TIPSv2 (CVPR'26) and TIPS (ICLR'25)
-
Updated
Aug 31, 2026 - Jupyter Notebook
#
vision-encoder
Here are 20 public repositories matching this topic...
OpenVision (ICCV 2025), OpenVision 2 (CVPR 2026), and OpenVision 3
-
Updated
Aug 22, 2026 - Python
timm, evolved
-
Updated
May 28, 2026 - Python
A Gradio-based demonstration for the AllenAI Molmo2-8B multimodal model, enabling image QA, multi-image pointing, video QA, and temporal tracking. Users upload images or videos, provide natural language prompts.
natural-language-processing pillow torch python3 pytorch vqa matplotlib gradio multimodal torchvision huggingface-transformers huggingface-spaces vision-language-model vlms multi-image-understanding vision-encoder allenai molmo2
-
Updated
May 25, 2026 - Python
[NeurIPS 2026] Implementation of the paper "Vision Correlators: Correlation-Driven Visual Understanding with Hypergraphs".
-
Updated
Sep 27, 2026 - Python
This demonstrates the process of adapting a large scale pretrained model, MetaCLIP 2, for fine tuning a specific downstream task: image classification.
facebook torch pytorch accelerate clip evaluate metaai huggingface-transformers vision-transformer huggingface-models huggingface-datasets metaclip vision-encoder metaclip-2
-
Updated
Nov 15, 2025 - Jupyter Notebook
Coral-Health is an image classification vision-language encoder model fine-tuned from google/siglip2-base-patch16-224 for a single-label classification task. It is designed to classify coral reef images into two health conditions using the SiglipForImageClassification architecture.
-
Updated
Apr 28, 2025 - Python
Flood-Image-Detection is a vision-language encoder model fine-tuned from google/siglip2-base-patch16-512 for binary image classification. It is trained to detect whether an image contains a flooded scene or non-flooded environment. The model uses the SiglipForImageClassification architecture.
google disaster flood gradio flooding huggingface-transformers vision-transformer vision-encoder siglip2
-
Updated
May 27, 2025 - Python
Multilabel-GeoSceneNet is a vision-language encoder model fine-tuned from google/siglip2-base-patch16-224 for multi-label image classification. It is designed to recognize and label multiple geographic or environmental elements in a single image using the SiglipForImageClassification architecture.
map geospatial landscape spaces gradio huggingface-transformers hugging-face siglip vision-encoder siglip2 geoscenenet
-
Updated
Apr 23, 2025 - Python
Self-supervised monocular depth estimation using a Vision Transformers [Encoder, multi-scale CNN decoder, pose estimation, and differentiable view reconstruction].
computer-vision supervised-learning optical-flow depth-maps kitti-dataset monocular-depth-estimation vision-transformers vision-transformer-image-classification depth-anything vision-encoder
-
Updated
Sep 6, 2026 - Python
Multilabel-Portrait-SigLIP2 is a vision-language model fine-tuned from google/siglip2-base-patch16-224 using the SiglipForImageClassification architecture. It classifies portrait-style images into one of the following visual portrait categories:
python google autoencoder image-classification gradio multilabel-classification portraits huggingface-transformers vision-transformer vision-encoder siglip2
-
Updated
Apr 16, 2025 - Python
shoe-type-detection is a vision-language encoder model fine-tuned from google/siglip2-base-patch16-512 for multi-class image classification. It is trained to detect different types of shoes such as Ballet Flats, Boat Shoes, Brogues, Clogs, and Sneakers. The model uses the SiglipForImageClassification architecture.
google type gradio multiclass-classification shoe huggingface-transformers huggingface-models vision-encoder siglip2
-
Updated
Jun 7, 2025 - Python
Benchmarking SSM Based Image Encoder Performance in Solar Irradiance Prediction using All-Sky Images
computer-vision swin-transformer convnext vmamba vision-encoder spatial-mamba multi-modal-forecasting solar-irradiance-prediction mambavision
-
Updated
Aug 7, 2026 - Python
Fashion-Product-Usage is a vision-language model fine-tuned from google/siglip2-base-patch16-224 using the SiglipForImageClassification architecture. It classifies fashion product images based on their intended usage context.
google image-classification season gradio clothing huggingface-transformers vision-transformer vision-encoder wearing-time siglip2
-
Updated
Apr 18, 2025 - Python
PussyCat-vs-Doggie-SigLIP2 is an image classification vision-language encoder model fine-tuned from google/siglip2-base-patch16-224 for a single-label classification task. It is designed to classify images as either a cat or a dog using the SiglipForImageClassification architecture.
cat dog prediction classification image-classification gradio huggingface-transformers vision-encoder siglip2
-
Updated
Apr 19, 2025 - Python
Leverage SigLIP 2's capabilities using LitServe.
python deep-learning transformers artificial-intelligence fastapi lightning-ai zero-shot-image-classification siglip litserve vision-encoder
-
Updated
Feb 28, 2025 - Python
Research project for exploring Kazakh Vision Language Models.
transformers fine-tuning large-language-models vision-language-model low-rank-adaptation vision-encoder
-
Updated
Jul 10, 2026 - Python
💠 Ambiente local e aberto, com ferramentas para observar, experimentar, inspecionar e documentar representações visuais de modelos. 💠 Primeira bancada: 🔹 Bancada Visual Qwen3.5-9B: ferramenta local para preparar imagens e sequências e explorar representações da torre visual do Qwen3.5-9B, com os pesos congelados.
python open-source jupyter-notebook transformers embeddings jupyterlab visual-encoding multimodal local-first visual-embeddings representation-analysis qwen vision-encoder codigo-aberto model-inspection qwen3-5
-
Updated
Sep 23, 2026 - Python
Cloudflare Clef 方向的多模态决策模型框架：指针决策头（选项打分替代词表生成）+ 原生视觉编码器 + 置信度校准门控。零依赖纯 Python 参考实现
python reinforcement-learning inference calibration zero-dependency decision-model multimodal llm qwen agentic-ai vision-encoder pointer-head cloudflare-clef
-
Updated
Oct 2, 2026 - Python
Add this topic to your repo
To associate your repository with the vision-encoder topic, visit your repo's landing page and select "manage topics."