Core-Structures-Guided Multi-Modal Classification Neural Architecture Search
Authors: Pinhan Fu, Xinyan Liang, Tingjin Luo, Qian Guo, Yayu Zhang, Yuhua Qian
IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Finally, extensive experimental results demonstrate the effectiveness of our CSG-NAS, attaining the superiority of classification performance, training efficiency and model complexity, compared to state-of-the-art competitors on several benchmark multi-modal tasks. |
| Researcher Affiliation | Academia | Pinhan Fu1 , Xinyan Liang1 , Tingjin Luo2, Qian Guo3, Yayu Zhang1, Yuhua Qian1 1 Institute of Big Data Science and Industry, Shanxi University, Taiyuan 030006, China 2 College of Science, National University of Defense Technology, Changsha, China 410073, China 3 School of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan 030024, China |
| Pseudocode | No | No pseudocode or algorithm blocks are explicitly labeled or presented in a structured format. |
| Open Source Code | Yes | The source code is available at https://github. com/fupinhan123/CSG-NAS. |
| Open Datasets | Yes | We validated five popular multi-modal datasets: (1) Chem Book-10k (CB) [Liang et al., 2021] dataset... (2) NUS-WIDE-128 (NUS) [Tang et al., 2017] dataset... (3) MMIMDB [Arevalo et al., 2017] dataset... (4) NTU RGB-D [Shahroudy et al., 2016] dataset... (5) Ego Gesture [Zhang et al., 2018] dataset... |
| Dataset Splits | Yes | To mitigate the randomness introduced by data splitting and network initialization, each dataset is divided into training and testing sets via 5-fold cross-validation. ...The dataset is divided into a training set of 15,552 films, a validation set of 2,608 films, and a test set of 7,799 films. ...The training, validation and test sets include 23,760, 2,519 and 16,558 samples, respectively. ...The training set of this dataset includes 14,416 samples, the validation set includes 4,768 samples, and the test set includes 4,977 samples. |
| Hardware Specification | Yes | The computational environment consists of Ubuntu 16.04.4, 512GB DDR4 RDIMM, 2X 40-Core Intel Xeon CPU E52698 v4 @ 2.20GHz, and NVIDIA Tesla P100. |
| Software Dependencies | Yes | Our method is implemented using Tensor Flow 2.0.3. |
| Experiment Setup | Yes | The parameters are set as follows: the population size N is 20, the number of population iterations T is 8, the dimension of the fusion vector FD is 128, and modality features are repeatable. ...Moreover, the population size is 28, iteration times is 8, fusion modality dimension is 64, and modalities are not reused. ...The experimental settings for CSG-NAS included a population size of 28, 10 iterations, no modal reuse, and a fusion dimension of 32. ...ENAS1: Crossover rate is r = r1, mutation rate is r = r2 ... ENAS2: Crossover rate is r = r1/9, mutation rate is r = 4r2. |