AI Paper Atlas

Research map / Video / Video segmentation and tracking

Online Model Distillation for Efficient Video Inference

Ravi Teja Mullapudi, Steven Chen, Keyi Zhang, Deva Ramanan, Kayvon Fatahalian

ICCV 2019 · Video › Video segmentation and tracking · approach: Video semantic and panoptic segmentation · 103 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
raise learning rate from 0.01 to 0.1 (ablation)JITNet 0.8 · LVS 6-video subsetmean IoU: 78.7 -> 16.7Hurt
lower learning rate from 0.01 to 0.001 (ablation)JITNet 0.8 · LVS 6-video subsetmean IoU: 78.7 -> 75.6Hurt
increase max updates per frame from 8 to 16 (ablation)JITNet 0.8 · LVS 6-video subsetmean IoU: 78.7 -> 78.0Hurt
reduce max updates per frame from 8 to 4 (ablation)JITNet 0.8 · LVS 6-video subsetmean IoU: 78.7 -> 77.3Hurt
increase min stride from 8 to 16 (ablation)JITNet 0.8 · LVS 6-video subsetmean IoU: 78.7 -> 76.1Hurt
decrease min stride from 8 to 4 (ablation)JITNet 0.8 · LVS 6-video subsetmean IoU: 78.7 -> 79.8Improved
add skip connections between encoder and decoder (ablation)JITNet 0.8 · LVS 6-video subsetmean IoU: 76.0 -> 78.7Improved
double network width (ablation)JITNet 0.8 · LVS 6-video subsetmean IoU: 78.7 -> 80.3Improved
halve network width (ablation)JITNet 0.8 · LVS 6-video subsetmean IoU: 78.7 -> 62.0Hurt
halve input resolution (scale 0.5) (ablation)JITNet 0.8 · LVS 6-video subsetmean IoU: 78.7 -> 75.9Hurt
use 75% input resolution (ablation)JITNet 0.8 · LVS 6-video subsetmean IoU: 78.7 -> 78.1No clear effect
use MobileNetV2 student (output stride 8) instead of JITNet (ablation)online distillation · LVS 6-video subsetmean IoU: 78.7 -> 75.3Hurt

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