Llmdet Base
LLMDet model was proposed in [LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models ]( by Shenghao Fu, Qize Yang, Qijie Mo, Junkai Yan, Xihan Wei, Jingke Meng,...
Model source
- Kind
- Other
- File size
- 893 MB
- Version
- vRevision 3537869
- Updated
- Oct 10, 2026
- Downloads
- 95.5K
- Source
- Hugging Face
Source description
LLMDet (base variant)
LLMDet model was proposed in LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models by Shenghao Fu, Qize Yang, Qijie Mo, Junkai Yan, Xihan Wei, Jingke Meng, Xiaohua Xie, Wei-Shi Zheng.
LLMDet improves upon the MM Grounding DINO and Grounding DINO by co-training the model with a large language model.
You can find all the LLMDet checkpoints under the LLMDet collection. Note that these checkpoints are inference only -- they do not include LLM which was used for training. The inference is identical to that of MM Grounding DINO.
Intended uses
You can use the raw model for zero-shot object detection.
Here's how to use the model for zero-shot object detection:
import torch
from transformers import AutoModelForZeroShotObjectDetection, AutoProcessor
from transformers.image_utils import load_image
# Prepare processor and model
model_id = "iSEE-Laboratory/llmdet_base"
device = "cuda" if torch.cuda.is_available() else "cpu"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForZeroShotObjectDetection.from_pretrained(model_id).to(device)
# Prepare inputs
image_url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = load_image(image_url)
text_labels = [["a cat", "a remote control"]]
inputs = processor(images=image, text=text_labels, return_tensors="pt").to(device)
# Run inference
with torch.no_grad():
outputs = model(**inputs)
# Postprocess outputs
results = processor.post_process_grounded_object_detection(
outputs,
threshold=0.4,
target_sizes=[(image.height, image.width)]
)
# Retrieve the first image result
result = results[0]
for box, score, labels in zip(result["boxes"], result["scores"], result["labels"]):
box = [round(x, 2) for x in box.tolist()]
print(f"Detected {labels} with confidence {round(score.item(), 3)} at location {box}")
Training Data
This model was trained on:
Evaluation results
-
Here's a table of LLMDet models and their performance on LVIS (results from official repo):
Model Pre-Train Data MiniVal APr MiniVal APc MiniVal APf MiniVal AP Val1.0 APr Val1.0 APc Val1.0 APf Val1.0 AP llmdet_tiny (O365,GoldG,GRIT,V3Det) + GroundingCap-1M 44.7 37.3 39.5 50.7 34.9 26.0 30.1 44.3 llmdet_base (O365,GoldG,V3Det) + GroundingCap-1M 48.3 40.8 43.1 54.3 38.5 28.2 34.3 47.8 llmdet_large (O365V2,OpenImageV6,GoldG) + GroundingCap-1M 51.1 45.1 46.1 56.6 42.0 31.6 38.8 50.2
BibTeX entry and citation info
@article{fu2025llmdet,
title={LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models},
author={Fu, Shenghao and Yang, Qize and Mo, Qijie and Yan, Junkai and Wei, Xihan and Meng, Jingke and Xie, Xiaohua and Zheng, Wei-Shi},
journal={arXiv preprint arXiv:2501.18954},
year={2025}
}
Sources
1 source
Sources
1 sourceVerified Oct 10
Model artifacts
1 artifact
Model artifacts
1 artifactSource excerpts
3 excerpts
Source excerpts
3 excerpts--- library_name: transformers tags: - vision license: apache-2.0 pipeline_tag: zero-shot-object-detection --- # LLMDet (base variant) [LLMDet](https://arxiv.org/abs/2501.18954) model was proposed in [LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models ](https://arxiv.org/abs/2501.18954) by Shenghao Fu, Qize Yang, Qijie Mo, Junkai Yan, Xihan Wei, Jingke Meng, Xiaohua Xie, Wei-Shi Zheng. LLMDet improves upon the [MM Grounding DINO](https://huggingface.co/docs/transformers/model_doc/mm-grounding-dino) and [Grounding DINO](https://huggingface.co/docs/transformers/model_doc/grounding-dino) by co-training the model with a large language model. You can find all the LLMDet checkpoints under the [LLMDet](https://huggingface.co/collections/rziga/llmdet-68398b294d9866c16046dcdd) collection. Note that these checkpoints are inference only -- they do not include LLM which was used for training. The inference is identical to that of [MM Grounding DINO](https://huggingface.co/docs/transformers/model_doc/mm-grounding-dino). ## Intended uses You can use the raw model for zero-shot object detection. Here's how to use the model for zero-shot object detection: ```py import torch from transformers import AutoModelForZeroShotObjectDetection, AutoProcessor from transformers.image_utils import load_image # Prepare processor and model model_id = "iSEE-Laboratory/llmdet_base" device = "cuda" if torch.cuda.is_available() else "cpu" processor = AutoProcessor.from_pretrained(model_id) model = AutoModelForZeroShotObjectDetection.from_pretrained(model_id).to(device) # Prepare inputs image_url = "http://images.cocodataset.org/val2017/000000039769.jpg" image = load_image(image_url) text_labels = [["a cat", "a remote control"]] inputs = processor(images=image, text=text_labels, return_tensors="pt").to(device) # Run inference with torch.no_grad(): outputs = model(**inputs) # Postprocess outputs results = processor.post_process_grounded_object_detection( outputs, threshold=0.4, target_sizes=[(image.height, image.width)] ) # Retrieve the first image result result = results[0] for box, score, labels in zip(result["boxes"], result["scores"], result["labels"]): box = [round(x, 2) for x in box.tolist()] print(f"Detected {labels} with confidence {round(score.item(), 3)} at location {box}") ``` ## Training Data This model was...
Source context: 95514 downloads · 10 likes · Pipeline zero-shot-object-detection · Library transformers · Repo iSEE-Laboratory/llmdet_base
Source context: 62713 downloads · 10 likes · Pipeline zero-shot-object-detection · Library transformers · Repo iSEE-Laboratory/llmdet_base
