Investigating the Benefits of Projection Head for Representation Learning

Authors: Yihao Xue, Eric Gan, Jiayi Ni, Siddharth Joshi, Baharan Mirzasoleiman

ICLR 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We empirically validate our results through various experiments on CIFAR-10/100, Urban Cars and shifted versions of Image Net. We also introduce a potential alternative to projection head, which offers a more interpretable and controllable design.
Researcher Affiliation Academia Department of Computer Science, University of California, Los Angeles
Pseudocode No The paper contains theoretical analyses and experimental results but does not include any pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statement or link indicating the availability of its source code.
Open Datasets Yes We empirically validate our results through various experiments on CIFAR-10/100, Urban Cars and shifted versions of Image Net.
Dataset Splits No The paper discusses training and evaluation but does not specify exact train/validation/test dataset splits with percentages or counts for reproducibility.
Hardware Specification No The paper does not provide specific details about the hardware used for its experiments, such as GPU or CPU models.
Software Dependencies No The paper mentions software like 'Sim CLR loss' and 'Adam optimizer' but does not specify version numbers for these or other software dependencies.
Experiment Setup Yes By default, we use a temperature of 0.5 and minimize the Sim CLR loss with the Adam optimizer. Our training batch size is 512, with a learning rate of 0.001 and weight decay set to 1 10 6. We train for 400 epochs.