Papers › Dissecting the impact of different loss functions with gradient surgery
Dissecting the impact of different loss functions with gradient surgery
Hong Xuan, Robert Pless
Pair-wise loss is an approach to metric learning that learns a semantic embedding by optimizing a loss function that encourages images from the same semantic class to be mapped closer than images from different classes. The literature reports a large and growing set of variations of the pair-wise loss strategies. Here we decompose the gradient of these loss functions into components that relate to how they push the relative feature positions of the anchor-positive and anchor-negative pairs. This decomposition allows the unification of a large collection of current pair-wise loss functions. Additionally, explicitly constructing pair-wise gradient updates to separate out these effects gives insights into which have the biggest impact, and leads to a simple algorithm that beats the state of the art for image retrieval on the CAR, CUB and Stanford Online products datasets.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Metric Learning | CARS196 | Gradient Surgery | R@1 | 86.5 | #24 of 36 | Archive leaderboard | report |
| Metric Learning | CUB-200-2011 | Gradient Surgery | R@1 | 63.8 | #23 of 30 | Archive leaderboard | report |
| Metric Learning | In-Shop | Gradient Surgery | R@1 | 92.21 | #7 of 15 | Archive leaderboard | report |
| Metric Learning | Stanford Online Products | Gradient Surgery | R@1 | 82.3 | #12 of 33 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections