Pith. sign in

REVIEW 5 cited by

DiffusionSeg: Adapting Diffusion Towards Unsupervised Object Discovery

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2303.09813 v1 pith:B7GM7PRF submitted 2023-03-17 cs.CV cs.AI

Chaofan Ma , Yuhuan Yang , Chen Ju , Fei Zhang , Jinxiang Liu , Yu Wang , Ya Zhang , Yanfeng Wang This is my paper · ORCID
classification cs.CVcs.AI
keywords diffusionmodelsobjectunsuperviseddatadiscoveryadaptingdiffusionseg
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Learning from a large corpus of data, pre-trained models have achieved impressive progress nowadays. As popular generative pre-training, diffusion models capture both low-level visual knowledge and high-level semantic relations. In this paper, we propose to exploit such knowledgeable diffusion models for mainstream discriminative tasks, i.e., unsupervised object discovery: saliency segmentation and object localization. However, the challenges exist as there is one structural difference between generative and discriminative models, which limits the direct use. Besides, the lack of explicitly labeled data significantly limits performance in unsupervised settings. To tackle these issues, we introduce DiffusionSeg, one novel synthesis-exploitation framework containing two-stage strategies. To alleviate data insufficiency, we synthesize abundant images, and propose a novel training-free AttentionCut to obtain masks in the first synthesis stage. In the second exploitation stage, to bridge the structural gap, we use the inversion technique, to map the given image back to diffusion features. These features can be directly used by downstream architectures. Extensive experiments and ablation studies demonstrate the superiority of adapting diffusion for unsupervised object discovery.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Leveraging Prior Knowledge of Diffusion Model for Person Search

    cs.CV 2025-10 conditional novelty 6.0 of 10

    DiffPS, a frozen Stable Diffusion backbone with cross-attention, frequency-refinement, and semantic-aggregation modules, achieves 97.8% mAP on CUHK-SYSU and 62.0% mAP on PRW.

  2. Decouple before Align: Visual Disentanglement Enhances Prompt Tuning

    cs.CV 2025-08 conditional novelty 6.0 of 10

    Decoupling images into foreground and background before aligning them with text improves CLIP prompt tuning on few-shot and generalization benchmarks.

  3. ConText: Driving In-context Learning for Text Removal and Segmentation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    ConText is the first visual in-context learning model for text removal and segmentation, chaining the two tasks and using self-prompting to reach new state-of-the-art scores.

  4. G4Seg: Generation for Inexact Segmentation Refinement with Diffusion Models

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Using the discrepancy between an image and its mask-conditioned Stable Diffusion reconstruction, G4Seg refines coarse segmentation masks by aligning pixels in CLIP feature space and mixing foreground probabilities.

  5. MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition

    cs.CV 2025-06 conditional novelty 5.0 of 10

    MoMa adapts frozen CLIP to video by injecting Mamba-computed scale and bias into each layer, improving accuracy and efficiency on multiple action recognition benchmarks.

Pith tools