AI Paper Atlas

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

DeepCD: Learning Deep Complementary Descriptors for Patch Representations

Tsun-Yi Yang, Jo-Han Hsu, Yen-Yu Lin, Yung-Yu Chuang

ICCV 2017 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 39 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 a 32-byte binary complementary descriptor stream (splitting model) to PNNet-128PNNet 128-d · Brown dataset real-valued descriptors (mean of 6 train/test combos)FPR95 (%): 7.26 -> 6.17Improved
use a separate 2-stream complementary network instead of the splitting model (ablation)DeepCD · Brown dataset real-valued descriptors (mean of 6 train/test combos)FPR95 (%): 6.17 -> 5.69Improved
add the DDM layer to DeepCD 2-stream (ablation)DeepCD 2-stream · Brown dataset real-valued descriptors (mean of 6 train/test combos)FPR95 (%): 5.69 -> 5.48Improved
double PNNet descriptor dimensionality to 256 instead of adding a complementary descriptor (ablation)PNNet · Brown dataset real-valued descriptors (mean of 6 train/test combos)FPR95 (%): 7.26 -> 6.98Improved
combine two PNNets with compact bilinear pooling (ablation)PNNet · Brown dataset real-valued descriptors (mean of 6 train/test combos)FPR95 (%)No clear effect
add the DDM layer to DeepCD 2-stream binary descriptors (128+64 bits) (ablation)DeepCD 2-stream binary · Brown dataset binary descriptors (mean of 6 train/test combos)FPR95 (%): 13.41 -> 13.34Improved
add the DDM layer to DeepCD 2-stream binary descriptors (512+256 bits) (ablation)DeepCD 2-stream binary · Brown dataset binary descriptors (mean of 6 train/test combos)FPR95 (%): 7.59 -> 7.55Improved
use a 2-stream instead of splitting model for binary descriptors (128+64 bits) (ablation)DeepCD binary · Brown dataset binary descriptors (mean of 6 train/test combos)FPR95 (%): 17.83 -> 13.41Improved
add the DDM layer to DeepCD 2-stream (ablation)DeepCD 2-stream · Strecha wide baseline matching (mean of fountain and herzjesu)mAP: 0.4518 -> 0.4588Improved
add complementary descriptor to PNNet for wide baseline matchingPNNet · Strecha wide baseline matching (mean of fountain and herzjesu)mAP: 0.3948 -> 0.4518Improved
add the DDM layer to DeepCD 2-stream (ablation)DeepCD 2-stream · Oxford descriptor benchmarkmAP: 0.5726 -> 0.5773Improved
add complementary descriptor to PNNet on OxfordPNNet · Oxford descriptor benchmarkmAP: 0.5541 -> 0.5726Improved

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