Research map / Detection and segmentation / CNN features
BIND: Binary Integrated Net Descriptors for Texture-Less Object Recognition
Jacob Chan, Jimmy Addison Lee, Qian Kemao
Check your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use multi-layer binary nets to encode object edges and internal homogeneous regions | BIND · MOD | recognition performance | Improved |
| Use multi-layer binary nets to encode object edges and internal homogeneous regions | BIND · D-Textureless | recognition performance | Improved |
| Use multi-layer binary nets to encode object edges and internal homogeneous regions | BIND · CMU-KO8 | true positive rate | Improved |
| Use polarity-invariant angle primitives and two-way matching | BIND · MOD | recognition performance | Improved |
| Use high-resolution regional nets to encode homogeneous space and edges | BIND · D-Textureless | recognition performance | Improved |
| Use maximal linelet fragmentation | BIND · BIND experiments | recognition speed | Hurt |
| Use maximal linelet fragmentation | BIND · BIND experiments | recognition performance | No clear effect |
| Use byte-indexed storage that stores only informative bytes | BIND · BIND experiments | descriptor storage: about 50% | Improved |
| Use byte-indexed storage that stores only informative bytes | BIND · BIND experiments | match speed | Improved |
| Use BIND’s precise linelet and description process | BIND · BIND experiments | runtime speedup versus BORDER: 2.2 times faster | Improved |
| Apply BIND’s texture-less-specific 3-layer bit combination to low-homogeneity objects | BIND · low-homogeneity objects | recognition performance | Hurt |
Later papers that compared with this method
1 later accepted paper reports BIND as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Object-level Semantic and Spatial Distillation for Open Vocabulary Detection (ICML 2026 · better on 1 of 1 shared result)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- BORDER: An Oriented Rectangles Approach to Texture-Less Object Recognition (CVPR 2016 · similarity 0.88)
- Binary Online Learned Descriptors (TPAMI 2017 · similarity 0.84)
- Deep TEN: Texture Encoding Network (CVPR 2017 · similarity 0.83)
- Unsupervised Deep Learning of Compact Binary Descriptors (TPAMI 2018 · similarity 0.82)
- Learning Compact Binary Descriptors With Unsupervised Deep Neural Networks (CVPR 2016 · similarity 0.82)
- Theoretically Achieving Continuous Representation of Oriented Bounding Boxes (CVPR 2024 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
