AI Paper Atlas

Research map / Detection and segmentation / CNN features

Learning Discriminative and Transformation Covariant Local Feature Detectors

Xu Zhang, Felix X. Yu, Svebor Karaman, Shih-Fu Chang

CVPR 2017 · Detection and segmentation › CNN features · approach: Box regression and loss design · 127 citations (OpenAlex)

Check 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 the proposed transformation predictor with standard patches and identity loss instead of T-P24Local feature detection · Webcam, 1000 featuresrepeatability (%): 61.7 -> 68.4Improved
Use the proposed transformation predictor with standard patches and identity loss instead of T-P24Local feature detection · Webcam, 200 featuresrepeatability (%): 45.1 -> 52.6Improved
Use the proposed transformation predictor with standard patches and identity loss instead of T-P24Local feature detection · EF, 1000 featuresrepeatability (%): 45.4 -> 46.6Improved
Use the proposed transformation predictor with standard patches and identity loss instead of HarLapLocal feature detection · EF, 200 featuresrepeatability (%): 33.4 -> 36.3Improved
Use the proposed transformation predictor with standard patches and identity loss instead of HesLapLocal feature detection · VGG-Affine, 1000 featuresrepeatability (%): 66.7 -> 70.2Improved
Use the proposed transformation predictor with standard patches and identity loss instead of HesLapLocal feature detection · VGG-Affine, 200 featuresrepeatability (%): 60.0 -> 61.2Improved
Use T-P24-detected patches as standard patches rather than randomly sampled patches (ablation)Proposed detector · Repeatability across VGG-Affine, EF, and Webcamrepeatability (%)Improved
Use T-P24-detected patches as standard patches rather than SIFT-detected patches (ablation)Proposed detector · Repeatability across VGG-Affine, EF, and Webcamrepeatability (%)Improved
Use T-P24-detected patches as standard patches rather than Hessian-Affine-detected patches (ablation)Proposed detector · Repeatability across VGG-Affine, EF, and Webcamrepeatability (%)Improved
Add the identity loss with an adequate nonzero trade-off rather than using only the covariant constraint (ablation)Proposed detector · Repeatability across VGG-Affine, EF, and Webcamrepeatability (%)Improved
Use α=0, removing the identity-loss contribution (ablation)Proposed detector · Repeatability across VGG-Affine, EF, and Webcamrepeatability (%)Hurt
Use α=100, relying on the identity constraint rather than balancing it with covariance (ablation)Proposed detector · Repeatability across VGG-Affine, EF, and Webcamrepeatability (%)Hurt

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