Zero Shot Segmentation
59 papers with code • 2 benchmarks • 3 datasets
Benchmarks
These leaderboards are used to track progress in Zero Shot Segmentation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
Libraries
Use these libraries to find Zero Shot Segmentation models and implementations
Segmentation in the Wild
TomoSAM
MatSeg
Most implemented papers
Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
idea-research/groundingdino
•
•
To effectively fuse language and vision modalities, we conceptually divide a closed-set detector into three phases and propose a tight fusion solution, which includes a feature enhancer, a language-guided query selection, and a cross-modality decoder for cross-modality fusion.
Image Segmentation Using Text and Image Prompts
After training on an extended version of the PhraseCut dataset, our system generates a binary segmentation map for an image based on a free-text prompt or on an additional image expressing the query.
Side Adapter Network for Open-Vocabulary Semantic Segmentation
A side network is attached to a frozen CLIP model with two branches: one for predicting mask proposals, and the other for predicting attention bias which is applied in the CLIP model to recognize the class of masks.
Segment Anything in High Quality
HQ-SAM is only trained on the introduced detaset of 44k masks, which takes only 4 hours on 8 GPUs.
Context-aware Feature Generation for Zero-shot Semantic Segmentation
bcmi/CaGNet-Zero-Shot-Semantic-Segmentation
•
•
In this paper, we propose a novel context-aware feature generation method for zero-shot segmentation named CaGNet.
A Simple Framework for Open-Vocabulary Segmentation and Detection
idea-research/openseed
•
•
ICCV 2023
We present OpenSeeD, a simple Open-vocabulary Segmentation and Detection framework that jointly learns from different segmentation and detection datasets.
A Closer Look at the Explainability of Contrastive Language-Image Pre-training
These phenomena conflict with conventional explainability methods based on the class attention map (CAM), where the raw model can highlight the local foreground regions using global supervision without alignment.
Segment Anything Model for Medical Image Analysis: an Experimental Study
We conclude that SAM shows impressive zero-shot segmentation performance for certain medical imaging datasets, but moderate to poor performance for others.
One-Prompt to Segment All Medical Images
kidswithtokens/one-prompt
•
•
CVPR 2024
Tested on 14 previously unseen datasets, the One-Prompt Model showcases superior zero-shot segmentation capabilities, outperforming a wide range of related methods.
Learning Mask-aware CLIP Representations for Zero-Shot Segmentation
jiaosiyu1999/maft
•
•
NeurIPS 2023
However, in the paper, we reveal that CLIP is insensitive to different mask proposals and tends to produce similar predictions for various mask proposals of the same image.
