CMX (SegFormer, MiT-B2) trained on NYUv2

Demo: predictions of this checkpoint on NYUv2 test scenes from our dataset mirror (RGB, hha input, prediction overlay; per-frame pixel accuracy vs. ground truth), rendered with the official code.

Unofficial mirror of the official CMX weights from huaaaliu/RGBX_Semantic_Segmentation. The weights are unchanged; this repository adds a weights-only model.safetensors copy and a config.json.

Model

SegFormer (MiT-B2) dual-branch encoder with cross-modal feature rectification and fusion modules.

Results (reported by the authors)

Metric Value
mIoU (single-scale, %) 54.1
mIoU (multi-scale + flip, %) 54.4

See the official repository for full tables and evaluation details.

Files

File Content
NYUDV2_CMX+Segformer-B2.pth original checkpoint, exactly as released
model.safetensors the model weights only (bit-exact copy of the checkpoint's model tensors; no optimizer state)
config.json architecture, dataset, results and provenance

Usage

import json
from huggingface_hub import hf_hub_download

repo = "dronefreak/cmx-mit-b2-nyuv2"
config = json.load(open(hf_hub_download(repo, "config.json")))
ckpt = hf_hub_download(repo, "NYUDV2_CMX+Segformer-B2.pth")   # original format: use it with the official code
print(config["architecture"], config["dataset"], ckpt)

Build the network with the official code (https://github.com/huaaaliu/RGBX_Semantic_Segmentation) using the matching config for this variant, then load NYUDV2_CMX+Segformer-B2.pth exactly as you would the original download, or load model.safetensors with safetensors.torch.load_file into the same model.

Citation

If you use these weights, please cite the original work:

@article{zhang2023cmx,
  title   = {CMX: Cross-modal fusion for RGB-X semantic segmentation with transformers},
  author  = {Zhang, Jiaming and Liu, Huayao and Yang, Kailun and Hu, Xinxin and Liu, Ruiping and Stiefelhagen, Rainer},
  journal = {IEEE Transactions on Intelligent Transportation Systems},
  year    = {2023}
}

Disclaimer

This is not an official release. All credit goes to the original authors (Jiaming Zhang, Huayao Liu, Kailun Yang, Xinxin Hu, Ruiping Liu, Rainer Stiefelhagen; KIT). The weights are redistributed under the MIT license of the official repository. If you are an author and want this mirror changed or removed, please open a discussion.

Downloads last month
-
Safetensors
Model size
66.6M params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train dronefreak/cmx-mit-b2-nyuv2

Collection including dronefreak/cmx-mit-b2-nyuv2

Paper for dronefreak/cmx-mit-b2-nyuv2