AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Hard-Aware Deeply Cascaded Embedding

Yuhui Yuan, Kuiyuan Yang, Chao Zhang

ICCV 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 311 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
add hard example mining (single model) (ablation)Contrastive (128-d) · CARS196 (ablation, no bbox)Recall@1: 56.0 -> 67.6Improved
train on the target dataset instead of pretrained features only (ablation)GoogLeNet · CARS196 (ablation, no bbox)Recall@1: 40.5 -> 56.0Improved
replace single-model hard mining with cascaded hard-aware mining (same architecture) (ablation)Hard + Contrastive · CARS196 (ablation, no bbox)Recall@1: 67.6 -> 71.4Improved
concatenate features of all three cascaded models (ablation)HDC + Contrastive-3 · CARS196 (ablation, no bbox)Recall@1: 71.4 -> 73.7Improved
use deeper cascaded sub-model (model 1 to 2) (ablation)HDC · CARS196 (ablation, no bbox)Recall@1: 41.9 -> 58.0Improved
use deeper cascaded sub-model (model 2 to 3) (ablation)HDC · CARS196 (ablation, no bbox)Recall@1: 58.0 -> 71.4Improved
add cascade over single-model hard mining (ablation)Hard + Contrastive · CARS196 (ablation, no bbox)LDA score: 1.99 -> 2.50Improved
concatenate features of all three cascaded models (ablation)HDC + Contrastive-3 · CUB-200-2011 (ablation, with bbox)Recall@1: 58.5 -> 60.7Improved
use deeper cascaded sub-model (model 1 to 3) (ablation)HDC · CUB-200-2011 (ablation, with bbox)Recall@1: 43.4 -> 58.5Improved
HDC vs PDDM + Quadruplet with bounding boxesHDC + Contrastive (384-d, bbox) · CARS196 (with bbox)Recall@1: 57.4 -> 83.8Improved
HDC vs Npairs with multiple cropsHDC + Contrastive (384-d, multi-crop) · Stanford Online ProductsRecall@1: 67.7 -> 70.1Improved
HDC vs previous best on Stanford Online ProductsHDC + Contrastive (384-d) · Stanford Online ProductsRecall@1: 65.5 -> 69.5Improved

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