AI Paper Atlas

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

Your Self-Supervised Projection Head Captures Object Co-Occurrence Statistics

Arthur Aubret, Jochen Triesch, Céline Teulière

NeurIPS 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Unsupervised object and part discovery · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Hypothesizes that common self-supervised learning pretext tasks implicitly model object co-occurrence statistics, and tests this using curated datasets of segmented objects from existing vision benchmarks.

Problem

Understanding the underlying principles that drive the success of self-supervised visual representation learning remains underexplored; the paper asks whether SSL pretext tasks implicitly capture object co-occurrence statistics.

Approach

Proposes that the projection head of SSL models encodes object co-occurrence statistics, testing this hypothesis with curated datasets of segmented objects derived from existing vision benchmarks.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use an internal projection-head layer instead of the final backbone layer to encode object co-occurrencespretrained SSL models (MoCoV3, BYOL, VICReg, DINO) · COCO-THINGSRSA Kendall's tau: 9.0 -> 33.4 (DINO-ViT-B)Improved
add a non-linear projection head during pre-training (ablation)SimCLR, BYOL, DINO · COCO-THINGS co-occurrence encodingRSA Kendall's tau: 2.3 -> 22.5 (BYOL)Improved
add a non-linear projection head during pre-training (ablation)SimCLR · ADE20k-THINGScontext accuracy: 24.5 -> 22.6Hurt
use projection head layer instead of backbone for human similarity judgmentspretrained SSL models · THINGS odd-one-out human judgmentsRSA Kendall's tau: 18.3 -> 22.7 (BYOL-R50)Improved
use a single linear projection layer instead of deeper head (ablation)SimCLR, BYOL, DINO · COCO-THINGSco-occurrence encoding vs backbone: SimCLR-1 mP.0 -0.4 vs backbone 4.3Hurt
sample positive pairs from different classes of the same context with probability p_c=0.3 (ablation)SimCLR and DINO pre-training · ImageNet-1k, 100 epochs, n_c=300accuracy: up to +5.52%Improved
raise p_c above 0.3 for cross-class same-context positive pairs (ablation)SimCLR and DINO pre-training · ImageNet-1k, 100 epochsaccuracyHurt
increase the number of controlled co-occurrence contexts n_c (ablation)SimCLR and DINO pre-training · ImageNet-1k, p_c=0.3accuracyImproved
go deeper in the projection head for in-context one-shot category classification (ablation)pretrained SSL models · COCO-THINGScategory classification accuracy: 92.9 -> 86.0 (DINO-ViT-B, B to P.3)Hurt
use the last linear layer of the projection head (ablation)pretrained SSL models · COCO-THINGSRSA Kendall's tau: 13.9 vs 33.4 (DINO-ViT-B P.2 vs P.1 max)Hurt
compute image-level instead of category-prototype similarities (ablation)co-occurrence metrics · COCO-THINGS, ADE20k-THINGS, LVIS-LVIScontext accuracyHurt
vary number of context clusters (3 to 300) when scoring projection layers (ablation)SimCLR, BYOL, DINO · LVIS-LVIS context accuracycontext accuracyMixed

Experimental setup

Datasets: segmented objects curated from existing vision benchmarks

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