mlsanityData to 14 Oct 2026

Holistic Order Prediction in Natural Scenes

arXiv 2510.01704 ↗First posted 2 Oct 2025cs.CV cs.AI cs.LGcited by 1

Not on the map. Why?

Abstract (arXiv)

Even in controlled settings, understanding instance-wise geometries is a challenging task for a wide range of visual models. Although specialized systems exist, modern arts rely on expensive input formats (category labels, binary segmentation masks) and inference costs (a quadratic amount of forward passes). We mitigate these limitations by proposing InstaFormer, a network capable of holistic order prediction. That is, solely given an input RGB image, InstaFormer returns the full occlusion and depth orderings for all the instances in the scene in a single forward pass. At its core, InstaFormer relies on interactions between object queries and latent mask descriptors that semantically represent the same objects while carrying complementary information. We comprehensively benchmark and ablate our approach to highlight its effectiveness. Our code and models are open-source and available at this URL: https://github.com/SNU-VGILab/InstaOrder.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 43 of its 52 references that are in the map. First posted on arXiv 2 Oct 2025.

Builds on

43 of 52 references.

References · 43

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  6. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  7. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  8. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  9. 2023Segment Anythingcited by 8,234
  10. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  11. 2023Visual Instruction Tuningcited by 7,869
  12. 2020End-to-End Object Detection with Transformerscited by 7,414
31 more
  1. 2023Improved Baselines with Visual Instruction Tuningcited by 4,418
  2. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  3. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
  4. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  5. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  6. 2016Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotationscited by 2,656
  7. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  8. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  9. 2024Depth Anything V2cited by 1,422
  10. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  11. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,152
  12. 2024Grounded SAM: Assembling Open-World Models for Diverse Visual Taskscited by 929
  13. 2023LISA: Reasoning Segmentation via Large Language Modelcited by 776
  14. 2022AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognitioncited by 719
  15. 2024SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilitiescited by 706
  16. 2024PaliGemma: A versatile 3B VLM for transfercited by 696
  17. 2023Ferret: Refer and Ground Anything Anywhere at Any Granularitycited by 509
  18. 2023GLaMM: Pixel Grounding Large Multimodal Modelcited by 455
  19. 2019COMET: Commonsense Transformers for Automatic Knowledge Graph Constructioncited by 450
  20. 2018Rethinking ImageNet Pre-trainingcited by 377
  21. 2023Repurposing Diffusion-Based Image Generators for Monocular Depth Estimationcited by 327
  22. 2024SpatialRGPT: Grounded Spatial Reasoning in Vision Language Modelscited by 311
  23. 2021SwinTrack: A Simple and Strong Baseline for Transformer Trackingcited by 126
  24. 2015Semantic Amodal Segmentationcited by 103
  25. 2020Self-Supervised Scene De-occlusioncited by 96
  26. 2023CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentationcited by 96
  27. 2023You Only Segment Once: Towards Real-Time Panoptic Segmentationcited by 40
  28. 2024LocCa: Visual Pretraining with Location-aware Captionerscited by 35
  29. 2021Instance-wise Occlusion and Depth Orders in Natural Scenescited by 31
  30. 2023Extending CLIP's Image-Text Alignment to Referring Image Segmentationcited by 19
  31. 2015Monocular Object Instance Segmentation and Depth Ordering with CNNscited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Taking Shortcuts for Categorical VQA Using Super Neuronscited by 0