Crisp Boundary Detection Using Pointwise Mutual Information
Open accessIntegrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The idea that representation learning algorithms may boil down to finding an embedding where similarity equals PMI is consistent with prior works that used PMI as a similarity measure for clustering in vision and language.
“We note that this idea is consistent with prior works that have used PMI as a similarity measure for clustering in vision and language (e.g., Isola et al. (2014); Isola (2015); Isola et al. (2016); Chambers & Jurafsky (2008)).”
From The Platonic Representation Hypothesis (2024) · cites this paper as Isola et al. (2014)
Cited by
Sorted by citations
Robust guided image filtering using Nonconvex potentials
Ham, B., Cho, M., & Ponce, J. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2669034 · Cited by 219 · see citing works
On the Binding Problem in Artificial Neural Networks
Greff, K., van Steenkiste, S., & Schmidhuber, J. (2020) · arXiv · doi:10.48550/arxiv.2012.05208 · Cited by 102 · see citing works
The Platonic Representation Hypothesis
Huh, M., Cheung, B., Wang, T., & Isola, P. (2024) · arXiv · doi:10.48550/arxiv.2405.07987 · Cited by 35 · see citing works
“We note that this idea is consistent with prior works that have used PMI as a similarity measure for clustering in vision and language ( e.g. , Isola et al. (2014); Isola (2015); Isola et al. (2016); Chambers & Jurafsky (2008)).”
Self-citation
- Authors
- Isola, P., Zoran, D., Krishnan, D., & Adelson, E. H.
- Affiliations
- Massachusetts Institute of Technology (US)
- Venue
- Lecture Notes in Computer Science
- Publisher
- Springer International Publishing
- Published
- 2014
- Pages
- 799-814
- ISSN
- 0302-9743 (ISSN-L)
- 1611-3349
- OpenAlex
- W105270443
- Cited by
- 199
- References
- 0
- Citations by year
- 2026: 4 · 2025: 10 · 2024: 9 · 2023: 10 · 2022: 18 · 2021: 22 · 2020: 19 · 2019: 12 · 2018: 20 · 2017: 27 · 2016: 22 · 2015: 24 · 2014: 2
- FWCI
- 13.44
- Type
- conference paper
- Language
- en
- Open access
- green
- orcid.org
- Licence
- cc-by-nc-sa
- www.springer.com/tdm (tdm)
- Locations
- Lecture notes in computer science (publishedVersion)
- DSpace@MIT (Massachusetts Institute of Technology) (submittedVersion, cc-by-nc-sa)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Keywords
- boundary detection, pointwise mutual information, object segmentation, spectral clustering, statistical dependence, BSDS500, image segmentation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
