Localized Structured Prediction
Authors: Carlo Ciliberto, Francis Bach, Alessandro Rudi
NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate the proposed estimator on simulated as well as real data. We highlight how locality leads to improved generalization performance, in particular when only few training examples are available. Learning the Direction of Ridges for Fingerprint. Similarly to [37], we considered the problem of detecting the pointwise direction of ridges in a fingerprint image on the FVC04 dataset1 comprising 80 grayscale 640 480 input images depicting fingerprints and corresponding output images encoding in each pixel the local direction of the ridges of the input fingerprint as an angle 2 [ , ]. |
| Researcher Affiliation | Academia | Carlo Ciliberto 1 Francis Bach 2 Alessandro Rudi 2 c.ciliberto@imperial.ac.uk francis.bach@inria.fr alessandro.rudi@inria.fr 1 Department of Electrical and Electronic Engineering, Imperial College, London, UK. 2 INRIA Département d informatique, École Normale Supérieure PSL Research University, Paris, France. |
| Pseudocode | Yes | Algorithm 1 |
| Open Source Code | No | The paper does not provide an explicit statement about the release of source code for the methodology described, nor does it include a link to a code repository. |
| Open Datasets | Yes | Learning the Direction of Ridges for Fingerprint. Similarly to [37], we considered the problem of detecting the pointwise direction of ridges in a fingerprint image on the FVC04 dataset1 comprising 80 grayscale 640 480 input images depicting fingerprints and corresponding output images encoding in each pixel the local direction of the ridges of the input fingerprint as an angle 2 [ , ]. |
| Dataset Splits | Yes | We randomly sampled 50/30 images for training/testing, performing 5-fold cross-validation on λ in [10 6, 10] (log spaced) and the kernel bandwidth in [10 3, 1]. |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory, or cloud instances) used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers (e.g., library or solver names with versions). |
| Experiment Setup | Yes | We randomly sampled 50/30 images for training/testing, performing 5-fold cross-validation on λ in [10 6, 10] (log spaced) and the kernel bandwidth in [10 3, 1]. For Local-4 and Local-LS we built an auxiliary set with m = 30000 random patches (see Sec. 4), sampled from the 50 training images. The parameter λ was chosen by hold-out cross-validation in [10 6, 10] (log spaced). |