search

lihong2303 / AGM

[ICCV2023] The repo for "Boosting Multi-modal Model Performance with Adaptive Gradient Modulation".
MIT License
25 stars 2 forks source link

Experiment Parameters #10

Open heshandevaka opened 9 months ago

heshandevaka commented 9 months ago

Hi,

Congratulations on the great work and thank you for open sourcing the codebase. I am trying to use this codebase to experiment with different multi-modal methods. However, I found the methods I am testing do not get comparable results to those reported in the paper. I am wandering whether this is due to my experiment parameters. Currently, I am using the default ones in the codebase if not otherwise specified in the paper. Could you please clarify the

  1. Number of epochs,
  2. alpha value for AGM method, and
  3. Modulation window (start and end epoch for modulation)

used for AVMNIST, URFUNNY, and CREMA-D datasets? Many thanks in advance!

lihong2303 commented 9 months ago

For AV-MNIST, UR-Funny, CREMA-D, Number of epoch: 1000, 800, 1500, alpha: 2.5, 4.0, 1.5, Modulation window: 0,1000; 0,800; 0, 1500;

heshandevaka commented 9 months ago

Thank you for the prompt response!

heshandevaka commented 4 months ago

Hi, I need a clarification on the alpha parameters given here. It seems like the alpha parameters are different for the early fusion and late fusion cases. could you please provide parameters for the early fusion phase (assuming the provided ones are for the late fusion case)? Many thanks in advance!