X-Decoder: Generalized Decoding for Pixel, Image, and Language

[Project Page] [Paper] [HuggingFace All-in-One Demo] [HuggingFace Instruct Demo] [Video]

by Xueyan Zou*, Zi-Yi Dou*, Jianwei Yang*, Zhe Gan, Linjie Li, Chunyuan Li, Xiyang Dai, Harkirat Behl, Jianfeng Wang, Lu Yuan, Nanyun Peng, Lijuan Wang, Yong Jae Lee^, Jianfeng Gao^ in CVPR 2023.

🌶️ Getting Started

We release the following contents for both SEEM and X-Decoder❗

👉 One-Line SEEM Demo with Linux:

git clone git@github.com:UX-Decoder/Segment-Everything-Everywhere-All-At-Once.git && sh aasets/scripts/run_demo.sh

📍 [New] Getting Started:

📍 [New] Latest Checkpoints and Numbers:

			COCO			Ref-COCOg			VOC		SBD
Method	Checkpoint	backbone	PQ ↑	mAP ↑	mIoU ↑	cIoU ↑	mIoU ↑	AP50 ↑	NoC85 ↓	NoC90 ↓	NoC85 ↓	NoC90 ↓
X-Decoder	ckpt	Focal-T	50.8	39.5	62.4	57.6	63.2	71.6	-	-	-	-
X-Decoder-oq201	ckpt	Focal-L	56.5	46.7	67.2	62.8	67.5	76.3	-	-	-	-
SEEM_v0	ckpt	Focal-T	50.6	39.4	60.9	58.5	63.5	71.6	3.54	4.59	*	*
SEEM_v0	-	Davit-d3	56.2	46.8	65.3	63.2	68.3	76.6	2.99	3.89	5.93	9.23
SEEM_v0	ckpt	Focal-L	56.2	46.4	65.5	62.8	67.7	76.2	3.04	3.85	*	*
SEEM_v1	ckpt	Focal-T	50.8	39.4	60.7	58.5	63.7	72.0	3.19	4.13	*	*
SEEM_v1	ckpt	SAM-ViT-B	52.0	43.5	60.2	54.1	62.2	69.3	2.53	3.23	*	*
SEEM_v1	ckpt	SAM-ViT-L	49.0	41.6	58.2	53.8	62.2	69.5	2.40	2.96	*	*

SEEM_v0: Supporting Single Interactive object training and inference
SEEM_v1: Supporting Multiple Interactive objects training and inference

🔥 News

[2023.10.04] We are excited to release ✅ training/evaluation/demo code, ✅ new checkpoints, and ✅ comprehensive readmes for both X-Decoder and SEEM!
[2023.09.24] We are providing new demo command/code for inference (DEMO.md)!
[2023.07.19] 🎢 We are excited to release the x-decoder training code (INSTALL.md, DATASET.md, TRAIN.md, EVALUATION.md)!
[2023.07.10] We release Semantic-SAM, a universal image segmentation model to enable segment and recognize anything at any desired granularity. Code and checkpoint are available!
[2023.04.14] We are releasing SEEM, a new universal interactive interface for image segmentation! You can use it for any segmentation tasks, way beyond what X-Decoder can do!

[2023.03.20] As an aspiration of our X-Decoder, we developed OpenSeeD ([Paper][Code]) to enable open-vocabulary segmentation and detection with a single model, Check it out!
[2023.03.14] We release X-GPT which is an conversational version of our X-Decoder through GPT-3 langchain!
[2023.03.01] The Segmentation in the Wild Challenge had been launched and ready for submitting results!
[2023.02.28] We released the SGinW benchmark for our challenge. Welcome to build your own models on the benchmark!
[2023.02.27] Our X-Decoder has been accepted by CVPR 2023!
[2023.02.07] We combine X-Decoder (strong image understanding), GPT-3 (strong language understanding) and Stable Diffusion (strong image generation) to make an instructional image editing demo, check it out!
[2022.12.21] We release inference code of X-Decoder.
[2022.12.21] We release Focal-T pretrained checkpoint.
[2022.12.21] We release open-vocabulary segmentation benchmark.

🖌️ DEMO

🫐 [X-GPT] 🍓[Instruct X-Decoder]

🎶 Introduction

X-Decoder is a generalized decoding model that can generate pixel-level segmentation and token-level texts seamlessly!

It achieves:

State-of-the-art results on open-vocabulary segmentation and referring segmentation on eight datasets;
Better or competitive finetuned performance to generalist and specialist models on segmentation and VL tasks;
Friendly for efficient finetuning and flexible for novel task composition.

It supports:

One suite of parameters pretrained for Semantic/Instance/Panoptic Segmentation, Referring Segmentation, Image Captioning, and Image-Text Retrieval;
One model architecture finetuned for Semantic/Instance/Panoptic Segmentation, Referring Segmentation, Image Captioning, Image-Text Retrieval and Visual Question Answering (with an extra cls head);
Zero-shot task composition for Region Retrieval, Referring Captioning, Image Editing.

Acknowledgement

We appreciate the contructive dicussion with Haotian Zhang
We build our work on top of Mask2Former
We build our demos on HuggingFace 🤗 with sponsored GPUs
We appreciate the discussion with Xiaoyu Xiang during rebuttal

Citation

@article{zou2022xdecoder,
  author      = {Zou*, Xueyan and Dou*, Zi-Yi and Yang*, Jianwei and Gan, Zhe and Li, Linjie and Li, Chunyuan and Dai, Xiyang and Wang, Jianfeng and Yuan, Lu and Peng, Nanyun and Wang, Lijuan and Lee*, Yong Jae and Gao*, Jianfeng},
  title       = {Generalized Decoding for Pixel, Image and Language},
  publisher   = {arXiv},
  year        = {2022},
}

kosei1515/X-Decoder