Parameterized Prompt for Incremental Object Detection

TL;DR

This paper introduces P$^2$IOD, a novel prompt-based method for incremental object detection that adaptively consolidates knowledge across tasks and handles co-occurrence scenarios, achieving state-of-the-art results.

Contribution

The paper proposes a parameterized prompt framework with a fusion strategy for incremental object detection, addressing co-occurrence challenges and preventing catastrophic forgetting.

Findings

P$^2$IOD outperforms existing methods on PASCAL VOC2007 and MS COCO datasets.

The approach effectively handles co-occurring objects in incremental detection tasks.

State-of-the-art performance achieved among baseline methods.

Abstract

Recent studies have demonstrated that incorporating trainable prompts into pretrained models enables effective incremental learning. However, the application of prompts in incremental object detection (IOD) remains underexplored. Our study reveals that existing prompt-pool-based approaches assume disjoint class sets across incremental tasks, which are unsuitable for IOD as they overlook the inherent co-occurrence phenomenon in detection. In co-occurring scenarios, unlabeled objects from previous tasks may appear in current task images, leading to confusion in prompts pool. In this paper, we hold that prompt structures should exhibit adaptive consolidation properties across tasks, with constrained updates to prevent confusion and catastrophic forgetting. Motivated by this, we introduce Parameterized Prompts for Incremental Object Detection (P$^2$IOD). Leveraging neural networks global evolution properties, P$^2$IOD employs networks as the parameterized prompts to adaptively consolidate knowledge across tasks. To constrain prompts structure updates, P$^2$IOD further engages a parameterized prompts fusion strategy. Extensive experiments on PASCAL VOC2007 and MS COCO datasets demonstrate that P$^2$IOD's effectiveness in IOD and achieves the state-of-the-art performance among existing baselines. Code is available at https://github.com/EMLS-ICTCAS/P2IOD.