Object detection and segmentation

Use AI object detection and segmentation models to distinguish objects in images & videos

Назад к коллекциям

Модели в коллекции

Сортировка: по популярности (run_count)
falcons-ai/nsfw_image_detection

Fine-Tuned Vision Transformer (ViT) for NSFW Image Classification

77 529 044 запусков
adirik/grounding-dino

Detect everything with language!

27 864 727 запусков
idea-research/ram-grounded-sam

A Strong Image Tagging Model with Segment Anything

1 580 070 запусков
schananas/grounded_sam

Mask prompting based on Grounding DINO & Segment Anything | Integral cog of doiwear.it

1 110 508 запусков
lucataco/florence-2-large

Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks

793 502 запусков
swook/inspyrenet

Segment foreground objects with high resolution and matting, using InSPyReNet

695 781 запусков
daanelson/yolox

High performance and lightweight object detection models

118 767 запусков
chigozienri/mediapipe-face

batch or individual face detection with mediapipe

96 105 запусков
hassamdevsy/mask2former

Facebook Mask2Former trained on ADE 20k Dataset

58 610 запусков
meta/sam-2-video

SAM 2: Segment Anything v2 (for videos)

56 502 запусков
meta/sam-2

SAM 2: Segment Anything v2 (for Images)

49 699 запусков
ahmdyassr/mask-clothing

Super fast clothing (and face) segmentation and masking with erosion and dilation capability, made for https://outfit.fm

46 034 запусков
cjwbw/semantic-segment-anything

Adding semantic labels for segment anything

36 618 запусков
adirik/owlvit-base-patch32

Zero-shot / open vocabulary object detection

24 965 запусков
zsxkib/yolo-world

Real-Time Open-Vocabulary Object Detection

12 712 запусков
naklecha/clothing-segmentation

This model can detect clothing using a custom state of the art clothing segmentation algorithm.

4 579 запусков
hadilq/hair-segment

This is an ML model to segment hairs in pictures.

740 запусков
jweek/mask_maker

Uses DINO to detect regions and further refines them with SAM. Returns masking data as RLE encoded JSON.

612 запусков
zsxkib/samurai

SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory

234 запусков