Saved in:
Bibliographic Details
Main Authors: Chen, Zhiyuan, Guo, Yuelin, Huang, Zitong, He, Haoyu, Lu, Renhao, Zhang, Weizhe
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.08018
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914150615089152
author Chen, Zhiyuan
Guo, Yuelin
Huang, Zitong
He, Haoyu
Lu, Renhao
Zhang, Weizhe
author_facet Chen, Zhiyuan
Guo, Yuelin
Huang, Zitong
He, Haoyu
Lu, Renhao
Zhang, Weizhe
contents Object detection models demand large-scale annotated datasets, which are costly and labor-intensive to create. This motivated Imaginary Supervised Object Detection (ISOD), where models train on synthetic images and test on real images. However, existing methods face three limitations: (1) synthetic datasets suffer from simplistic prompts, poor image quality, and weak supervision; (2) DETR-based detectors, due to their random query initialization, struggle with slow convergence and overfitting to synthetic patterns, hindering real-world generalization; (3) uniform denoising pressure promotes model overfitting to pseudo-label noise. We propose Cascade HQP-DETR to address these limitations. First, we introduce a high-quality data pipeline using LLaMA-3, Flux, and Grounding DINO to generate the FluxVOC and FluxCOCO datasets, advancing ISOD from weak to full supervision. Second, our High-Quality Proposal guided query encoding initializes object queries with image-specific priors from SAM-generated proposals and RoI-pooled features, accelerating convergence while steering the model to learn transferable features instead of overfitting to synthetic patterns. Third, our cascade denoising algorithm dynamically adjusts training weights through progressively increasing IoU thresholds across decoder layers, guiding the model to learn robust boundaries from reliable visual cues rather than overfitting to noisy labels. Trained for just 12 epochs solely on FluxVOC, Cascade HQP-DETR achieves a SOTA 61.04\% mAP@0.5 on PASCAL VOC 2007, outperforming strong baselines, with its competitive real-data performance confirming the architecture's universal applicability.
format Preprint
id arxiv_https___arxiv_org_abs_2511_08018
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle High-Quality Proposal Encoding and Cascade Denoising for Imaginary Supervised Object Detection
Chen, Zhiyuan
Guo, Yuelin
Huang, Zitong
He, Haoyu
Lu, Renhao
Zhang, Weizhe
Computer Vision and Pattern Recognition
Object detection models demand large-scale annotated datasets, which are costly and labor-intensive to create. This motivated Imaginary Supervised Object Detection (ISOD), where models train on synthetic images and test on real images. However, existing methods face three limitations: (1) synthetic datasets suffer from simplistic prompts, poor image quality, and weak supervision; (2) DETR-based detectors, due to their random query initialization, struggle with slow convergence and overfitting to synthetic patterns, hindering real-world generalization; (3) uniform denoising pressure promotes model overfitting to pseudo-label noise. We propose Cascade HQP-DETR to address these limitations. First, we introduce a high-quality data pipeline using LLaMA-3, Flux, and Grounding DINO to generate the FluxVOC and FluxCOCO datasets, advancing ISOD from weak to full supervision. Second, our High-Quality Proposal guided query encoding initializes object queries with image-specific priors from SAM-generated proposals and RoI-pooled features, accelerating convergence while steering the model to learn transferable features instead of overfitting to synthetic patterns. Third, our cascade denoising algorithm dynamically adjusts training weights through progressively increasing IoU thresholds across decoder layers, guiding the model to learn robust boundaries from reliable visual cues rather than overfitting to noisy labels. Trained for just 12 epochs solely on FluxVOC, Cascade HQP-DETR achieves a SOTA 61.04\% mAP@0.5 on PASCAL VOC 2007, outperforming strong baselines, with its competitive real-data performance confirming the architecture's universal applicability.
title High-Quality Proposal Encoding and Cascade Denoising for Imaginary Supervised Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.08018