DGTRS-CLIP-ViT-L-14

This is the DGTRS-CLIP-ViT-L-14 model. It can be used for a variety of tasks, including zero-shot image classification and text-image retrieval.

This model is compatible with both the transformers and diffusers libraries.

How to use

With transformers

from transformers import CLIPProcessor, CLIPModel
from PIL import Image
import torch

# Load model and processor
model = CLIPModel.from_pretrained("BiliSakura/DGTRS-CLIP-ViT-L-14")
processor = CLIPProcessor.from_pretrained("BiliSakura/DGTRS-CLIP-ViT-L-14")

# Load and process image
image = Image.open("path/to/your/image.jpg")
inputs = processor(
    text=["a photo of a building", "a photo of vegetation", "a photo of water"],
    images=image,
    return_tensors="pt",
    padding=True
)

# Get image-text similarity scores
with torch.inference_mode():
    outputs = model(**inputs)
    logits_per_image = outputs.logits_per_image
    probs = logits_per_image.softmax(dim=1)

print(f"Similarity scores: {probs}")

Zero-shot image classification:

from transformers import CLIPProcessor, CLIPModel
from PIL import Image
import torch

model = CLIPModel.from_pretrained("BiliSakura/DGTRS-CLIP-ViT-L-14")
processor = CLIPProcessor.from_pretrained("BiliSakura/DGTRS-CLIP-ViT-L-14")

# Define candidate labels
candidate_labels = [
    "a satellite image of urban area",
    "a satellite image of forest",
    "a satellite image of agricultural land",
    "a satellite image of water body"
]

image = Image.open("path/to/your/image.jpg")
inputs = processor(
    text=candidate_labels,
    images=image,
    return_tensors="pt",
    padding=True
)

with torch.inference_mode():
    outputs = model(**inputs)
    probs = outputs.logits_per_image.softmax(dim=1)

# Get the predicted label
predicted_idx = probs.argmax().item()
print(f"Predicted label: {candidate_labels[predicted_idx]}")
print(f"Confidence: {probs[0][predicted_idx]:.4f}")

Extracting individual features:

from transformers import CLIPProcessor, CLIPModel
from PIL import Image
import torch

model = CLIPModel.from_pretrained("BiliSakura/DGTRS-CLIP-ViT-L-14")
processor = CLIPProcessor.from_pretrained("BiliSakura/DGTRS-CLIP-ViT-L-14")

# Get image features only
image = Image.open("path/to/your/image.jpg")
image_inputs = processor(images=image, return_tensors="pt")

with torch.inference_mode():
    image_features = model.get_image_features(**image_inputs)

# Get text features only
text_inputs = processor(
    text=["a satellite image of urban area"],
    return_tensors="pt",
    padding=True,
    truncation=True
)

with torch.inference_mode():
    text_features = model.get_text_features(**text_inputs)

print(f"Image features shape: {image_features.shape}")
print(f"Text features shape: {text_features.shape}")

With diffusers

This model's text encoder can be used with Stable Diffusion and other diffusion models:

from diffusers import StableDiffusionPipeline
from transformers import CLIPTextModel, CLIPTokenizer
import torch

# Load the text encoder and tokenizer
text_encoder = CLIPTextModel.from_pretrained(
    "BiliSakura/DGTRS-CLIP-ViT-L-14/diffusers",
    subfolder="text_encoder",
    torch_dtype=torch.float16
)
tokenizer = CLIPTokenizer.from_pretrained(
    "BiliSakura/DGTRS-CLIP-ViT-L-14"
)

# Encode text prompt
prompt = "a satellite image of a city with buildings and roads"
text_inputs = tokenizer(
    prompt,
    padding="max_length",
    max_length=77,
    truncation=True,
    return_tensors="pt"
)

with torch.inference_mode():
    text_outputs = text_encoder(text_inputs.input_ids)
    text_embeddings = text_outputs.last_hidden_state

print(f"Text embeddings shape: {text_embeddings.shape}")

Using with Stable Diffusion:

from diffusers import StableDiffusionPipeline
import torch

# Load pipeline with custom text encoder
pipe = StableDiffusionPipeline.from_pretrained(
    "runwayml/stable-diffusion-v1-5",
    text_encoder=text_encoder,
    tokenizer=tokenizer,
    torch_dtype=torch.float16
)
pipe = pipe.to("cuda")

# Generate image
prompt = "a high-resolution satellite image of urban area"
image = pipe(prompt, num_inference_steps=50, guidance_scale=7.5).images[0]
image.save("generated_image.png")

Citation

If you use this model in your research, please cite the original paper:

@article{chenDGTRSDDGTRSCLIPDualGranularity2025a,
  title = {{{DGTRSD}} and {{DGTRSCLIP}}: {{A Dual-Granularity Remote Sensing Image}}--{{Text Dataset}} and {{Vision}}--{{Language Foundation Model}} for {{Alignment}}},
  shorttitle = {{{DGTRSD}} and {{DGTRSCLIP}}},
  author = {Chen, Weizhi and Deng, Yupeng and Jin, Wei and Chen, Jingbo and Chen, Jiansheng and Feng, Yuman and Xi, Zhihao and Liu, Diyou and Li, Kai and Meng, Yu},
  year = 2025,
  journal = {IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing},
  volume = {18},
  pages = {29113--29130},
  issn = {2151-1535},
  doi = {10.1109/JSTARS.2025.3625958},
  urldate = {2025-12-18},
  keywords = {Buildings,Cross modal retrieval,Cross-modal alignment,curriculum learning,dual-granularity,Green buildings,Integrated circuit modeling,remote sensing,Remote sensing,Resource management,Semantics,Sports,Training,vision-language foundation models (VLFM),Visualization}
}