DUET: 2D Structured and Approximately Equivariant Representations
Authors: Xavier Suau, Federico Danieli, T. Anderson Keller, Arno Blaas, Chen Huang, Jason Ramapuram, Dan Busbridge, Luca Zappella
ICML 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We provide extensive experiments on several datasets, comparing with Sim CLR and ESSL. |
| Researcher Affiliation | Collaboration | 1Apple 2University of Amsterdam. |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Code available at https://github.com/apple/ml-duet |
| Open Datasets | Yes | We sweep 100 values of g1, g2 in [0, 1] for 1000 randomly selected CIFAR-10 (Krizhevsky, 2009) test images and we show the average pairwise L2 distance in Figure 2. Table 2 benchmarks the more complex tasks CIFAR-100 (Krizhevsky, 2009) and Tiny Image Net (Li et al., 2017). DUET s structure to rotations yields a gain of +21% with respect to Sim CLR when transferring to Caltech101 (Li et al., 2022), and between +5.97% and +16.97% when transferring to other datasets like CIFAR-10, CIFAR-100, DTD (Cimpoi et al., 2014) or Oxford Pets (Parkhi et al., 2012). Structure to color transformations also proves beneficial, with a +6.36% gain on Flowers (Tung, 2020) (grayscale), Food101 (Bossard et al., 2014) (hue). |
| Dataset Splits | Yes | We train a logistic regression classifier on the representations of the training split of each dataset. No augmentations are applied during the classifier training. At test time, we evaluate the classifier on the test set of each dataset. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments. |
| Software Dependencies | No | The paper mentions the use of ResNet-32 architecture and Adam optimizer, but it does not specify versions for general software dependencies like Python, PyTorch, TensorFlow, or CUDA libraries. |
| Experiment Setup | Yes | Additional training parameters are shown in Table 5. Table 5: Batch size 2048, Epochs 800, Learning rate 0.0001, Learning rate warm-up 10 epochs, Learning rate schedule Cosine, Optimizer Adam(β = [0.9, 0.95]), Weight decay 0.0001. |