Saliency Guided End-to-End Learning for Weakly Supervised Object Detection
Authors: Baisheng Lai, Xiaojin Gong
IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on PASCAL VOC demonstrate that our approach outperforms all state-of-the-arts. |
| Researcher Affiliation | Academia | College of Information Science & Electronic Engineering, Zhejiang University, China {laibs,gongxj}@zju.edu.cn |
| Pseudocode | No | The paper describes the network architecture and training procedure in text and with diagrams (Figure 1) but does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any links to open-source code for the described methodology, nor does it state that the code will be made publicly available. |
| Open Datasets | Yes | The experiments are conducted on the PASCAL VOC 2007 and 2012 datasets [Everingham et al., 2010], which are the benchmark most widely used in WSOD. |
| Dataset Splits | Yes | The VOC 2007 dataset contains 2501 training, 2510 validation, and 4952 test images. VOC 2012 has 5717 training, 5823 validation, and 10991 test images. |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used to run the experiments. It only mentions "Our approach is implemented using the Mat Conv Net toolbox" without further hardware details. |
| Software Dependencies | No | The paper states "Our approach is implemented using the Mat Conv Net toolbox [Vedaldi and Lenc, 2015]" but does not provide specific version numbers for this or any other software dependencies. |
| Experiment Setup | Yes | For training, we run 20 epochs, in which the first 10 epochs take a learning rate of 10 5 and the second 10 epochs take 10 6. Each image is randomly flipped and scaled to have maximal width or height of {480, 576, 688, 864, 1200} with respect to the original aspect ratio. The hyper parameters in our network are set empirically as σ = 103, λ1 = 0.1, λ2 = 1 and λ3 = 5 10 4. |