atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Deep Camouflage Images

AAAI 2020 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 21 citations (OpenAlex)

Read the paperCheck 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
Replace content loss with attention-aware camouflage loss (ablation)Deep camouflage generation · Koala example (qualitative)camouflage effectHelped
Add naturalness (manifold) regularization (ablation)Deep camouflage generation · Koala example (qualitative)visual naturalnessHelped
Add total variation loss (ablation)Deep camouflage generation · Koala example (qualitative)boundary smoothnessHelped
Add attention map to camouflage loss (ablation)Deep camouflage generation · Lion example (qualitative)hiding effectivenessHelped
Increase lambda_cam from 1e-6 to 1e-5 (ablation)Deep camouflage generation · Horse example (qualitative)recognition difficulty (higher = easier to spot): 1e-6 -> 1e-5Mixed
Use proposed method instead of AB, TT, PC, CAM, NS, DPS, CFPS, DPHCamouflage generation · User study, 50 AMT raters, 1-5 scalerating distributionHelped

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