Text-Guided Modality Correction for Open-Vocabulary Object Detection
Organizations: School of Medical Imaging, Xuzhou Medical University, Xuzhou, 221004, China · School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, 210094, China · College of Information Science and Technology, Nanjing Forestry University, Nanjing, 210037, China
Abstract
Open-vocabulary object detection (OVD) is essential for detecting objects beyond the categories seen during training. Establishing vision-language associations is crucial for recognizing unseen categories, while integrating complementary visual features across levels supports detection at different scales. However, existing methods often provide insufficient textual guidance for object regions, rely on limited cross-modal alignment strategies, and underuse complementary features across levels, limiting their ability to detect unseen categories and objects of varying scales. To address these limitations, we propose a Text-Guided Modality Correction Network (TMCNet) that incorporates textual guidance into region feature extraction, cross-modal alignment, and multi-scale decoding to strengthen region-category semantic correspondence and promote complementary feature fusion across levels. First, a text-guided modality encoder incorporates textual semantics into queries to guide regional feature aggregation, reducing semantic ambiguity in object representations. Second, a cross-modal alignment module strengthens the correspondence between region representations and category semantics through interactions between visual and textual features. Finally, a progressive text correction decoder combines a top-down pathway with lateral connections to progressively fuse text-guided deep semantic features with shallow visual features at the corresponding scales, preserving both semantic information and spatial detail for objects of different sizes. Experiments on two public datasets, COCO-OVD and LVIS-OVD, demonstrate that TMCNet achieves strong performance in open-vocabulary object detection using simple text queries as guidance. Extending TMCNet to open-vocabulary segmentation also yields performance gains, demonstrating its cross-task applicability and extensibility.
Figures & tables
| Detection-adapted Baseline | VLM | Feature backbone | TGME | CMAP | PTCD | COCO-OVD(%) | ||
| AP | AP | AP | ||||||
| OVSeg-OVD ∗ | ViT-B/16 | ResNet-101c | ✗ | ✗ | ✗ | 33.70 | 53.70 | 49.30 |
| ViT-B/16 | ResNet-101c | ✓ | ✗ | ✗ | 37.90 {}_{\color[rgb]{1,0,0}\textrm{+4.20}} | 58.00 | 52.80 | |
| ViT-B/16 | ResNet-101c | ✗ | ✓ | ✗ | 35.10 {}_{\color[rgb]{1,0,0}\textrm{+1.40}} | 55.20 | 51.40 | |
| ViT-B/16 | ResNet-101c | ✓ | ✓ | ✗ | 38.50 {}_{\color[rgb]{1,0,0}\textrm{+4.80}} | 58.20 | 53.00 | |
| ViT-B/16 | ResNet-101c | ✓ | ✓ | ✓ | 39.20 {}_{\color[rgb]{1,0,0}\textrm{+5.50}} | 58.50 | 53.30 | |
| Detection-adapted Baseline | VLM | Feature backbone | TGME | CMAP | PTCD | LVIS-OVD(%) | |||
| AP r | AP c | AP f | mAP | ||||||
| OVSeg-OVD ∗ | ViT-B/16 | ResNet-101c | ✗ | ✗ | ✗ | 22.40 | 28.30 | 36.00 | 32.40 |
| ViT-B/16 | ResNet-101c | ✓ | ✗ | ✗ | 24.90 {}_{\color[rgb]{1,0,0}\textrm{+2.50}} | 30.70 | 38.20 | 34.50 | |
| ViT-B/16 | ResNet-101c | ✗ | ✓ | ✗ | 23.80 {}_{\color[rgb]{1,0,0}\textrm{+1.40}} | 29.50 | 37.40 | 33.70 | |
| ViT-B/16 | ResNet-101c | ✓ | ✓ | ✗ | 26.1 {}_{\color[rgb]{1,0,0}\textrm{+3.70}} | 31.90 | 39.50 | 36.00 | |
| ViT-B/16 | ResNet-101c | ✓ | ✓ | ✓ | 26.70 {}_{\color[rgb]{1,0,0}\textrm{+4.30}} | 37.10 | 40.00 | 36.50 | |
| Methods | RTM | CAF | TGME | COCO-OVD(%) | LVIS-OVD(%) | |||||
| AP | AP | AP | AP r | AP c | AP f | mAP | ||||
| OVSeg-OVD ∗ | ✗ | ✗ | ✗ | 33.70 | 53.70 | 49.30 | 22.40 | 28.30 | 36.00 | 32.40 |
| TMCNet OVSeg | ✓ | ✗ | ✗ | 37.00 {}_{\color[rgb]{1,0,0}\textrm{+3.30}} | 56.50 | 51.00 | 23.60 {}_{\color[rgb]{1,0,0}\textrm{+1.20}} | 33.70 | 36.90 | 33.40 |
| ✗ | ✓ | ✗ | 37.70 {}_{\color[rgb]{1,0,0}\textrm{+4.00}} | 57.00 | 51.50 | 23.90 {}_{\color[rgb]{1,0,0}\textrm{+1.50}} | 34.10 | 37.30 | 33.80 | |
| ✗ | ✗ | ✓ | 39.20 {}_{\color[rgb]{1,0,0}\textrm{+5.50}} | 58.50 | 53.30 | 26.70 {}_{\color[rgb]{1,0,0}\textrm{+4.30}} | 37.10 | 40.00 | 36.50 | |
| SED-OVD ∗ | ✓ | ✗ | ✗ | 36.10 | 54.20 | 49.90 | 24.80 | 34.50 | 38.00 | 34.00 |
| Methods | CLIP | LP | CMAP | COCO-OVD(%) | LVIS-OVD(%) | |||||
| AP | AP | AP | AP r | AP c | AP f | mAP | ||||
| OVSeg-OVD ∗ | ✓ | ✗ | ✗ | 33.70 | 53.70 | 49.30 | 22.40 | 28.30 | 36.00 | 32.40 |
| TMCNet OVSeg | ✓ | ✗ | ✗ | 37.50 {}_{\color[rgb]{1,0,0}\textrm{+3.80}} | 57.10 | 51.60 | 24.00 {}_{\color[rgb]{1,0,0}\textrm{+1.60}} | 34.10 | 37.60 | 34.10 |
| ✗ | ✓ | ✗ | 38.40 {}_{\color[rgb]{1,0,0}\textrm{+4.70}} | 57.70 | 52.30 | 24.50 {}_{\color[rgb]{1,0,0}\textrm{+2.10}} | 34.60 | 38.00 | 34.50 | |
| ✗ | ✗ | ✓ | 39.20 {}_{\color[rgb]{1,0,0}\textrm{+5.50}} | 58.50 | 53.30 | 26.70 {}_{\color[rgb]{1,0,0}\textrm{+4.30}} | 37.10 | 40.00 | 36.50 | |
| SED-OVD ∗ | - | ✗ | ✗ | 36.10 | 54.20 | 49.90 | 24.80 | 34.50 | 38.00 | 34.00 |
| Detection-adapted Methods | CLIP | Def_DETR | CLIP_Trans | COCO-OVD(%) | LVIS-OVD(%) | |||||
| AP | AP | AP | AP r | AP c | AP f | mAP | ||||
| TMCNet OVSeg | ✓ | ✗ | ✗ | 38.00 | 57.30 | 52.00 | 24.00 | 34.00 | 37.30 | 33.50 |
| ✗ | ✓ | ✗ | 38.80 | 58.00 | 52.80 | 24.90 | 35.00 | 38.20 | 34.60 | |
| ✗ | ✗ | ✓ | 39.20 {}_{\color[rgb]{1,0,0}\textrm{+1.20}} | 58.50 | 53.30 | 26.70 {}_{\color[rgb]{1,0,0}\textrm{+4.30}} | 37.10 | 40.00 | 36.50 | |
| TMCNet SED | ✓ | ✗ | ✗ | 39.40 | 58.50 | 52.90 | 25.50 | 35.20 | 38.80 | 34.80 |
| ✗ | ✓ | ✗ | 40.70 | 59.90 | 54.30 | 26.00 | 35.90 | 39.40 | 35.50 | |
| Methods | Publication | Train Setting | Backbone | detectors | COCO-OVD(%) | ||
| AP | AP | AP | |||||
| OVR-CNN [ 45 ] † | CVPR’21 | V-OVD | RN50-C4 | Faster R-CNN | 22.80 | 46.00 | 39.90 |
| BARON [ 36 ] † | CVPR’23 | V-OVD | RN50-C4 | Faster R-CNN | 33.10 | 54.80 | 49.10 |
| BIND [ 46 ] † | CVPR’24 | V-OVD | ViT-B/16 | Built-in detector | 36.30 | 54.70 | 50.20 |
| CAKE [ 30 ] † | AAAI’25 | V-OVD | RN50 | Faster R-CNN | 38.20 | 58.00 | 52.80 |
| RegionCLIP [ 48 ] † | CVPR’22 | C-OVD | RN50-C4 | CLIP | 26.80 | 54.80 | 47.50 |
| Methods | Publication | Backbone | detectors | LVIS-OVD(%) | Inf. time (ms/image) | |||
| AP r | AP c | AP f | mAP | |||||
| OV-DETR [ 44 ] † | ECCV’22 | RN50 | Def_DETR | 21.00 | 25.00 | 32.50 | 26.60 | 574.20 |
| BIND [ 46 ] † | CVPR’24 | ViT-B/16 | Built-in detector | 29.40 | 30.60 | 33.50 | 31.40 | 42.60 |
| SAS-Det [ 47 ] † | CVPR’24 | RN50-C4 | Faster R-CNN | 20.90 | 26.10 | 31.60 | 27.40 | 71.20 |
| CAKE [ 30 ] † | AAAI’25 | RN50 | Faster R-CNN | 25.00 | 34.80 | 38.40 | 34.90 | 35.80 |
| MSPL [ 8 ] † | ECCV’26 | RN50-FPN | Faster R-CNN | 25.00 | 33.30 | 37.20 | 33.50 | - |
| Methods | VLM | Feature backbone | Train Dataset | A-847 | PC-459 | A-150 | PC-59 | PAS-20 |
| OVSeg [ 20 ] † | ViT-B/16 | Swin-B | COCO-Stuff-171 | 7.10 | 11.00 | 24.80 | 53.30 | 92.60 |
| TMCNet OVSeg | ViT-B/16 | Swin-B | COCO-Stuff-171 | 9.10 {}_{\color[rgb]{1,0,0}\textrm{+2.00}} | 14.20 {}_{\color[rgb]{1,0,0}\textrm{+3.20}} | 30.90 {}_{\color[rgb]{1,0,0}\textrm{+6.10}} | 55.70 {}_{\color[rgb]{1,0,0}\textrm{+2.40}} | 95.40 {}_{\color[rgb]{1,0,0}\textrm{+2.80}} |
| SED [ 39 ] † | ConvNeXt-B | - | COCO-Stuff-171 | 8.90 | 12.40 | 31.20 | 47.30 | 93.70 |
| TMCNet SED | ConvNeXt-B | - | COCO-Stuff-171 | 11.40 {}_{\color[rgb]{1,0,0}\textrm{+2.50}} | 16.70 {}_{\color[rgb]{1,0,0}\textrm{+4.30}} | 32.80 {}_{\color[rgb]{1,0,0}\textrm{+1.60}} | 57.40 {}_{\color[rgb]{1,0,0}\textrm{+10.10}} | 95.30 {}_{\color[rgb]{1,0,0}\textrm{+1.60}} |
| Methods | Publication | VLM | Training Dataset | A-847 | PC-459 | A-150 | PC-59 | PAS-20 |
| ZegFormer [ 9 ] | CVPR’22 | ViT-B/16 | COCO-Stuff-156 | 4.90 | 9.10 | 16.90 | 42.80 | 86.20 |
| ZSseg [ 41 ] | ECCV’22 | ViT-B/16 | COCO-Stuff-171 | 7.00 | – | 20.50 | 47.70 | 88.40 |
| OVSeg [ 20 ] | CVPR’23 | ViT-B/16 | COCO-Stuff-171 | 7.10 | 11.00 | 24.80 | 53.30 | 92.60 |
| SED [ 39 ] † | CVPR’24 | ConvNeXt-B | COCO-Stuff-171 | 8.90 | 12.40 | 31.20 | 47.30 | 93.70 |
| CAT-Seg + DeCLIP [ 35 ] † | CVPR’25 | ViT-B/16 | COCO-Stuff-171 | 9.50 | 15.40 | 31.30 | 55.60 | 92.60 |
| LoGoSeg [ 3 ] † | AAAI’26 | ConvNeXt-B | COCO-Stuff-171 | 10.20 | 16.30 | 32.00 | 55.80 | 93.00 |
Open-Vocabulary Object Detection
Open-vocabulary object detection lets models locate and label objects using text categories beyond their fixed training labels.
See all 94 papers