MSPL: Multi-Step Pseudo-Labeling for Open-Vocabulary Object Detection

2025-10-16 · Hojun Choi, Youngsun Lim, Jaeyo Shin, Hyunjung Shim arxiv

Open-vocabulary object detection (OVD) aims to recognize and localize object categories beyond the training set. Recent approaches leverage vision-language models to generate pseudo-labels using image-text alignment, allowing detectors to generalize to unseen classes without explicit supervision. However, these methods depend heavily on single-step image-text matching, neglecting the intermediate reasoning steps crucial for interpreting semantically complex visual contexts, such as crowding or occlusion. In this paper, we introduce MSPL, a framework that incorporates multi-step visual reasoning into the pseudo-labeling process for OVD. It decomposes complex scene understanding into three interpretable steps-object localization, category recognition, and background grounding-where these intermediate reasoning states serve as rich supervision sources. Extensive experiments on standard OVD evaluation protocols demonstrate that MSPL achieves state-of-the-art performance with superior pseudo-labeling efficiency, outperforming the strong baseline by 9.4 AP50 for novel classes on OV-COCO and improving box and mask APr by 3.2 and 2.2, respectively, on OV-LVIS. Code and models are available at https://github.com/hchoi256/mspl.

📄 PDF Abstract BibTeX arXiv:2510.14792

Code (0)

등록된 구현이 없습니다.

Tasks

Object Localization Image-text matching Scene Understanding Object Detection

One-Shot Federated Unsupervised Domain Adaptation with Scaled Entropy Attention and Multi-Source Smoothed Pseudo Labeling

2025-03-13 · Ali Abedi, Q. M. Jonathan Wu, Ning Zhang, Farhad Pourpanah

Federated Learning (FL) is a promising approach for privacy-preserving collaborative learning. However, it faces significant challenges when dealing with domain shifts, especially when each client has access only to its …

Domain Adaptation Federated Learning Privacy Preserving Unsupervised Domain Adaptation

Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labeling

2021-11-24 · CVPR 2022 1 · Dat Huynh, Jason Kuen, Zhe Lin, Jiuxiang Gu 외

Open-vocabulary instance segmentation aims at segmenting novel classes without mask annotations. It is an important step toward reducing laborious human supervision. Most existing works first pretrain a model on captione…

Instance Segmentation Semantic Segmentation

Learning Pseudo-Labeler beyond Noun Concepts for Open-Vocabulary Object Detection

2023-12-04 · Sunghun Kang, Junbum Cha, Jonghwan Mun, Byungseok Roh 외

Open-vocabulary object detection (OVOD) has recently gained significant attention as a crucial step toward achieving human-like visual intelligence. Existing OVOD methods extend target vocabulary from pre-defined categor…

Image to text object-detection Object Detection Open-vocabulary object detection+3

Integrating splice-isoform expression into genome-scale models characterizes breast cancer metabolism

2018-09-21

Motivation: Despite being often perceived as the main contributors to cell fate and physiology, genes alone cannot predict cellular phenotype. During the process of gene expression, 95% of human genes can code for multip…

PseudoAugment: Learning to Use Unlabeled Data for Data Augmentation in Point Clouds

2022-10-24 · Zhaoqi Leng, Shuyang Cheng, Benjamin Caine, Weiyue Wang 외

Data augmentation is an important technique to improve data efficiency and save labeling cost for 3D detection in point clouds. Yet, existing augmentation policies have so far been designed to only utilize labeled data, …

Data Augmentation Pseudo Label vehicle detection