Attentive Group Equivariant Convolutional Networks
Authors: David Romero, Erik Bekkers, Jakub Tomczak, Mark Hoogendoorn
ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We show empirically that our attentive group equivariant convolutional networks consistently outperform conventional group convolutional networks on benchmark image datasets. Simultaneously, we provide interpretability to the learned concepts through the visualization of equivariant attention maps. |
| Researcher Affiliation | Academia | 1Vrije Universiteit Amsterdam, 2University of Amsterdam, The Netherlands. |
| Pseudocode | No | The paper does not contain any pseudocode or algorithm blocks. |
| Open Source Code | Yes | Our code is publicly available at: https://github.com/dwromero/att_gconvs |
| Open Datasets | Yes | The rotated MNIST dataset (Larochelle et al., 2007) contains 62k gray-scale 28x28 handwritten digits uniformly rotated for [0, 2π). The dataset is split into training, validation and test sets of 10k, 2k and 50k images respectively. The CIFAR-10 dataset (Krizhevsky et al., 2009) consists of 60k real-world 32x32 RGB images uniformly drawn from 10 classes. The Patch Camelyon dataset (Veeling et al., 2018) consists of 327k 96x96 RGB image patches of tumorous/non-tumorous breast tissues extracted from the Camelyon16 dataset (Bejnordi et al., 2017). |
| Dataset Splits | Yes | The rotated MNIST dataset (Larochelle et al., 2007) ... The dataset is split into training, validation and test sets of 10k, 2k and 50k images respectively. |
| Hardware Specification | No | The paper mentions '72GB of CUDA memory' and '5GBs for the p4-All-CNN' when discussing memory requirements for CIFAR-10 experiments, which implies GPU usage. However, it does not specify any particular GPU model, CPU, or other detailed hardware specifications. |
| Software Dependencies | No | The paper does not explicitly list any software dependencies with specific version numbers (e.g., Python, PyTorch, TensorFlow versions). |
| Experiment Setup | Yes | For our attention models, we utilize a filter size of 7 and a reduction ratio r of 2 on the attention branch. For all our attention models, we utilize a filter size of 7 and a reduction ratio r of 16 on the attention branch. |