Yawei Li, Xingyu Zhou, Shuhang Gu, Leheng Zhang, Xiaorui Zhao
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.
| Repository | Role | Ran |
|---|---|---|
| labshuhanggu/adaptive-token-dictionary | — | 11 of 15 |
| Function | Status | Where 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") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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.
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.