We introduce **SEEM** that can **S**egment **E**verything **E**verywhere with **M**ulti-modal prompts all at once. SEEM allows users to easily segment an image using prompts of different types including visual prompts (points, marks, boxes, scribbles and image segments) and language prompts (text and audio), etc. It can also work with any combination of prompts or generalize to custom prompts!
* **[2023.10.10]** We release the training [log](https://huggingface.co/xdecoder/SEEM/raw/main/seem_v1_focall_unicl.log) for SEEM-Large-v1 and [log](https://huggingface.co/xdecoder/SEEM/raw/main/seem_v1_focalt_unicl.log) for SEEM-Tiny-v1!
* **[2023.10.04]** We are excited to release :white_check_mark: [training/evaluation/demo code](https://github.com/UX-Decoder/Segment-Everything-Everywhere-All-At-Once/edit/v1.0/README.md#bookmark_tabs-catalog), :white_check_mark: [new checkpoints](https://github.com/UX-Decoder/Segment-Everything-Everywhere-All-At-Once/edit/v1.0/README.md#bookmark_tabs-catalog), and :white_check_mark: [comprehensive readmes](https://github.com/UX-Decoder/Segment-Everything-Everywhere-All-At-Once/edit/v1.0/README.md#bookmark_tabs-catalog) for ***both X-Decoder and SEEM***!
* **[2023.09.25]** Our work has been accepted to NeurIPS 2023!
* **[2023.07.27]** We are excited to release our [X-Decoder](https://github.com/microsoft/X-Decoder) training code! We will release its descendant SEEM training code very soon!
* **[2023.07.10]** We release [Semantic-SAM](https://github.com/UX-Decoder/Semantic-SAM), a universal image segmentation model to enable segment and recognize anything at any desired granularity. Code and checkpoint are available!
* **[2023.05.02]** We have released the [SEEM Focal-L](https://projects4jw.blob.core.windows.net/x-decoder/release/seem_focall_v1.pt) and [X-Decoder Focal-L](https://projects4jw.blob.core.windows.net/x-decoder/release/xdecoder_focall_last.pt) checkpoints and [configs](https://github.com/UX-Decoder/Segment-Everything-Everywhere-All-At-Once/blob/main/demo_code/configs/seem/seem_focall_lang.yaml)!
* **[2023.04.28]** We have updated the [ArXiv](https://arxiv.org/pdf/2304.06718.pdf) that shows *better interactive segmentation results than SAM*, which trained on x50 more data than us!
* **[2023.04.26]** We have released the [Demo Code](https://github.com/UX-Decoder/Segment-Everything-Everywhere-All-At-Once/tree/main/demo_code) and [SEEM-Tiny Checkpoint](https://projects4jw.blob.core.windows.net/x-decoder/release/seem_focalt_v1.pt)! Please try the One-Line Started!
* **[2023.04.20]** SEEM Referring Video Segmentation is out! Please try the [Video Demo](https://huggingface.co/spaces/xdecoder/SEEM) and take a look at the [NERF examples](https://github.com/UX-Decoder/Segment-Everything-Everywhere-All-At-Once#tulip-nerf-examples).
* [FocalNet](https://github.com/microsoft/FocalNet) and [DaViT](https://github.com/dingmyu/davit) : We used FocalNet and DaViT as the vision backbones.
* [UniCL](https://github.com/microsoft/UniCL) : We used unified contrastive learning technique for learning image-text representations.
* [X-Decoder](https://github.com/microsoft/X-Decoder) : We built SEEM based on X-Decoder which is a generalist decoder that can do multiple tasks with one model only.
:fire: **Other projects you may find interesting:**
* [Semantic-SAM](https://github.com/UX-Decoder/Semantic-SAM), a universal image segmentation model to enable segment and recognize anything at any desired granularity
Inspired by the appealing universal interface in LLMs, we are advocating a universal, interactive multi-modal interface for any type of segmentation with **ONE SINGLE MODEL**. We emphasize **4** important features of **SEEM** below.
- Select at least one type of prompt of your choice (If you want to use referred region of another image please check "Example" and upload another image in referring image panel);
- Remember to provide the actual prompt for each prompt type you select, otherwise you will meet an error (e.g., remember to draw on the referring image);
- Our model by default support the **vocabulary** of COCO 80 categories, others will be classified to 'others' or misclassified. If you want to segment using open-vocabulary labels, include the text label in 'text' button after drawing scribbles.
An example of Transformers. The referred image is the truck form of Optimus Prime. Our model can always segment Optimus Prime in target images no matter which form it is in. Thanks Hongyang Li for this fun example.
SEEM understands the spatial relationship very well. Look at the three zebras! The segmented zebras have similar positions with the referred zebras. For example, when the leftmost zebra is referred on the upper row, the leftmost zebra on the bottom row is segmented.
In the following figure, we compare the levels of interaction and semantics of three segmentation tasks (edge detection, open-set, and interactive segmentation). Open-set Segmentation usually requires a high level of semantics and does not require interaction. Compared with [SAM](https://arxiv.org/abs/2304.02643), SEEM covers a wider range of interaction and semantics levels. For example, SAM only supports limited interaction types like points and boxes, while misses high-semantic tasks since it does not output semantic labels itself. The reasons are: First, SEEM has a unified prompt encoder that encodes all visual and language prompts into a joint representation space. In consequence, SEEM can support more general usages. It has potential to extend to custom prompts. Second, SEEM works very well on text to mask (grounding segmentation) and outputs semantic-aware predictions.
<!-- This figure shows a comparison of our model with concurrent work SAM on the level of interactions and semantics. The x-axis and y-axis denote the level of interaction and semantics, respectively. Three segmentation tasks are shown, including Open-set Segmentation, Edge detection, and Interactive Segmentation. These tasks have different levels of interactions and semantics. For example, Open-set Segmentation usually requires a high level of semantics and does not require interaction. Compared with SAM, our model covers a wider range of interaction and semantics levels. For example, SAM only supports limited interaction types like points and boxes, while misses high-semantic tasks since it does not output semantic labels itself. Note that although we do not report edge detection results, our model can support it by simply converting masks to edges. -->
