mlsanityData to 7 Oct 2026

Matching Semantically Similar Non-Identical Objects

arXiv 2403.08227 ↗First posted 13 Mar 2024cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Not identical but similar objects are ubiquitous in our world, ranging from four-legged animals such as dogs and cats to cars of different models and flowers of various colors. This study addresses a novel task of matching such non-identical objects at the pixel level. We propose a weighting scheme of descriptors, Semantic Enhancement Weighting (SEW), that incorporates semantic information from object detectors into existing sparse feature matching methods, extending their targets from identical objects captured from different perspectives to semantically similar objects. The experiments show successful matching between non-identical objects in various cases, including in-class design variations, class discrepancy, and domain shifts (e.g., photo vs. drawing and image corruptions). The code is available at https://github.com/Circ-Leaf/NIOM .

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 65 of its 101 references that are in the map. First posted on arXiv 13 Mar 2024.

Builds on

65 of 101 references.

References · 65

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  6. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  7. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  8. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  9. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  10. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  11. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  12. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
38 more
  1. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  2. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 983
  3. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  4. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  5. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
  6. 2018Computational Optimal Transportcited by 765
  7. 2020Quantifying Attention Flow in Transformerscited by 759
  8. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  9. 2023LightGlue: Local Feature Matching at Light Speedcited by 583
  10. 2023Emergent Correspondence from Image Diffusioncited by 437
  11. 2020DISK: Learning local features with policy gradientcited by 310
  12. 2023A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondencecited by 297
  13. 2023RoMa: Robust Dense Feature Matchingcited by 296
  14. 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 261
  15. 2015YFCC100M: The New Data in Multimedia Researchcited by 234
  16. 2023Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondencecited by 211
  17. 2023Tracking Everything Everywhere All at Oncecited by 190
  18. 2021COTR: Correspondence Transformer for Matching Across Imagescited by 182
  19. 2022DKM: Dense Kernelized Feature Matching for Geometry Estimationcited by 174
  20. 2022ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformercited by 170
  21. 2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 155
  22. 2017Convolutional neural network architecture for geometric matchingcited by 138
  23. 2020Patch2Pix: Epipolar-Guided Pixel-Level Correspondencescited by 128
  24. 2023Unsupervised Semantic Correspondence Using Stable Diffusioncited by 120
  25. 2024Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speedcited by 119
  26. 2020Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutionscited by 92
  27. 2021Learning to Match Features with Seeded Graph Matching Networkcited by 92
  28. 2023Telling Left from Right: Identifying Geometry-Aware Semantic Correspondencecited by 85
  29. 2021CATs: Cost Aggregation Transformers for Visual Correspondencecited by 77
  30. 2023GlueStick: Robust Image Matching by Sticking Points and Lines Togethercited by 65
  31. 2021GAN-Supervised Dense Visual Alignmentcited by 61
  32. 2017End-to-end weakly-supervised semantic alignmentcited by 60
  33. 2023Dense Optical Tracking: Connecting the Dotscited by 58
  34. 2019Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Featurescited by 56
  35. 2023SiLK -- Simple Learned Keypointscited by 54
  36. 2022CATs++: Boosting Cost Aggregation with Convolutions and Transformerscited by 53
  37. 2017SCNet: Learning Semantic Correspondencecited by 48
  38. 2017Proposal Flow: Semantic Correspondences from Object Proposalscited by 46

50 most cited of 65 All 65 (JSON)

Built on by

Not cited yet.