Conditional Self-Supervised Learning for Few-Shot Classification

Authors: Yuexuan An, Hui Xue, Xingyu Zhao, Lu Zhang

IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments demonstrate that our proposed method without any fine-tuning can achieve a significant accuracy improvement on the few-shot classification scenarios compared to the state-of-the-art few-shot learning methods. 4 Experiments In this section, the effectiveness of CSS is verified by various experiments. Three standard few-shot classification datasets (CIFAR-FS [Bertinetto et al., 2019], CUB-200 [Wah et al., 2011], mini-Image Net [Vinyals et al., 2016]) are selected to compare the performance of our approach with previous few-shot learning methods.
Researcher Affiliation Academia School of Computer Science and Engineering, Southeast University, Nanjing, 210096, China 2MOE Key Laboratory of Computer Network and Information Integration (Southeast University), China {yx an, hxue, xyzhao, lu Zhang}@seu.edu.com
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described, such as a specific repository link or an explicit code release statement.
Open Datasets Yes Three standard few-shot classification datasets (CIFAR-FS [Bertinetto et al., 2019], CUB-200 [Wah et al., 2011], mini-Image Net [Vinyals et al., 2016]) are selected to compare the performance of our approach with previous fewshot learning methods.
Dataset Splits No The paper describes meta-training with Dtr and meta-testing with Dte, defining support and query sets within each task. However, it does not provide specific dataset split information (exact percentages, sample counts, or explicit mention of a validation set) needed to reproduce a standard train/validation/test data partitioning.
Hardware Specification Yes All the computations are performed on a GPU server with NVIDIA TITAN RTX, Intel Core i7-8700 CPU 3.20GHz processor and 32 GB memory.
Software Dependencies No The paper mentions implementing methods with 'Py Torch' but does not provide specific version numbers for PyTorch or any other ancillary software components.
Experiment Setup Yes For the fair comparison, we implement all methods by Py Torch. Since [Chen et al., 2019b] shows that the gap among different methods drastically reduces as the backbone gets deeper, all algorithms use the Conv-4-64 [Vinyals et al., 2016] as the backbone and the feature embedding dimension is set to 1600. In CSS, fθ, gξ and hϕ are implement by the Conv-4-64 backbone, and the output dimension of Fω is 2048. The projection MLP head σ is a composite function, which is composed of Fω and a multi-layer neural network with {1600, 2048, 2048} units and batch normalization in each layer. The prediction MLP head δ is parameterized by a three-layer neural network with 512 hidden units and batch normalization in the hidden layer. All hidden layers use ReLU function [Glorot et al., 2011] as the activation function.