Parameterized Prompt for Incremental Object Detection
This work addresses incremental learning for object detection, a domain-specific problem in computer vision, by proposing a novel prompt-based method to handle co-occurring classes, representing an incremental improvement over existing approaches.
The paper tackles the problem of incremental object detection (IOD) by addressing the limitations of existing prompt-based methods that assume disjoint class sets, which fail in co-occurring scenarios. It introduces Parameterized Prompts for IOD (P^2IOD), which uses neural networks as adaptive prompts to consolidate knowledge across tasks, achieving state-of-the-art performance on PASCAL VOC2007 and MS COCO datasets.
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. Existing prompts 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 images. 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 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.