paper-with-me

홈 › Papers

Incremental Object Detection with Prompt-based Methods

2025-08-20 · Matthias Neuwirth-Trapp, Maarten Bieshaar, Danda Pani Paudel, Luc Van Gool arxiv

Visual prompt-based methods have seen growing interest in incremental learning (IL) for image classification. These approaches learn additional embedding vectors while keeping the model frozen, making them efficient to train. However, no prior work has applied such methods to incremental object detection (IOD), leaving their generalizability unclear. In this paper, we analyze three different prompt-based methods under a complex domain-incremental learning setting. We additionally provide a wide range of reference baselines for comparison. Empirically, we show that the prompt-based approaches we tested underperform in this setting. However, a strong yet practical method, combining visual prompts with replaying a small portion of previous data, achieves the best results. Together with additional experiments on prompt length and initialization, our findings offer valuable insights for advancing prompt-based IL in IOD.

📄 PDF Abstract BibTeX arXiv:2508.14599

Code (0)

등록된 구현이 없습니다.

Tasks

Incremental LearningImage ClassificationObject Detection

Similar Papers 제목 키워드 기반

I3DOD: Towards Incremental 3D Object Detection via Prompting

2023-08-24 · Wenqi Liang, Gan Sun, Chenxi Liu, Jiahua Dong 외

3D object detection has achieved significant performance in many fields, e.g., robotics system, autonomous driving, and augmented reality. However, most existing methods could cause catastrophic forgetting of old classes…

3D Object DetectionAutonomous DrivingObjectobject-detection+2

Parameterized Prompt for Incremental Object Detection

2025-10-31 · Zijia An, Boyu Diao, Ruiqi Liu, Libo Huang 외 arxiv

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 under…

Incremental LearningObject Detection

Beyond Prompt Degradation: Prototype-guided Dual-pool Prompting for Incremental Object Detection

2026-03-02 · Yaoteng Zhang, Zhou Qing, Junyu Gao, Qi Wang arxiv

Incremental Object Detection (IOD) aims to continuously learn new object categories without forgetting previously learned ones. Recently, prompt-based methods have gained popularity for their replay-free design and param…

General KnowledgeObject Detection

iDPA: Instance Decoupled Prompt Attention for Incremental Medical Object Detection

2025-05-31 · Huahui Yi, Wei Xu, Ziyuan Qin, Xi Chen 외

Existing prompt-based approaches have demonstrated impressive performance in continual learning, leveraging pre-trained large-scale models for classification tasks; however, the tight coupling between foreground-backgrou…

Continual LearningMedical Object Detectionobject-detectionObject Detection

Not Just Object, But State: Compositional Incremental Learning without Forgetting

2024-11-04 · Yanyi Zhang, Binglin Qiu, Qi Jia, Yu Liu 외

Most incremental learners excessively prioritize coarse classes of objects while neglecting various kinds of states (e.g. color and material) attached to the objects. As a result, they are limited in the ability to reaso…

DiversityIncremental LearningObjectPrompt Learning