mlsanityData to 7 Oct 2026

DADO: A Depth-Attention framework for Object Discovery

arXiv 2510.07089 ↗First posted 8 Oct 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Unsupervised object discovery, the task of identifying and localizing objects in images without human-annotated labels, remains a significant challenge and a growing focus in computer vision. In this work, we introduce a novel model, DADO (Depth-Attention self-supervised technique for Discovering unseen Objects), which combines an attention mechanism and a depth model to identify potential objects in images. To address challenges such as noisy attention maps or complex scenes with varying depth planes, DADO employs dynamic weighting to adaptively emphasize attention or depth features based on the global characteristics of each image. We evaluated DADO on standard benchmarks, where it outperforms state-of-the-art methods in object discovery accuracy and robustness without the need for fine-tuning.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 25 of its 35 references that are in the map. First posted on arXiv 8 Oct 2025.

Builds on

25 of 35 references.

References · 25

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2023Segment Anythingcited by 8,158
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  7. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  8. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  9. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  10. 2021Vision Transformers for Dense Predictioncited by 1,789
  11. 2021Do Vision Transformers See Like Convolutional Neural Networks?cited by 671
  12. 2021Intriguing Properties of Vision Transformerscited by 446
13 more
  1. 2021Localizing Objects with Self-Supervised Transformers and no Labelscited by 227
  2. 2018Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approachcited by 119
  3. 2022TokenCut: Segmenting Objects in Images and Videos with Self-supervised Transformer and Normalized Cutcited by 111
  4. 2015Unsupervised Object Discovery and Localization in the Wild: Part-based Matching with Bottom-up Region Proposalscited by 69
  5. 2020Three Ways to Improve Semantic Segmentation with Self-Supervised Depth Estimationcited by 66
  6. 2020Toward unsupervised, multi-object discovery in large-scale image collectionscited by 65
  7. 2021Large-Scale Unsupervised Object Discoverycited by 54
  8. 2021Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimationcited by 25
  9. 2023MOST: Multiple Object localization with Self-supervised Transformers for object discoverycited by 17
  10. 2023Multi-Object Discovery by Low-Dimensional Object Motioncited by 16
  11. 2023Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Surveycited by 16
  12. 2023Self-attention in Vision Transformers Performs Perceptual Grouping, Not Attentioncited by 15
  13. 2024Unsupervised Object Discovery: A Comprehensive Survey and Unified Taxonomycited by 4

Built on by

Not cited yet.