├── Dockerfile ├── LICENSE ├── README.md ├── example ├── 0.benchmark │ ├── README.md │ ├── benchmark.sh │ ├── evaluate_refcoco.py │ └── test_dataset_acc.py └── 1.infer │ ├── asserts │ └── example.jpg │ └── main.py ├── requirements.txt └── updownfunk_mask.gif /Dockerfile: -------------------------------------------------------------------------------- 1 | FROM pytorch/pytorch:2.4.1-cuda11.8-cudnn9-devel 2 | 3 | # Set environment variables 4 | ENV PYTHONDONTWRITEBYTECODE=1 5 | ENV PYTHONUNBUFFERED=1 6 | ENV DEBIAN_FRONTEND=noninteractive 7 | 8 | # Set working directory 9 | WORKDIR /app 10 | 11 | # Install basic packages 12 | RUN apt-get update && \ 13 | apt-get install -y --no-install-recommends \ 14 | git \ 15 | wget \ 16 | && apt-get clean \ 17 | && rm -rf /var/lib/apt/lists/* 18 | 19 | # Copy requirements.txt 20 | COPY requirements.txt . 21 | 22 | # Install the packages 23 | RUN pip install --no-cache-dir --upgrade pip && \ 24 | pip install --no-cache-dir -r requirements.txt 25 | 26 | # Install the packages using Tencent Cloud mirror 27 | # RUN pip install --no-cache-dir -i https://mirrors.cloud.tencent.com/pypi/simple/ --trusted-host mirrors.cloud.tencent.com --upgrade pip && \ 28 | # pip install --no-cache-dir -i https://mirrors.cloud.tencent.com/pypi/simple/ --trusted-host mirrors.cloud.tencent.com -r requirements.txt 29 | 30 | 31 | # Set an entrypoint that drops you into a shell 32 | ENTRYPOINT ["/bin/bash"] -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 |
2 |

A Segment Anything Model with MLCD Integration

3 | 4 | 5 | arXiv 6 | 7 |
8 | 9 | 10 | 11 | ## RefCOCO Segmentation Evaluation Results: 12 |
13 | 14 | [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multi-label-cluster-discrimination-for-visual/referring-expression-segmentation-on-refcocog)](https://paperswithcode.com/sota/referring-expression-segmentation-on-refcocog?p=multi-label-cluster-discrimination-for-visual) 15 | [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multi-label-cluster-discrimination-for-visual/referring-expression-segmentation-on-refcoco-5)](https://paperswithcode.com/sota/referring-expression-segmentation-on-refcoco-5?p=multi-label-cluster-discrimination-for-visual) 16 | [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multi-label-cluster-discrimination-for-visual/referring-expression-segmentation-on-refcoco-3)](https://paperswithcode.com/sota/referring-expression-segmentation-on-refcoco-3?p=multi-label-cluster-discrimination-for-visual) 17 | [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multi-label-cluster-discrimination-for-visual/referring-expression-segmentation-on-refcocog-1)](https://paperswithcode.com/sota/referring-expression-segmentation-on-refcocog-1?p=multi-label-cluster-discrimination-for-visual) 18 | [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multi-label-cluster-discrimination-for-visual/referring-expression-segmentation-on-refcoco-8)](https://paperswithcode.com/sota/referring-expression-segmentation-on-refcoco-8?p=multi-label-cluster-discrimination-for-visual) 19 | [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multi-label-cluster-discrimination-for-visual/referring-expression-segmentation-on-refcoco-4)](https://paperswithcode.com/sota/referring-expression-segmentation-on-refcoco-4?p=multi-label-cluster-discrimination-for-visual) 20 | [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multi-label-cluster-discrimination-for-visual/referring-expression-segmentation-on-refcoco-9)](https://paperswithcode.com/sota/referring-expression-segmentation-on-refcoco-9?p=multi-label-cluster-discrimination-for-visual) 21 | [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multi-label-cluster-discrimination-for-visual/referring-expression-segmentation-on-refcoco)](https://paperswithcode.com/sota/referring-expression-segmentation-on-refcoco?p=multi-label-cluster-discrimination-for-visual) 22 | [![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/multi-label-cluster-discrimination-for-visual/referring-expression-segmentation-on-refcoco)](https://paperswithcode.com/sota/referring-expression-segmentation-on-refcoco?p=multi-label-cluster-discrimination-for-visual) 23 | 24 |
25 | 26 | 27 | | Dataset | Split | MLCD-seg-7B | EVF-SAM | GLaMM | VisionLLM v2| LISA | 28 | | :-- | :-: | :-: | :-: | :-: | :-: | :-: | 29 | | RefCOCO | val | **83.6** | 82.4 | 79.5 | 79.2 | 74.9 | 30 | | RefCOCO | testA | **85.3** | 84.2 | 83.2 | 82.3 | 79.1 | 31 | | RefCOCO | testB | **81.5** | 80.2 | 76.9 | 77.0 | 72.3 | 32 | | RefCOCO+ | val | **79.4** | 76.5 | 72.6 | 68.9 | 65.1 | 33 | | RefCOCO+ | testA | **82.9** | 80.0 | 78.7 | 75.8 | 70.8 | 34 | | RefCOCO+ | testB | **75.6** | 71.9 | 64.6 | 61.8 | 58.1 | 35 | | RefCOCOg | val | **79.7** | 78.2 | 74.2 | 73.3 | 67.9 | 36 | | RefCOCOg | test | **80.5** | 78.3 | 74.9 | 74.8 | 70.6 | 37 | 38 | ## Example: 39 | 40 | output 41 | output 42 | 43 | 44 | ## How to use: 45 | 46 | If you just want to use this code, please refer to this sample below 47 | ```python 48 | from transformers import AutoModel, AutoTokenizer 49 | from PIL import Image 50 | 51 | 52 | model_path = "DeepGlint-AI/MLCD-Seg" # or use your local path 53 | mlcd_seg = AutoModel.from_pretrained( 54 | model_path, 55 | torch_dtype=torch.float16, 56 | trust_remote_code=True 57 | ).cuda() 58 | tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False) 59 | # Assuming you have an image named test.jpg 60 | seg_img = Image.open("test.jpg").convert('RGB') 61 | seg_prompt = "Could you provide a segmentation mask for the right giraffe in this image?" 62 | pred_mask = model.seg(seg_img, seg_prompt, tokenizer, force_seg=False) 63 | 64 | ``` 65 | 66 | If you want to use this code in video, please refer to this sample below 67 | ```python 68 | from transformers import AutoModel, AutoTokenizer 69 | from PIL import Image 70 | import torch 71 | from torchvision import transforms 72 | import subprocess 73 | import os 74 | 75 | # video path 76 | video_path = "updownfunk.mp4" 77 | input_dir = "frames" 78 | output_dir = "mask_frames" 79 | os.makedirs(input_dir, exist_ok=True) 80 | os.makedirs(output_dir, exist_ok=True) 81 | 82 | # assert you have ffmpeg installed, mp4 -> jpg 83 | cmd = [ 84 | "ffmpeg", 85 | "-i", video_path, 86 | "-vf", "fps=30", # 30FPS 87 | "-qscale:v", "1", 88 | os.path.join(input_dir, "frame_%04d.jpg") 89 | ] 90 | subprocess.run(cmd) 91 | 92 | # model path 93 | 94 | model_path = "/root/MLCD-Seg/" # or use your local path 95 | mlcd_seg = AutoModel.from_pretrained( 96 | model_path, 97 | torch_dtype=torch.float16, 98 | trust_remote_code=True 99 | ).cuda() 100 | tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False) 101 | 102 | 103 | # read jpgs 104 | image_files = sorted([f for f in os.listdir(input_dir) if f.endswith(('.jpg', '.png', '.jpeg'))]) 105 | 106 | for idx, filename in enumerate(image_files, start=1): 107 | 108 | src_path = os.path.join(input_dir, filename) 109 | seg_img = Image.open(src_path).convert('RGB') 110 | 111 | seg_prompt = "This