AI Paper Atlas

Research map / Optimization / Optimizers

Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval

Andrew Brown, Weidi Xie, Vicky Kalogeiton, Andrew Zisserman

ECCV 2020 · Optimization › Optimizers · approach: Surrogate losses and robust solvers · 146 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
append Smooth-AP loss to ArcFaceArcFace · VGGFace2 test face retrievalmAP: 0.858 -> 0.902Improved
append Smooth-AP loss to ArcFaceArcFace · IJB-C face retrievalmAP: 0.772 -> 0.803Improved
append Smooth-AP loss to SENet-50 softmax modelSENet-50 · VGGFace2 test face retrievalmAP: 0.828 -> 0.850Improved
use Smooth-AP instead of triplet loss for fine-tuningArcFace · VGGFace2 test face retrievalmAP: 0.880 -> 0.902Improved
use Smooth-AP instead of pairwise contrastive lossSENet-50 · IJB-C face retrievalmAP: 0.728 -> 0.754Improved
use Smooth-AP instead of Blackbox APResNet50 · INaturalist retrievalRecall@1 (%): 62.9 -> 65.9Improved
increase Smooth-AP batch size from 224 to 384 (ablation)Smooth-AP · INaturalist retrievalRecall@1 (%): 65.9 -> 67.2Improved
lower sigmoid temperature tau from 0.1 to 0.01 (ablation)Smooth-AP · VGGFace2 test (SENet-50 ablation, mAP)mAP: 0.824 -> 0.844Improved
lower sigmoid temperature tau from 0.01 to 0.001 (ablation)Smooth-AP · VGGFace2 test (SENet-50 ablation, mAP)mAP: 0.844 -> 0.839Hurt
increase positive-set size |P| from 4 to 16 (ablation)Smooth-AP · VGGFace2 test (SENet-50 ablation, mAP)mAP: 0.844 -> 0.824Hurt
increase batch size from 64 to 256 (ablation)Smooth-AP · VGGFace2 test (SENet-50 ablation, mAP)mAP: 0.824 -> 0.853Improved
use Smooth-AP instead of FastAP on VehicleID smallResNet50 · VehicleID (Small test set)Recall@1 (%): 91.9 -> 94.9Improved

Later papers that compared with this method

2 later accepted papers report SmoothAP as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy