Localizing by Describing: Attribute-Guided Attention Localization for Fine-Grained Recognition

Authors: Xiao Liu, Jiang Wang, Shilei Wen, Errui Ding, Yuanqing Lin

AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on the CUB-200-2011 dataset (Wah et al. 2011) demonstrate the superiority of the proposed scheme on both fine-grained recognition and attribute recognition.
Researcher Affiliation Industry Xiao Liu, Jiang Wang, Shilei Wen, Errui Ding, Yuanqing Lin Baidu Research {liuxiao12, wenshilei, dingerrui, linyuanqing}@baidu.com wangjiangb@gmail.com
Pseudocode Yes Algorithm 1 Localizing by describing algorithm:
Open Source Code No The paper does not provide any statement or link regarding the availability of its source code.
Open Datasets Yes We conduct experiments on the CUB-200-2011 datasets (Wah et al. 2011).
Dataset Splits No The paper states 'where 5, 994 images are for training, and the rest 5, 794 images are for testing' but does not explicitly detail a separate validation split or its size/methodology.
Hardware Specification Yes We train the models using Stochastic Gradient Descent (SGD) with momentum of 0.9, epoch number of 150, weight decay of 0.001, and a mini-batch size of 28 on four K40 GPUs.
Software Dependencies No The paper mentions using 'Res Net-50 (He et al. 2016)' and 'ROI-pooled feature maps (Girshick 2015)' but does not specify software dependencies with version numbers (e.g., Python, TensorFlow, PyTorch versions).
Experiment Setup Yes We train the models using Stochastic Gradient Descent (SGD) with momentum of 0.9, epoch number of 150, weight decay of 0.001, and a mini-batch size of 28 on four K40 GPUs. The initial learning rate is set at 0.0001 and reduced twice with a ratio of 0.1 after 50 and 100 epoches. An additional dropout layer with an ratio of 0.5 is added after res5c , and the size of fc15 is changed from 1000 to 200.