Matching Pixels Using Co-Occurrence Statistics
We propose a new error measure for matching pixels that is based on co-occurrence statistics. The measure relies on a co-occurrence matrix that counts the number of times pairs of pixel values co-occur within a window. The error incurred by matching a pair of pixels is inverse proportional to the probability that their values co-occur together, and not their color difference. This measure also works with features other than color, e.g. deep features. We show that this improves the state-of-the-art performance of template matching on standard benchmarks. We then propose an embedding scheme that maps the input image to an embedded image such that the Euclidean distance between pixel values in the embedded space resembles the co-occurrence statistics in the original space. This lets us run existing vision algorithms on the embedded images and enjoy the power of co-occurrence statistics for free. We demonstrate this on two algorithms, the Lucas-Kanade image registration and the Kernelized Correlation Filter (KCF) tracker. Experiments show that performance of each algorithm improves by about 10%.
Code (0)
등록된 구현이 없습니다.
Tasks
Image RegistrationTemplate MatchingSimilar Papers 제목 키워드 기반
Learning to Segment using Summary Statistics and Weak Supervision
Medical experts often manually segment images to obtain diagnostic statistics and discard the resulting annotations. We aim to train segmentation models to alleviate this burden, but constrained to the retained summary s…
Image ReconstructionOn-the-Fly Rectification for Robust Large-Vocabulary Topic Inference
Across many data domains, co-occurrence statistics about the joint appearance of objects are powerfully informative. By transforming unsupervised learning problems into decompositions of co-occurrence statistics, spectra…
Community DetectionNgram2vec: Learning Improved Word Representations from Ngram Co-occurrence Statistics
The existing word representation methods mostly limit their information source to word co-occurrence statistics. In this paper, we introduce ngrams into four representation methods: SGNS, GloVe, PPMI matrix, and its SVD …
Language ModelingLanguage ModellingWord EmbeddingsUnsupervised Learning of Distributional Relation Vectors
Word embedding models such as GloVe rely on co-occurrence statistics to learn vector representations of word meaning. While we may similarly expect that co-occurrence statistics can be used to capture rich information ab…
RelationRelation ExtractionWord EmbeddingsModeling Semantic Relatedness using Global Relation Vectors
Word embedding models such as GloVe rely on co-occurrence statistics from a large corpus to learn vector representations of word meaning. These vectors have proven to capture surprisingly fine-grained semantic and syntac…
Relation