AI Paper Atlas

Research map / Architectures and efficiency / Neural architecture search

Compatibility-Aware Heterogeneous Visual Search

Rahul Duggal, Hao Zhou, Shuo Yang, Yuanjun Xiong, Wei Xia, Zhuowen Tu, Stefano Soatto

CVPR 2021 · Architectures and efficiency › Neural architecture search · approach: AutoML pipeline search · 20 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
Replace the homogeneous ResNet-101 query with Cmp-NAS while retaining ResNet-101 for gallery indexingVisual search · IJB-C face retrievalTPIR@FPIR=10^-1 (%): 86.7 -> 85.1Hurt
Replace the homogeneous MobileNetV2 system with a Cmp-NAS query and ResNet-101 galleryVisual search · IJB-C face retrievalTPIR@FPIR=10^-1 (%): 77.1 -> 85.1Improved
Replace the homogeneous ResNet-101 query with Cmp-NAS while retaining ResNet-101 for gallery indexingVisual search · DeepFashion2 retrievalTop-10 retrieval accuracy (%): 65.2 -> 64.9Hurt
Replace the homogeneous MobileNetV3 system with a Cmp-NAS query and ResNet-101 galleryVisual search · DeepFashion2 retrievalTop-10 retrieval accuracy (%): 62.7 -> 64.9Improved
Add BCT when training the query model (ablation)Pruned ResNet-101 query model · IJB-C face retrievalHeterogeneous 1:N accuracy: Magnitude prune: 0.0 -> 87.2; Channel prune: 0.0 -> 87.4Improved
Replace training from scratch with fine-tuning (ablation)Magnitude-pruned ResNet-101 query · IJB-C face retrievalHeterogeneous 1:N accuracy: 0.0 -> 86.5Improved
Replace training from scratch with knowledge distillation (ablation)Magnitude-pruned ResNet-101 query · IJB-C face retrievalHeterogeneous 1:N accuracy: 0.0 -> 0.0No clear effect
Replace BCT with fine-tuning (ablation)Magnitude-pruned ResNet-101 query · IJB-C face retrievalHeterogeneous 1:N accuracy: 87.2 -> 86.5Hurt
Replace BCT with knowledge distillation (ablation)Magnitude-pruned ResNet-101 query · IJB-C face retrievalHeterogeneous 1:N accuracy: 87.2 -> 0.0Hurt
Replace training from scratch with fine-tuning (ablation)Channel-pruned ResNet-101 query · IJB-C face retrievalHeterogeneous 1:N accuracy: 0.0 -> 86.3Improved
Replace training from scratch with knowledge distillation (ablation)Channel-pruned ResNet-101 query · IJB-C face retrievalHeterogeneous 1:N accuracy: 0.0 -> 0.0No clear effect
Replace BCT with fine-tuning (ablation)Channel-pruned ResNet-101 query · IJB-C face retrievalHeterogeneous 1:N accuracy: 87.4 -> 86.3Hurt

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