AI Paper Atlas

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

MemSAC: Memory Augmented Sample Consistency for Large Scale Domain Adaptation

Tarun Kalluri, Astuti Sharma, Manmohan Chandraker

ECCV 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Conditional distribution alignment · 12 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 sample consistency loss Lsc to CDAN (ablation)MemSAC · CUB-Drawings averageaccuracy: 60.98 -> 67.95Improved
add adversarial loss Ladv to Lsc only (ablation)MemSAC · CUB-Drawings averageaccuracy: 52.79 -> 67.95Improved
add Lsc on top of source-only training without adversarial loss (ablation)MemSAC · CUB-Drawings averageaccuracy: 51.47 -> 52.79Improved
use temperature 0.07 instead of 1.0 (ablation)MemSAC · CUB-Drawings averageaccuracy: 60.91 -> 67.95Improved
use temperature 0.07 instead of 0.007 (ablation)MemSAC · CUB-Drawings averageaccuracy: 64.23 -> 67.95Improved
use cosine similarity instead of inverse Euclidean (ablation)MemSAC · CUB-Drawings averageaccuracy: 64.23 -> 67.95Improved
use cosine similarity instead of Gaussian (ablation)MemSAC · CUB-Drawings averageaccuracy: 60.47 -> 67.95Improved
add MemSAC to DANNDANN · DomainNet-345 R->C and C->Raccuracy: 46.39 -> 49.74 (+3.35%)Improved
add MemSAC to CANCAN · DomainNet-345 R->C and C->Raccuracy: 47.82 -> 49.57 (+1.75%)Improved
add MemSAC to CDANCDAN · DomainNet-345 R->C and C->Raccuracy: 50.08 -> 54.37 (+4.29%)Improved
add MemSAC with ResNet-101 backbone versus CDANCDAN · DomainNet-345 R->C and C->R (ResNet-101)accuracy: 49.55 -> 54.88Improved
use a memory bank (size above batch size 32) instead of none (ablation)MemSAC · CUB-Drawings C->D and D->Caccuracy: no numeric delta in textImproved

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