Results for "image-segmentation"
100 matches found.
CIDAS/clipseg-rd64-refined
No description available.
ZhengPeng7/BiRefNet
Bilateral Reference for High-Resolution Dichotomous Image Segmentation...
briaai/RMBG-1.4
Developed by: BRIA AI - Model type: Background Removal - License: bria-rmbg-1.4 - The model is released under a Creative Commons license for...
jonathandinu/face-parsing
Developed by: Jonathan Dinu - Model type: Transformer-based semantic segmentation image model - License: non-commercial research and educati...
Xenova/segformer-b0-finetuned-ade-512-512
No description available.
nvidia/segformer-b0-finetuned-ade-512-512
SegFormer consists of a hierarchical Transformer encoder and a lightweight all-MLP decode head to achieve great results on semantic segmenta...
facebook/mask2former-swin-large-cityscapes-semantic
Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding la...
fashn-ai/fashn-human-parser
This model segments human images into 18 semantic categories including body parts (face, hair, arms, hands, legs, feet, torso), clothing ite...
mattmdjaga/segformer_b2_clothes
No description available.
briaai/RMBG-2.0
For production / commercial deployment, use the Bria API — same RMBG-2.0 quality, fully licensed, zero infrastructure: | Use | Self-Hosted (...
shi-labs/oneformer_ade20k_swin_tiny
OneFormer is the first multi-task universal image segmentation framework. It needs to be trained only once with a single universal architect...
nvidia/segformer-b5-finetuned-ade-640-640
SegFormer consists of a hierarchical Transformer encoder and a lightweight all-MLP decode head to achieve great results on semantic segmenta...
nvidia/segformer-b1-finetuned-ade-512-512
SegFormer consists of a hierarchical Transformer encoder and a lightweight all-MLP decode head to achieve great results on semantic segmenta...
shi-labs/oneformer_coco_swin_large
OneFormer is the first multi-task universal image segmentation framework. It needs to be trained only once with a single universal architect...
facebook/mask2former-swin-tiny-coco-instance
Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding la...
shi-labs/oneformer_ade20k_swin_large
OneFormer is the first multi-task universal image segmentation framework. It needs to be trained only once with a single universal architect...
facebook/mask2former-swin-large-ade-semantic
Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding la...
nvidia/segformer-b5-finetuned-cityscapes-1024-1024
SegFormer consists of a hierarchical Transformer encoder and a lightweight all-MLP decode head to achieve great results on semantic segmenta...
PramaLLC/BEN2
No description available.
ZhengPeng7/BiRefNet-portrait
Bilateral Reference for High-Resolution Dichotomous Image Segmentation...
facebook/mask2former-swin-large-mapillary-vistas-semantic
Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding la...
nvidia/segformer-b2-finetuned-ade-512-512
SegFormer consists of a hierarchical Transformer encoder and a lightweight all-MLP decode head to achieve great results on semantic segmenta...
facebook/mask2former-swin-base-coco-panoptic
Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding la...
facebook/detr-resnet-50-panoptic
The DETR model is an encoder-decoder transformer with a convolutional backbone. Two heads are added on top of the decoder outputs in order t...
facebook/mask2former-swin-large-coco-instance
Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding la...
tue-mps/coco_panoptic_eomt_large_640
No description available.
facebook/mask2former-swin-small-coco-instance
Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding la...
nvidia/segformer-b3-finetuned-ade-512-512
SegFormer consists of a hierarchical Transformer encoder and a lightweight all-MLP decode head to achieve great results on semantic segmenta...
ZhengPeng7/BiRefNet_dynamic
Bilateral Reference for High-Resolution Dichotomous Image Segmentation...
nvidia/segformer-b4-finetuned-ade-512-512
SegFormer consists of a hierarchical Transformer encoder and a lightweight all-MLP decode head to achieve great results on semantic segmenta...
ZhengPeng7/BiRefNet_HR
No description available.
PaddlePaddle/PP-DocLayoutV3
No description available.
nvidia/segformer-b2-finetuned-cityscapes-1024-1024
SegFormer consists of a hierarchical Transformer encoder and a lightweight all-MLP decode head to achieve great results on semantic segmenta...
facebook/mask2former-swin-large-coco-panoptic
Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding la...
cocktailpeanut/rm
No description available.
facebook/mask2former-swin-small-ade-semantic
Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding la...
shi-labs/oneformer_cityscapes_swin_large
OneFormer is the first multi-task universal image segmentation framework. It needs to be trained only once with a single universal architect...
nvidia/segformer-b0-finetuned-cityscapes-1024-1024
SegFormer consists of a hierarchical Transformer encoder and a lightweight all-MLP decode head to achieve great results on semantic segmenta...
ZhengPeng7/BiRefNet_lite
Bilateral Reference for High-Resolution Dichotomous Image Segmentation...
facebook/mask2former-swin-large-mapillary-vistas-panoptic
Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding la...
Xenova/modnet
No description available.
mcmonkey/clipseg-rd64-refined-fp16
No description available.
facebook/mask2former-swin-tiny-coco-panoptic
Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding la...
openmmlab/upernet-convnext-small
UperNet is a framework for semantic segmentation. It consists of several components, including a backbone, a Feature Pyramid Network (FPN) a...
ZhengPeng7/BiRefNet_HR-matting
No description available.
facebook/mask2former-swin-base-ade-semantic
Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding la...
shi-labs/oneformer_ade20k_dinat_large
OneFormer is the first multi-task universal image segmentation framework. It needs to be trained only once with a single universal architect...
sayeed99/segformer_b3_clothes
No description available.
onnx-community/BEN2-ONNX
No description available.
facebook/mask2former-swin-tiny-ade-semantic
Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding la...
microsoft/beit-large-finetuned-ade-640-640
The BEiT model is a Vision Transformer (ViT), which is a transformer encoder model (BERT-like). In contrast to the original ViT model, BEiT ...
restor/tcd-segformer-mit-b0
No description available.
nvidia/segformer-b1-finetuned-cityscapes-1024-1024
SegFormer consists of a hierarchical Transformer encoder and a lightweight all-MLP decode head to achieve great results on semantic segmenta...
nvidia/segformer-b3-finetuned-cityscapes-1024-1024
SegFormer consists of a hierarchical Transformer encoder and a lightweight all-MLP decode head to achieve great results on semantic segmenta...
sayeed99/segformer-b3-fashion
No description available.
nvidia/segformer-b4-finetuned-cityscapes-1024-1024
SegFormer consists of a hierarchical Transformer encoder and a lightweight all-MLP decode head to achieve great results on semantic segmenta...
ZhengPeng7/BiRefNet-DIS5K
Bilateral Reference for High-Resolution Dichotomous Image Segmentation...
onnx-community/ormbg-ONNX
No description available.
cyberagent/layerd-birefnet
No description available.
restor/tcd-segformer-mit-b5
No description available.
openmmlab/upernet-swin-base
UperNet is a framework for semantic segmentation. It consists of several components, including a backbone, a Feature Pyramid Network (FPN) a...
Intel/dpt-large-ade
The Midas 3.0 nbased Dense Prediction Transformer (DPT) model was trained on ADE20k for semantic segmentation. It was introduced in the pape...
thang101020/upernet-segmenthomeai
UperNet is a framework for semantic segmentation. It consists of several components, including a backbone, a Feature Pyramid Network (FPN) a...
Xenova/face-parsing
No description available.
tue-mps/coco_instance_eomt_large_1280
No description available.
ZhengPeng7/BiRefNet-matting
Bilateral Reference for High-Resolution Dichotomous Image Segmentation...
camenduru/RMBG-2.0
No description available.
facebook/maskformer-swin-base-coco
MaskFormer addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding lab...
openmmlab/upernet-swin-small
UperNet is a framework for semantic segmentation. It consists of several components, including a backbone, a Feature Pyramid Network (FPN) a...
facebook/mask2former-swin-tiny-cityscapes-semantic
Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding la...
microsoft/beit-base-finetuned-ade-640-640
The BEiT model is a Vision Transformer (ViT), which is a transformer encoder model (BERT-like). In contrast to the original ViT model, BEiT ...
nvidia/segformer-b0-finetuned-cityscapes-512-1024
SegFormer consists of a hierarchical Transformer encoder and a lightweight all-MLP decode head to achieve great results on semantic segmenta...
facebook/mask2former-swin-large-ade-panoptic
Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding la...
chendelong/DirectSAM-1800px-0424
No description available.
tue-mps/eomt-dinov3-ade-semantic-large-512
| Property | Value | |----| | Backbone | DINOv3 ViT-L/16 | | Input Resolution | 512×512 | | Task | Semantic Segmentation | | Dataset | ADE20...
facebook/mask2former-swin-base-coco-instance
Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding la...
tue-mps/eomt-dinov3-coco-panoptic-large-640
| Property | Value | |----| | Backbone | DINOv3 ViT-L/16 | | Input Resolution | 640×640 | | Task | Panoptic Segmentation | | Dataset | COCO ...
sayeed99/segformer-b2-fashion
No description available.
bwittmann/vesselFM
No description available.
keremberke/yolov8m-building-segmentation
- ultralyticsplus - yolov8 - ultralytics - yolo - vision - image-segmentation - pytorch - awesome-yolov8-models libraryname: ultralytics lib...
tue-mps/eomt-dinov3-coco-instance-large-640
| Property | Value | |----| | Backbone | DINOv3 ViT-L/16 | | Input Resolution | 640×640 | | Task | Instance Segmentation | | Dataset | COCO ...
huyvux3005/manga109-segmentation-bubble
No description available.
apple/deeplabv3-mobilevit-xx-small
MobileViT is a light-weight, low latency convolutional neural network that combines MobileNetV2-style layers with a new block that replaces ...
openmmlab/upernet-convnext-tiny
UperNet is a framework for semantic segmentation. It consists of several components, including a backbone, a Feature Pyramid Network (FPN) a...
facebook/maskformer-swin-small-coco
MaskFormer addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding lab...
pamixsun/segformer_for_optic_disc_cup_segmentation
No description available.
facebook/mask2former-swin-small-coco-panoptic
Mask2Former addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding la...
keremberke/yolov8m-pothole-segmentation
- ultralyticsplus - yolov8 - ultralytics - yolo - vision - image-segmentation - pytorch - awesome-yolov8-models libraryname: ultralytics lib...
ZhengPeng7/BiRefNet-legacy
Bilateral Reference for High-Resolution Dichotomous Image Segmentation...
ZechenBai/VideoLISA-3.8B
No description available.
Ricky06662/VisionReasoner-7B
No description available.
facebook/maskformer-swin-base-ade
MaskFormer addresses instance, semantic and panoptic segmentation with the same paradigm: by predicting a set of masks and corresponding lab...
ZhengPeng7/BiRefNet-HRSOD
Bilateral Reference for High-Resolution Dichotomous Image Segmentation...
yolo12138/segformer-b2-human-parse-24
More information needed ``` "id2label": { "0": "background", "1": "hat", "2": "hair", "3": "glove", "4": "glasses", "5": "upperonlytorsoregi...
ZhengPeng7/BiRefNet_dynamic-matting
Bilateral Reference for High-Resolution Dichotomous Image Segmentation...
michaelyuanqwq/roboengine-sam
No description available.
apple/deeplabv3-mobilevit-small
MobileViT is a light-weight, low latency convolutional neural network that combines MobileNetV2-style layers with a new block that replaces ...
qualcomm/DeepLabV3-Plus-MobileNet
Model Type: Modelusecase.semanticsegmentation Model Stats: - Model checkpoint: VOC2012 - Input resolution: 513x513 - Number of output classe...
keremberke/yolov8m-pcb-defect-segmentation
- ultralyticsplus - yolov8 - ultralytics - yolo - vision - image-segmentation - pytorch - awesome-yolov8-models libraryname: ultralytics lib...
openmmlab/upernet-swin-large
UperNet is a framework for semantic segmentation. It consists of several components, including a backbone, a Feature Pyramid Network (FPN) a...