Pith. sign in

REVIEW 11 cited by

Unsupervised Semantic Segmentation by Distilling Feature Correspondences

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2203.08414 v1 pith:B3EK55QF submitted 2022-03-16 cs.CV cs.AIcs.LGstat.ML

Unsupervised Semantic Segmentation by Distilling Feature Correspondences

classification cs.CV cs.AIcs.LGstat.ML
keywords textbffeaturessemanticunsupervisedfeatureformsegmentationsemantically
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Unsupervised semantic segmentation aims to discover and localize semantically meaningful categories within image corpora without any form of annotation. To solve this task, algorithms must produce features for every pixel that are both semantically meaningful and compact enough to form distinct clusters. Unlike previous works which achieve this with a single end-to-end framework, we propose to separate feature learning from cluster compactification. Empirically, we show that current unsupervised feature learning frameworks already generate dense features whose correlations are semantically consistent. This observation motivates us to design STEGO ($\textbf{S}$elf-supervised $\textbf{T}$ransformer with $\textbf{E}$nergy-based $\textbf{G}$raph $\textbf{O}$ptimization), a novel framework that distills unsupervised features into high-quality discrete semantic labels. At the core of STEGO is a novel contrastive loss function that encourages features to form compact clusters while preserving their relationships across the corpora. STEGO yields a significant improvement over the prior state of the art, on both the CocoStuff ($\textbf{+14 mIoU}$) and Cityscapes ($\textbf{+9 mIoU}$) semantic segmentation challenges.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Resolving Long-Tail Ambiguity in Unsupervised 3D Point Cloud Segmentation with Language Priors

    cs.CV 2026-05 unverdicted novelty 7.0

    LangTail uses entity-level semantic priors from language models aligned via contrastive learning in a hierarchical clustering setup to resolve long-tail ambiguity, yielding +13.5, +12.9, and +8.9 mIoU gains on ScanNet...

  2. Boxes2Pixels: Learning Defect Segmentation from Noisy SAM Masks

    cs.CV 2026-04 accept novelty 7.0

    Boxes2Pixels distills noisy SAM pseudo-masks into a compact DINOv2-based student with auxiliary localization and one-sided self-correction, delivering +6.97 anomaly mIoU and +9.71 binary IoU gains over baselines on wi...

  3. Learning Cross-View Semantic Priors for Single-Reference Unseen Object Pose Estimation

    cs.CV 2026-06 unverdicted novelty 6.0

    New CVSI module with IVSP and RAGC losses for single-reference unseen object 6D pose estimation that reports state-of-the-art results on six BOP benchmarks.

  4. Registers Matter for Pixel-Space Diffusion Transformers

    cs.CV 2026-05 unverdicted novelty 6.0

    Register tokens enhance pixel-space DiT training and output quality via cleaner high-noise feature maps, and a dual-stream design adds further gains with little overhead.

  5. TACoS: Weakly Supervised Learning of Two-Dimensional Materials from Scribble Annotations to Precise Segmentation

    cs.CV 2026-07 conditional novelty 5.0

    TACoS achieves over 96% of fully supervised segmentation performance on 2D material flakes using less than 0.6% annotated pixels via a unified framework of consistency learning, tree energy regularization, and asymmet...

  6. Lightweight 3D Feature Pretraining by Bayesian Inversion of 2D Foundation Models

    cs.CV 2026-06 unverdicted novelty 5.0

    Casper3D is a backbone-agnostic variational model that infers stable 3D semantics from noisy 2D embeddings by treating them as observations of a latent 3D state and training via held-out viewpoint prediction.

  7. Unsupervised Semantic Segmentation Facilitates Model Understanding

    cs.CV 2026-05 unverdicted novelty 5.0

    A visualization protocol based on unsupervised semantic segmentation reveals positional biases, scaling behaviors, and boundary artifacts across self-supervised vision transformer models.

  8. Unsupervised Semantic Segmentation Facilitates Model Understanding

    cs.CV 2026-05 unverdicted novelty 5.0

    A visualization protocol using unsupervised semantic segmentation outputs reveals positional biases, scaling behaviors, and boundary artifacts in self-supervised ViTs and distinguishes them from locality bias.

  9. Registers Matter for Pixel-Space Diffusion Transformers

    cs.CV 2026-05 unverdicted novelty 5.0

    Register tokens improve pixel-space Diffusion Transformers by cleaning high-noise feature maps, and Register Guidance amplifies that effect.

  10. Information theoretic underpinning of self-supervised learning by clustering

    cs.LG 2026-05 unverdicted novelty 5.0

    SSL clustering is derived as KL-divergence optimization where a teacher-distribution constraint normalizes via inverse cluster priors and simplifies to batch centering by Jensen's inequality.

  11. Unsupervised Monocular Road Segmentation for Autonomous Driving via Scene Geometry

    cs.CV 2025-10 unverdicted novelty 5.0

    An unsupervised monocular road segmentation method generates initial labels from horizon and quadrilateral geometric priors then refines them via temporal feature tracking and mutual information to reach 0.86 IoU on C...