AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Semi-supervised Visual Tracking of Marine Animals Using Autonomous Underwater Vehicles

Levi Cai, Nathan McGuire, Roger T. Hanlon, T. Aran Mooney, Yogesh Girdhar

IJCV 2023 · Label-efficient and robust learning › Semi-supervised learning · approach: GAN-based semi-supervised learning · 62 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
use KeepTrack (distractor-aware, built on SuperDiMP) instead of SuperDiMPSuperDiMP · VMATsuccess AUC: 48.5 -> 53.6Improved
use KeepTrackFast parameters instead of KeepTrackKeepTrack · VMATsuccess AUC: 52.7 -> 53.6No clear effect
use KeepTrackFast parameters instead of KeepTrack (speed)KeepTrack · Jetson Xavierframe rate: 2-4fps -> 7-9fpsImproved
add transformer layers to SuperDiMP-style trackers (TrDiMP, TrSiam, TransT)SuperDiMP · VMATsuccess AUCNo clear effect
use transformer-based trackers in midwater and active lighting scenestransformer trackers · VMAT midwater / active lightingsuccess AUCImproved
use online discriminator-based trackers instead of Siamese-based onessemi-supervised trackers · VMATsuccess AUCImproved
move from simple midwater scenes to coral reef and seagrass habitatsall trackers · VMAT CR and SG subsetssuccess AUCHurt

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