Overcoming Prompts Pool Confusion via Parameterized Prompt for Incremental Object Detection
By: Zijia An , Boyu Diao , Ruiqi Liu and more
Potential Business Impact:
Teaches computers to recognize new things without forgetting old ones.
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.
Similar Papers
Incremental Object Detection with Prompt-based Methods
CV and Pattern Recognition
Teaches computers to find new things in pictures.
Hierarchical Prompt Learning for Image- and Text-Based Person Re-Identification
CV and Pattern Recognition
Find people in photos using pictures or words.
Retrieval-Augmented Prompt for OOD Detection
CV and Pattern Recognition
Helps computers spot weird pictures they haven't seen.