AI Paper Atlas

Research map / Optimization / Optimizers

Sampling Wisely: Deep Image Embedding by Top-K Precision Optimization

Jing Lu, Chaofan Xu, Wei Zhang, Ling-Yu Duan, Tao Mei

ICCV 2019 · Optimization › Optimizers · approach: Surrogate losses and robust solvers · 23 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
use top-k precision sampling loss l_k instead of distance weighted samplingDenseNet201 embedding · CUB-200-2011Precision@1 (%): 57.56 -> 61.07Improved
use l_k instead of semi-hard triplet lossDenseNet201 embedding · Stanford CarsPrecision@1 (%): 75.16 -> 80.03Improved
use l_k instead of angular lossDenseNet201 embedding · Stanford CarsPrecision@1 (%): 77.44 -> 80.03Improved
use l_k instead of hard mining triplet lossDenseNet201 embedding · Online ProductsPrecision@1 (%): 74.98 -> 78.40Improved
use l_k instead of uniform triplet lossDenseNet201 embedding · Online ProductsPrecision@1 (%): 62.89 -> 78.40Improved
choose negatives by uniform sampling rather than any smarter samplingtriplet loss · all three datasetsPrecision@1Hurt
swap between hard mining, semi-hard and distance-weighted samplingtriplet loss · CUB, Cars, Online ProductsPrecision@1Mixed

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