SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2404.04050 · CVPR · 2024

No Time to Train: Empowering Non-Parametric Networks for Few-shot 3D Scene Segmentation

Hao Dong, Chaoyou Fu, Renrui Zhang, Peng Gao, Ziyu Guo, Jiaming Liu, Bowei He, Han Xiao, Xiangyang Zhu

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 14 functions out of this paper's own repositories and ran 8 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
yangyangyang127/seg-nn canonical 3 of 6
zrrskywalker/point-nn — 5 of 8
FunctionStatusWhere it lives
index_points Ran yangyangyang127/seg-nn/models/model_utils.py
pointer only (licence: NONE) · get_code("449a0265144f6530")
DecNP Ran zrrskywalker/point-nn/models/point_nn_seg.py
code served (permissive licence) · get_code("0ab557c415cb34d8")
FPS_kNN Ran zrrskywalker/point-nn/models/point_nn_seg.py
code served (permissive licence) · get_code("3863bd6bf124b486")
Pooling Ran zrrskywalker/point-nn/models/point_nn_seg.py
code served (permissive licence) · get_code("ed8271fc0b6bacf2")
PosE_Geo Ran zrrskywalker/point-nn/models/point_nn_seg.py
code served (permissive licence) · get_code("fe445ddc2c2d2ed8")
PosE_Initial Ran zrrskywalker/point-nn/models/point_nn_seg.py
code served (permissive licence) · get_code("1210b75f3d993b5c")
build_shared_mlp Ran yangyangyang127/seg-nn/pointnet2_ops_lib/pointnet2_ops/pointnet2_modules.py
pointer only (licence: NONE) · get_code("c80f9bbb31e6cb9f")
read_ply_xyzrgb Ran yangyangyang127/seg-nn/preprocess/collect_scannet_data.py
pointer only (licence: NONE) · get_code("765482885d5669b1")
EncNP Not yet run zrrskywalker/point-nn/models/point_nn_seg.py
code served (permissive licence) · get_code("38c0829d3d0401f9")
LGA Not yet run zrrskywalker/point-nn/models/point_nn_seg.py
code served (permissive licence) · get_code("41424ba0323e1e1e")
Point_NN_Seg Not yet run zrrskywalker/point-nn/models/point_nn_seg.py
code served (permissive licence) · get_code("b835d6bd233b7b66")
get_raw2scannet_label_map Not yet run yangyangyang127/seg-nn/preprocess/collect_scannet_data.py
pointer only (licence: NONE) · get_code("f13268f02f8a1e65")
knn_point Not yet run yangyangyang127/seg-nn/models/model_utils.py
pointer only (licence: NONE) · get_code("55397203c1d5dac1")
square_distance Not yet run yangyangyang127/seg-nn/models/model_utils.py
pointer only (licence: NONE) · get_code("6ddec81b1d23c787")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

To reduce the reliance on large-scale datasets, recent works in 3D segmentation resort to few-shot learning. Current 3D few-shot segmentation methods first pre-train models on 'seen' classes, and then evaluate their generalization performance on 'unseen' classes. However, the prior pre-training stage not only introduces excessive time overhead but also incurs a significant domain gap on 'unseen' classes. To tackle these issues, we propose a Nonparametric Network for few-shot 3D Segmentation, Seg-NN, and its Parametric variant, Seg-PN. Without training, Seg-NN extracts dense representations by hand-crafted filters and achieves comparable performance to existing parametric models. Due to the elimination of pre-training, Seg-NN can alleviate the domain gap issue and save a substantial amount of time. Based on Seg-NN, Seg-PN only requires training a lightweight QUEry-Support Transferring (QUEST) module, which enhances the interaction between the support set and query set. Experiments suggest that Seg-PN outperforms previous state-of-the-art method by +4.19% and +7.71% mIoU on S3DIS and ScanNet datasets respectively, while reducing training time by -90%, indicating its effectiveness and efficiency. Code is available here.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2404.04050")
get_code_for_paper("2404.04050")
have("2404.04050")

Connect an agent — have() is free.