AI Paper Atlas

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

Soft Neighbors are Positive Supporters in Contrastive Visual Representation Learning

Chongjian GE, Jiangliu Wang, Zhan Tong, Shoufa Chen, Yibing Song, Ping Luo

ICLR 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 14 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 soft positiveness weights to neighbors (vs. treating neighbors as exactly positive) (ablation)SNCLR with 30 neighbors, ViT-S · ImageNet linear eval (300 ep)top-1 accuracy: +1.14 (72.24 to 73.38)Improved
add nearest-neighbor soft positives (K=30) vs. no neighbors (ablation)SNCLR, ViT-S · ImageNet linear eval (300 ep)top-1 accuracy: +1.07 (71.17 to 72.24) without positiveness; +2.21 with positivenessImproved
neighbor number K from 30 to 10 or 50 (ablation)SNCLR, ViT-S · ImageNet linear eval (300 ep)top-1 accuracy: 72.81 (K=10) and 72.92 (K=50) vs 73.38 (K=30)Hurt
increase candidate neighbor set length from 8000 to 128000 (ablation)SNCLR, ViT-S · ImageNet linear eval (300 ep)top-1 accuracy: 72.25 to 73.38 (non-monotonic, e.g. 32000 gives 72.43)Improved
apply soft neighbors to positives only vs. negatives only vs. both (ablation)SNCLR, ViT-S · ImageNet linear eval (300 ep)top-1 accuracy: positives only +0.71, negatives only +1.26, both +2.21 over baseline 71.17Improved
SNCLR (ResNet-50, 800 ep) vs. prior SSL methodsResNet-50 · ImageNet linear evaltop-1 accuracy: 75.3 vs 74.5 (NNCLR) and 74.3 (BYOL)Improved
SNCLR vs. baselines on ViT-S and ViT-BViT-S, ViT-B · ImageNet linear eval (300 ep)top-1 accuracy: 73.4 vs 72.5 (DINO) on ViT-S; 76.8 vs 76.2 (MoCo v3) on ViT-BImproved
SNCLR vs. baselines on COCO detection and instance segmentationResNet-50 Mask R-CNN · COCO det./seg. 1xAP^bb / AP^mk: 39.4 AP^bb at 200 ep equals BYOL-800; 39.9 at 800 ep vs BYOL 39.4Improved
cross-attention module uses learned linear projections instead of identity mappingspositiveness attention module · ImageNet linear eval (ViT-S)top-1 accuracyNo clear effect

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