Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1]
Generalized Zero-Shot Learning with Deep Calibration Network
Authors: Shichen Liu, Mingsheng Long, Jianmin Wang, Michael I. Jordan
NeurIPS 2018 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We perform extensive evaluation with state of the art methods for zero-shot and generalized zero-shot learning on four benchmark datasets, which will validate the efficacy of the proposed DCN approach. |
| Researcher Affiliation | Academia | School of Software, Tsinghua University, China KLiss, MOE; BNRist; Research Center for Big Data, Tsinghua University, China University of California, Berkeley, Berkeley, USA EMAIL EMAIL EMAIL |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper mentions implementing the approach using PyTorch, with a footnote pointing to https://pytorch.org, but does not provide specific access to their own source code for the described methodology. |
| Open Datasets | Yes | Animals with Attributes (Aw A) [32] is a widely-used dataset for coarse-grained zero-shot learning... Caltech-UCSD-Birds-200-2011 (CUB) [50] is a fine-grained dataset... SUN Attribute (SUN) [39] is a fine-grained dataset... Attribute Pascal and Yahoo (a PY) [13] is a small-scale dataset... |
| Dataset Splits | Yes | SUN Attribute (SUN) [39] is a fine-grained dataset, medium-scale in the number of images, containing 14,340 images from 717 types of scenes annotated with 102 attributes. We adopt the standard split of [32], containing 645 source classes (in which 65 classes are used for validation) and 72 target classes. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., exact GPU/CPU models, memory amounts) used for running its experiments. |
| Software Dependencies | No | Our end-to-end trainable approach is implemented using Py Torch1. (footnote 1 refers to https://pytorch.org) - No specific version numbers for software dependencies are provided. |
| Experiment Setup | Yes | We use stochastic gradient descent with 0.9 momentum and a mini-batch size of 64. We cross-validate the learning rate in [10 4, 10 1], the temperature τ [0.1, 10], and the entropy-penalty parameter λ [10 3, 10 1]. |