AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching

Di Hu, Rui Qian, Minyue Jiang, Xiao Tan, Shilei Wen, Errui Ding, Weiyao Lin, Dejing Dou

NeurIPS 2020 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 68 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 alternating localization/classification training with K-means pseudo-labels in stage 1 (ablation)two-stage sounding object localization · MUSIC-SyntheticCIoU@0.3: 17.4 -> 32.3Improved
add product operation (sounding-area filter) in stage 2 (ablation)two-stage sounding object localization · MUSIC-SyntheticCIoU: 2.6 -> 32.3Improved
add audiovisual consistency loss Lc in stage 2 (ablation)two-stage sounding object localization · MUSIC-SyntheticCIoU: 18.0 -> 32.3Improved
add audiovisual consistency loss Lc in stage 2 (ablation)two-stage sounding object localization · MUSIC-DuetCIoU: 22.4 -> 30.2Improved
add localization loss L1 alongside Lc (ablation)two-stage sounding object localization · MUSIC-SyntheticCIoU: 0.0 -> 2.6Improved
use ImageNet-pretrained visual backbone instead of scratch (ablation)two-stage sounding object localization · MUSIC-SyntheticCIoU@0.3: 7.8 -> 32.3Improved
use ImageNet-pretrained visual backbone instead of scratch (ablation)two-stage sounding object localization · MUSIC-soloIoU@0.5: 25.0 -> 51.4Improved
lambda in [0.5, 1.0] versus 0.3 or 1.5 (ablation)two-stage sounding object localization · MUSIC-SyntheticCIoU@0.3: 11.0 -> 32.3Improved
increase number of clusters from 11 to 20 (or 13) (ablation)two-stage sounding object localization · MUSIC-SyntheticCIoU@0.3: 32.3 -> 29.5No clear effect
change mask threshold from 0.05 to 0.07 (ablation)two-stage sounding object localization · MUSIC-soloIoU@0.5: 51.4 -> 43.1Hurt
class-aware distribution matching vs Sound-of-pixeltwo-stage sounding object localization · MUSIC-SyntheticCIoU@0.3: 8.1 -> 32.3Improved
class-aware method vs Sound-of-pixeltwo-stage sounding object localization · AudioSet-instrument-multiNSA: 88.8 -> 56.8Hurt

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