SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.10224 · ICLR · 2022

CycleMLP: A MLP-like Architecture for Dense Prediction

Ping Luo, Enze Xie, Shoufa Chen, Chongjian Ge, Runjian Chen, Ding Liang, 𝑆 𝐻, 𝑆

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 15 functions out of this paper's own repositories and ran 9 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
ShoufaChen/CycleMLP canonical 1 of 4
Ahmad-Omar-Ahsan/CycleMLP — 6 of 9
revsic/tf-mlptts pwc_unofficial 1 of 1
copy not recorded — 1 of 1
FunctionStatusWhere it lives
CycleFC Ran Ahmad-Omar-Ahsan/CycleMLP/models/cycle_mlp.py
code served (permissive licence) · get_code("6ba716e31944fe22")
Cycle_Block Ran Ahmad-Omar-Ahsan/CycleMLP/models/cycle_mlp.py
code served (permissive licence) · get_code("a7533815a60a5ff4")
MLP Ran Ahmad-Omar-Ahsan/CycleMLP/models/cycle_mlp.py
code served (permissive licence) · get_code("65aa6021f94c1bd7")
MLP_Block Ran Ahmad-Omar-Ahsan/CycleMLP/models/cycle_mlp.py
code served (permissive licence) · get_code("9f01e73d5c35c5b6")
OverlapPatchEmbed Ran Ahmad-Omar-Ahsan/CycleMLP/models/cycle_mlp.py
code served (permissive licence) · get_code("93aac00d7f2d7fba")
Spatial_Proj Ran Ahmad-Omar-Ahsan/CycleMLP/models/cycle_mlp.py
code served (permissive licence) · get_code("3e5be041fd16d9c9")
load_state Ran revsic/tf-mlptts/config.py
code served (permissive licence) · get_code("a93e65374343828b")
pair Ran this paper's copy was not recorded; identical code first harvested from LINs-lab/DynMoE
pointer only · get_code("6ba8cee9f5daea41")
pil_loader Ran ShoufaChen/CycleMLP/mcloader/mcloader.py
code served (permissive licence) · get_code("6cc5ed3b37c68d9d")
CycleMLP Not yet run Ahmad-Omar-Ahsan/CycleMLP/models/cycle_mlp.py
code served (permissive licence) · get_code("a58aae0835a61b41")
CycleMLP_Block Not yet run Ahmad-Omar-Ahsan/CycleMLP/models/cycle_mlp.py
code served (permissive licence) · get_code("e8703140c0494e82")
Stage Not yet run Ahmad-Omar-Ahsan/CycleMLP/models/cycle_mlp.py
code served (permissive licence) · get_code("20a854cf90927d91")
basic_blocks Not yet run ShoufaChen/CycleMLP/cycle_mlp.py
code served (permissive licence) · get_code("f679822e5f5f467c")
build_transform Not yet run ShoufaChen/CycleMLP/datasets.py
code served (permissive licence) · get_code("3bc74137ab36aa79")
sfc_flop_jit Not yet run ShoufaChen/CycleMLP/utils.py
code served (permissive licence) · get_code("2a2617c52f0e6b56")

Repositories linked to this paper

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

Abstract

This paper presents a simple MLP-like architecture, CycleMLP, which is a versatile backbone for visual recognition and dense predictions. As compared to modern MLP architectures, e.g. , MLP-Mixer (Tolstikhin et al., 2021), ResMLP (Touvron et al., 2021a), and gMLP (Liu et al., 2021a), whose architectures are correlated to image size and thus are infeasible in object detection and segmentation, CycleMLP has two advantages compared to modern approaches. (1) It can cope with various image sizes. (2) It achieves linear computational complexity to image size by using local windows. In contrast, previous MLPs have O(N 2 ) computations due to fully spatial connections. We build a family of models which surpass existing MLPs and even state-of-the-art Transformer-based models, e.g. Swin Transformer (Liu et al., 2021b), while using fewer parameters and FLOPs. We expand the MLP-like models' applicability, making them a versatile backbone for dense prediction tasks. CycleMLP achieves competitive results on object detection, instance segmentation, and semantic segmentation. In particular, CycleMLP-Tiny outperforms Swin-Tiny by 1.3% mIoU on ADE20K dataset with fewer FLOPs. Moreover, CycleMLP also shows excellent zero-shot robustness on ImageNet-C dataset. Code is available at https: //github.com/ShoufaChen/CycleMLP.

For agents

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

get_harvested_code_for_paper("2107.10224")
get_code_for_paper("2107.10224")
have("2107.10224")

Connect an agent — have() is free.