AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

To Adapt or Not to Adapt? Real-Time Adaptation for Semantic Segmentation

Marc Botet Colomer, Pier Luigi Dovesi, Theodoros Panagiotakopoulos, Joao Frederico Carvalho, Linus Härenstam-Nielsen, Hossein Azizpour, Hedvig Kjellström, Daniel Cremers, Matteo Poggi

ICCV 2023 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Adaptation for semantic segmentation · 22 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
add HAMT (hardware-aware backprop orchestration) to full online training (ablation)HAMLET · Increasing StormFPS / all-domain mIoU: 5.9 -> 7.0 FPS; 69.5 -> 68.7 mIoUMixed
add Least Training (adapt only on detected domain shift) (ablation)HAMLET with HAMT · Increasing StormFPS / 200mm mIoU: 7.0 -> 29.5 FPS; 60.2 -> 51.8 mIoU (200mm)Mixed
add Adaptive Learning Rate to LT (ablation)HAMLET · Increasing StormmIoU (200mm): 51.8 -> 54.1Improved
add domain-conditioned module and random class sampling on top of ALR (ablation)HAMLET · Increasing StormmIoU (200mm): 54.1 -> 58.2Improved
use Least Training alone when domain shifts are frequent (ablation)HAMLET · Fast Storm CFPS: 5.6 -> 7.2 FPS (A vs C)No clear effect
full HAMLET with all components vs full online training (ablation)HAMLET · Fast Storm Ctotal h-mean mIoU: 67.2 -> 67.8Improved
run CoTTA in real-time (adapt once every 50 frames)CoTTA · OnDA Increasing Stormh-mean mIoU (total): 66.8 -> 62.3Hurt
use HAMLET instead of TENT for online adaptationSegFormer MiT-B1 · OnDA Increasing Stormh-mean mIoU (total): 59.9 -> 67.2Improved
adapt SegFormer MiT-B1 with HAMLET vs source model onlySegFormer MiT-B1 · OnDA Increasing Stormh-mean mIoU (forward): 57.8 -> 66.8Improved
use a TENT replay bufferTENT · OnDA Increasing Stormh-mean mIoU (total): 59.9 -> 59.9No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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