Submodular Asymmetric Feature Selection in Cascade Object Detection
Authors: Baosheng Yu, Meng Fang, Dacheng Tao, Jie Yin
AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We use face detection as a case study and perform experiments on two real-world face detection datasets. The experimental results demonstrate that our algorithm SAFS outperforms the state-of-art feature selection algorithms in cascade object detection, such as FFS and LACBoost. |
| Researcher Affiliation | Collaboration | Centre for Quantum Computation and Intelligent Systems, University of Technology, Sydney Department of Computing and Information Systems, The University of Melbourne CSIRO, Australia |
| Pseudocode | Yes | Algorithm 1 The cascade framework; Algorithm 2 The SAFS algorithm |
| Open Source Code | No | The paper does not provide any statement or link indicating that the source code for the described methodology is publicly available. |
| Open Datasets | Yes | CBCL Face Database #1 2: It consists of a training set of 6977 images (2429 face and 4548 non-face) and a test set of 24045 images (472 face and 23573 non-face) and all face images are aligned to a base resolution of 19 19 pixels. Caltech 10,000 Web Faces 3: It contains images of people collected from the web through Google Image Search. The dataset has 10,524 human faces of various resolutions and in different settings, e.g. portrait images, groups of people, etc. All faces are cropped into a base resolution of 36 36 pixels. Footnotes provide URLs: 2MIT Center For Biological and Computation Learning, http://www.ai.mit.edu/projects/cbcl 3http://www.vision.caltech.edu/Image Datasets/ |
| Dataset Splits | No | The paper mentions training and testing data but does not specify a separate validation split or the exact percentages/counts for a train/validation/test split. It states: 'To train a node classifier, our training data contained 1000 frontal face images and 1000 non-face images. For testing, we used 1000 frontal face images and 1000 non-face images in our experiments.' |
| Hardware Specification | No | The paper does not provide any specific details regarding the hardware specifications (e.g., GPU models, CPU types, memory) used for conducting the experiments. |
| Software Dependencies | No | The paper does not specify any software dependencies with version numbers, such as programming languages, libraries, or frameworks used for implementation. |
| Experiment Setup | No | The paper describes general setup details like the number of features and training data size but does not provide specific experimental setup details such as hyperparameter values (e.g., learning rate, batch size, epochs, optimizer settings) or explicit model initialization. |