AI Paper Atlas

Research map / Video / Video segmentation and tracking

TMCOSS: Thresholded Multi-Criteria Online Subset Selection for Data-Efficient Autonomous Driving

Soumi Das, Harikrishna Patibandla, Suparna Bhattacharya, Kshounis Bera, Niloy Ganguly, Sourangshu Bhattacharya

ICCV 2021 · Video › Video segmentation and tracking · approach: Video semantic and panoptic segmentation · 5 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
replace additive loss term with thresholded concave term (TMCOSS-TL vs MCOSS)MCOSS · CARLA One-Turn, training conditions, 100:20episodes completed: 8 -> 8, test 7 -> 9Improved
add bucket-specific relative angle loss (BL) instead of total loss (ablation)TMCOSS-TL · CARLA One-Turn, training conditions, 100:20episodes completed: 8 -> 10Improved
add bucket-specific relative angle loss (BL) instead of total loss (ablation)TMCOSS-TL · CARLA One-Turn, training conditions, 100:7episodes completed: 7 -> 8Improved
use TMCOSS-BL instead of MCOSSMCOSS · CARLA One-Turn, training conditions, 100:7episodes completed: 5 -> 8Improved
use TMCOSS-BL instead of SubMCOSSSubMCOSS · CARLA One-Turn, training conditions, 100:7episodes completed: 3 -> 8Improved
add pointwise loss criterion additively (MCOSS vs OSS)OSS · CARLA One-Turn, test conditions, 100:20episodes completed: 7 -> 7No clear effect
use TMCOSS-BL instead of TMCOSS-TL (ablation)TMCOSS-TL · CARLA affordances, 100:20Red Light accuracy: 96.05 -> 92.83Hurt
use TMCOSS instead of MCOSSMCOSS · BDD drivable area segmentation, 100:20Drivable Area IoU: 76.0 -> 80.0Improved
use TMCOSS instead of MCOSSMCOSS · BDD drivable area segmentation, 100:20Alternate Drive Area IoU: 59.0 -> 65.0Improved
use TMCOSS instead of MCOSSMCOSS · Cityscapes semantic segmentation, 100:20Mean IoU: 72.33 -> 79.33Improved
use TMCOSS instead of MCOSSMCOSS · Cityscapes semantic segmentation, 100:20Wall IoU: 29.0 -> 50.0Improved
use uniform sampling instead of OSSOSS · CARLA One-Turn, training conditions, 100:20episodes completed: 7 -> 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