AI Paper Atlas

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

Structured Feature Similarity With Explicit Feature Map

Takumi Kobayashi

CVPR 2016 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 7 citations (OpenAlex)

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 the proposed TENSOR similarity instead of L2SIFT image retrieval · Oxford buildingmAP: 67.6 -> 73.2Improved
Apply the proposed feature map to CNN featuresCNN features · Scene-15accuracy: 90.3±0.2 -> 91.2±0.5Improved
Apply the proposed feature map to CNN featuresCNN features · SUN-397accuracy: 52.1±0.3 -> 54.3±0.3Improved
Use explicit feature mapping rather than pairwise similarity computation (ablation)Proposed SIFT similarity · Keypoint matching, 4096 sample pairstime per sample pair: 1146.5 -> 65.7Improved
Use TENSOR sub-features rather than VECTOR sub-features (ablation)SSIM-based SIFT matching · Mikolajczyk and Schmid keypoint matching datasetaverage precisionImproved
Preserve the intrinsic SIFT tensor layout rather than randomly permuting feature elements (ablation)SSIM-based SIFT matching · Mikolajczyk and Schmid keypoint matching datasetaverage precisionImproved
Use an additive SSIM formulation rather than the original multiplicative formulation (ablation)TENSOR-structured SIFT matching · Mikolajczyk and Schmid keypoint matching datasetaverage precisionImproved
Combine two of M, V, and C rather than using any single ingredient alone (ablation)Sadd similarity · Mikolajczyk and Schmid keypoint matching datasetaverage precisionImproved
Use the proposed similarity for image quality assessment rather than original SSIMImage similarity assessment · TID2008Kendall rank correlation coefficient: 0.5768 -> 0.5489Hurt
Replace L2 with the proposed similarity for SURF-128 keypoint matchingSURF-128 · Mikolajczyk and Schmid keypoint matching datasetaverage precisionImproved

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