Yeti Gürbüz, Ozan Şener, A Aydın, Alatan Rsim
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
A common architectural choice for deep metric learning is a convolutional neural network followed by global average pooling (GAP). Albeit simple, GAP is a highly effective way to aggregate information. One possible explanation for the effectiveness of GAP is considering each feature vector as representing a different semantic entity and GAP as a convex combination of them. Following this perspective, we generalize GAP and propose a learnable generalized sum pooling method (GSP). GSP improves GAP with two distinct abilities: i) the ability to choose a subset of semantic entities, effectively learning to ignore nuisance information, and ii) learning the weights corresponding to the importance of each entity. Formally, we propose an entropy-smoothed optimal transport problem and show that it is a strict generalization of GAP, i.e., a specific realization of the problem gives back GAP. We show that this optimization problem enjoys analytical gradients enabling us to use it as a direct learnable replacement for GAP. We further propose a zero-shot loss to ease the learning of GSP. We show the effectiveness of our method with extensive evaluations on 4 popular metric learning benchmarks.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2308.09228")
get_code_for_paper("2308.09228")
have("2308.09228")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2308.09228.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2308.09228)
Connect an agent — have() is free.