Learning Task-aware Local Representations for Few-shot Learning
Authors: Chuanqi Dong, Wenbin Li, Jing Huo, Zheng Gu, Yang Gao
IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conduct comprehensive experiments on the challenging mini Imagenet and three fine-grained datasets to verify that the proposed ATL-Net achieves superior performance over the state-of-the-art methods. |
| Researcher Affiliation | Academia | Chuanqi Dong , Wenbin Li , Jing Huo , Zheng Gu and Yang Gao State Key Laboratory for Novel Software Technology, Nanjing University, China {dongchuanqi, guzheng}@smail.nju.edu.cn, {liwenbin, huojing, gaoy}@nju.edu.cn |
| Pseudocode | Yes | Algorithm 1 Training of ATL-Net Input: Episodic task T = {AS, AQ} 1: while no converge do 2: LS FΘ(AS) 3: LQ FΘ(AQ) 4: for Lq in LQ do 5: Get relation matrix MR by Eq. (1) 6: Calculate adaptive threshold V c for Lq by Eq. (6) 7: Construct adaptive episodic attention MA by Eq. (2), Eq. (3) and Eq. (7) 8: Calculate probability Pq for Lq by Eq. (5) 9: end for 10: L P Y log(P) 11: Mini-batch Adam to minimize L, update Θ, Ψ and Γ 12: end while |
| Open Source Code | Yes | 1The source code can be available from https://github.com/ Legen Dong/ATL-Net |
| Open Datasets | Yes | mini Image Net [Vinyals et al., 2016] is a subset of Image Net [Deng et al., 2009], which consists of 100 classes and 600 images per class. ... We also evaluate our method on three fine-grained image classification datasets. Stanford Dogs [Khosla et al., 2011] contains 120 categories with a total number of 20, 580 images. Stanford Cars [Krause et al., 2013] contains 196 classes of cars and 16, 185 images. CUB-200 [Welinder et al., 2010] contains 200 bird species with a total number of 6, 033 images. |
| Dataset Splits | Yes | Following the commonly used strategy, we divide the dataset into training (auxiliary)/validation/test set with a percentage of 64/16/20 respectively. For fair comparisons, we use the data splits of [Li et al., 2019b; Li et al., 2019c; Huang et al., 2019], as Table 1 shows. |
| Hardware Specification | No | The paper states "We implement our experiments using Py Torch [Paszke et al., 2019]" but does not provide specific hardware details like GPU/CPU models or processor types. |
| Software Dependencies | No | We implement our experiments using Py Torch [Paszke et al., 2019]. This mentions the software but not a specific version number. |
| Experiment Setup | Yes | All the images are resized to 84 84. During the training stage, we randomly construct 250, 000 episodes from the training (auxiliary) set for the mini Imagenet dataset and the Stanford Car dataset, and 150, 000 for the other two datasets to avoid overfitting. In each episode, we collect 15 query images per class. ... We use Adam [Kingma and Ba, 2015] optimizer with a cross-entropy loss to train the network. The initial learning rate is set to 0.001. |