Incremental Object Detection with Prompt-based Methods

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Neuwirth-Trapp, Matthias, Bieshaar, Maarten, Paudel, Danda Pani, Van Gool, Luc
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911194669907968
author Neuwirth-Trapp, Matthias
Bieshaar, Maarten
Paudel, Danda Pani
Van Gool, Luc
author_facet Neuwirth-Trapp, Matthias
Bieshaar, Maarten
Paudel, Danda Pani
Van Gool, Luc
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_14599
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Incremental Object Detection with Prompt-based Methods
Neuwirth-Trapp, Matthias
Bieshaar, Maarten
Paudel, Danda Pani
Van Gool, Luc
Computer Vision and Pattern Recognition
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.
title Incremental Object Detection with Prompt-based Methods
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.14599