SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.08209 · CVPR · 2024

Transcending the Limit of Local Window: Advanced Super-Resolution Transformer with Adaptive Token Dictionary

Yawei Li, Xingyu Zhou, Shuhang Gu, Leheng Zhang, Xiaorui Zhao

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 15 functions out of this paper's own repositories and ran 11 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
labshuhanggu/adaptive-token-dictionary — 11 of 15
FunctionStatusWhere it lives
AC_MSA Ran labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py
code served (permissive licence) · get_code("2d93e34cbbe0fa7b")
ATD_CA Ran labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py
code served (permissive licence) · get_code("a705dbc0a3d310ee")
ConvFFN_td Ran labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py
code served (permissive licence) · get_code("ffc960c5105253ab")
PatchEmbed Ran labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py
code served (permissive licence) · get_code("6317975e251ab4b3")
PatchUnEmbed Ran labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py
code served (permissive licence) · get_code("3732cc4a6f0ef56f")
Upsample Ran labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py
code served (permissive licence) · get_code("a3aba55c35e501fd")
UpsampleOneStep Ran labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py
code served (permissive licence) · get_code("9f0f80f58d07551b")
WindowAttention Ran labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py
code served (permissive licence) · get_code("f6d717e16606d5e6")
dwconv Ran labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py
code served (permissive licence) · get_code("8962dc49cd030b9e")
feature_shuffle Ran labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py
code served (permissive licence) · get_code("71f42c96ab0f7f91")
index_reverse Ran labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py
code served (permissive licence) · get_code("631a9cdc62e42ba1")
ATD Not yet run labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py
code served (permissive licence) · get_code("ea638ff98268e1f2")
ATDB Not yet run labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py
code served (permissive licence) · get_code("7d7aefff486dc4f7")
ATDTransformerLayer Not yet run labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py
code served (permissive licence) · get_code("3284755d16ba68ae")
BasicBlock Not yet run labshuhanggu/adaptive-token-dictionary/basicsr/archs/atd_arch.py
code served (permissive licence) · get_code("40f551c6bc695162")

Repositories linked to this paper

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

Abstract

Token Dictionary Training Dataset Learn … (a) window-based self-attention (c) category-based self-attention (b) token dictionary cross-attention Figure 1. Three different kinds of attention mechanism: (a) window-based self-attention exploits tokens in the same local window to enhance image tokens; (b) our proposed token dictionary cross-attention leverages the auxiliary dictionary to summarize and incorporate global information to the image tokens; (c) our proposed category-based self-attention adopts category labels to divide image tokens.

For agents

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

get_harvested_code_for_paper("2401.08209")
get_code_for_paper("2401.08209")
have("2401.08209")

Connect an agent — have() is free.