David Romero, Jean-Baptiste Cordonnier
We lifted 5 functions out of this paper's own repositories and ran 3 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 |
|---|---|---|
| dwromero/g_selfatt | canonical | 3 of 5 |
| Function | Status | Where it lives |
|---|---|---|
| Swish | Ran | dwromero/g_selfatt/g_selfatt/nn/group_self_attention.py code served (permissive licence) · get_code("a3342b2b45206cdd") |
| extract_patches | Ran | dwromero/g_selfatt/g_selfatt/nn/group_self_attention.py code served (permissive licence) · get_code("2f313da6e1ea1bd2") |
| normalize_tensor_one_minone | Ran | dwromero/g_selfatt/g_selfatt/nn/group_self_attention.py code served (permissive licence) · get_code("8ada35fb97381064") |
| Group | Not yet run | dwromero/g_selfatt/g_selfatt/nn/group_self_attention.py code served (permissive licence) · get_code("bfb2e02b1d344fdf") |
| GroupSelfAttention | Not yet run | dwromero/g_selfatt/g_selfatt/nn/group_self_attention.py code served (permissive licence) · get_code("b68ba9eafcd5cd5e") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
We provide a general self-attention formulation to impose group equivariance to arbitrary symmetry groups. This is achieved by defining positional encodings that are invariant to the action of the group considered. Since the group acts on the positional encoding directly, group equivariant self-attention networks (GSA-Nets) are steerable by nature. Our experiments on vision benchmarks demonstrate consistent improvements of GSA-Nets over non-equivariant self-attention networks.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2010.00977")
get_code_for_paper("2010.00977")
have("2010.00977")
Connect an agent — have() is free.