atlas

Research map / Detection and segmentation / CNN features

Deep Semantic Feature Matching

CVPR 2017 · Detection and segmentation › CNN features · approach: Local features and context in CNNs · 91 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 activation-guided key feature selection instead of EdgeBox-based selection (ablation)Ours · PASCAL-Part, FlowWeb clustersPCK: 0.24 -> 0.25Helped
remove spatial constraints and use nearest-neighbor matching (ablation)Ours · PASCAL-Part, FlowWeb clustersPCK: 0.25 -> 0.15Hurt
add the binary objectness potential (ablation)Ours · Proposal FlowPCK: 0.66 -> 0.68Helped
add unary and binary objectness potentials (ablation)Ours · Proposal FlowPCK: 0.62 -> 0.68Helped
use the proposed dense matching method instead of LOMsemantic matching · Proposal FlowPCK: 0.56 -> 0.68Helped
use the proposed matching method instead of Flow Websemantic matching · PASCAL-PartIOU: 0.43 -> 0.43No clear effect

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