AI Paper Atlas

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

Semantic Clustering for Robust Fine-Grained Scene Recognition

Marian George, Mandar Dixit, Gábor Zogg, Nuno Vasconcelos

ECCV 2016 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Augmentation and mixture-of-experts generalization · 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 semantic clustering (latent topics with per-topic classifiers) (ablation)OOM · SnapStoreaccuracy (%): 45.7 -> 47.9Improved
add semantic clustering (ablation)OOM (soft detections) · MIT67accuracy (%): 68.2 -> 68.6No clear effect
add semantic clustering (ablation)OOM · cross-domain average (7 scenarios)accuracy (%): 58.5 -> 60.4Improved
add semantic clustering (ablation)ObjectBank · cross-domain average (7 scenarios)accuracy (%): 32.9 -> 33.4No clear effect
cluster DeCaF features with k-means (ablation)DeCaF · cross-domain average (7 scenarios)accuracy (%): 58.8 -> 56.7Hurt
replace raw detection scores with OOM scene probabilitiesObjectBank (CNN detections) · SnapStoreaccuracy (%): 34.8 -> 45.4Improved
use discriminant object selection (fewer objects) (ablation)OOM (soft detections) · SnapStoreaccuracy (%): 43.1 -> 45.4Improved
use discriminant object selection (fewer objects) (ablation)OOM (soft detections) · MIT67accuracy (%): 68.0 -> 68.2 -> 66.4Mixed
fine-tune Places CNN instead of using fc7 featuresPlaces CNN · SnapStoreaccuracy (%): 44.2 -> 42.4Hurt
use max pooling instead of average pooling over topic classifiers (ablation)semantic clustering · SnapStoreaccuracy (%)Hurt
vary number of k-means clusters k (ablation)semantic clustering · SnapStoreaccuracy (%)No clear effect
use hard (RCNN, 200 objects) instead of soft detectionsOOM · MIT67accuracy (%): 68.2 -> 49.4Hurt

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