, we explore how to leverage knowledge from a
pre-trained model in rehearsal-free continual learning and find that vanilla L2
parameter regularization outperforms EWC parameter regularization and feature
distillation. We then highlight the impact of the rehearsal-free continual
learning settings with a classifier expansion benchmark, showing that a
strategy based on our findings combined with a positive/negative label
balancing heuristic can close the performance gap between the upper bound and
the existing strategies by up to roughly 50%. Finally, we show that a simple
method consisting of pre-training, L2 regularization, and prediction
distillation can even outperform rehearsal-based methods on the common
CIFAR-100 benchmark.

通过知识蒸馏和参数正则化的组合，并探索加入预训练模型的方法，实现了单一，逐步扩展任务的无需回忆连续学习，避免遗忘以前学过的类别并不断优化性能。