Pith. sign in

REVIEW 10 cited by

Localizing Objects with Self-Supervised Transformers and no Labels

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 2109.14279 v1 pith:5S6ALM4J submitted 2021-09-29 cs.CV

classification cs.CV
keywords imageobjectobjectsresultsdiscoverylocalizinglostpoints
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Localizing objects in image collections without supervision can help to avoid expensive annotation campaigns. We propose a simple approach to this problem, that leverages the activation features of a vision transformer pre-trained in a self-supervised manner. Our method, LOST, does not require any external object proposal nor any exploration of the image collection; it operates on a single image. Yet, we outperform state-of-the-art object discovery methods by up to 8 CorLoc points on PASCAL VOC 2012. We also show that training a class-agnostic detector on the discovered objects boosts results by another 7 points. Moreover, we show promising results on the unsupervised object discovery task. The code to reproduce our results can be found at https://github.com/valeoai/LOST.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 10 Pith papers

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

  1. Repurposing Stable Diffusion Attention for Training-Free Unsupervised Interactive Segmentation

    cs.CV 2024-11 conditional novelty 7.0 of 10

    By counting Markov-chain hitting times in Stable Diffusion attention, M2N2 performs training-free interactive segmentation that outperforms trained unsupervised methods on three of four benchmarks.

  2. Human-like Object Grouping in Self-supervised Vision Transformers

    cs.CV 2026-03 conditional novelty 6.5 of 10

    DINO self-supervised transformers best predict human same/different object RTs; object-centric patch affinity and Gram-matrix distillation explain and transfer the alignment.

  3. `Attention-Guided Cross-Temporal Clustering for Self-Supervised Video Object Segmentation

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A frozen SAM2 backbone with adaptive token selection and symmetric KL clustering achieves competitive self-supervised video object segmentation by aligning soft part assignments across time.

  4. Discovering and using Spelke segments

    cs.CV 2025-07 conditional novelty 6.0 of 10

    SpelkeNet, a self-supervised video world model, discovers Spelke segments in static images by aggregating motion correlations across imagined pokes.

  5. FIX-CLIP: Dual-Branch Hierarchical Contrastive Learning via Synthetic Captions for Better Understanding of Long Text

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A dual-branch CLIP training pipeline with regional prompts and hierarchical feature alignment reaches state-of-the-art on long- and short-text retrieval.

  6. Cut out and Replay: A Simple yet Versatile Strategy for Multi-Label Online Continual Learning

    cs.LG 2025-05 conditional novelty 6.0 of 10

    CUTER replays cropped label-specific object regions instead of whole multi-label images, and regularizes patch-feature graphs to keep the cropping ability alive, improving multi-label online continual learning across ...

  7. Few-Shot Adaptation of Training-Free Foundation Model for 3D Medical Image Segmentation

    cs.CV 2025-01 conditional novelty 6.0 of 10

    Using a handful of labeled slices as memory in SAM2's video-segmentation pipeline enables prompt-free, fine-tuning-free segmentation of 3D medical volumes.

  8. DINOde: Continuous Vision-Text Alignment for Open-Vocabulary Semantic Segmentation

    cs.CV 2026-07 conditional novelty 5.0 of 10

    A 10-step ODE text-to-vision flow with tangent-space projection outperforms single-step MLP projection for open-vocabulary semantic segmentation, reaching 49.5 average mIoU without mask refinement.

  9. Mixing Configurations for Downstream Prediction

    cs.LG 2025-10 conditional novelty 5.0 of 10

    Mixing multiple resolution clusterings of an embedding, aligned between train and test, and fused by attention, improves downstream regression and classification over single-resolution baselines.

  10. Object-Centric Cropping for Visual Few-Shot Classification

    cs.CV 2025-07 unverdicted novelty 4.0 of 10

    The supplied full text (arXiv:2508.00225) is a different paper from the claimed metadata (arXiv:2508.00218), so no claim about few-shot classification is backed by the manuscript.

Pith tools