About CRF

[chuangchuangtan]

Hi , Thanks for sharing the code. When calculating Peak-IoU, did you apply CRF or ConvCRF on localization map as SEM?

[Panxjia]

Thanks for your attention, we did not use CRF and its variants.

[chuangchuangtan]

Can you release the details of training strategy for CAM, Has, ACol, CutMix, SPG and ADL? When implementing those methods, I get different results comparing with Table 3 of SPA paper. Thank you.

[chuangchuangtan]

Did you use 23151 or 50000 images to calculate results of Peak-T, Peak-IoU and GT-Known Loc in Table 3?

[Panxjia]

around 23k images

[Panxjia]

please refer to link

[chuangchuangtan]

I implement CutMix twice according to evaluation script, train script and evaluation hyperparameter, and con't get results of Peak-T, Peak-IoU in Table 3. I achieve Peak-IoU 52.96 and 52.80, instead of Peak-IoU 54.54.

CUDA_VISIBLE_DEVICES=0 python main.py --dataset_name ILSVRC --architecture inception_v3 --wsol_method cutmix --experiment_name ILSVRC_inception_v3_cutmix_20210507 --pretrained TRUE --num_val_sample_per_class 5 --large_feature_map TRUE --batch_size 32 --epochs 10 --lr 0.00024974608 --lr_decay_frequency 3 --weight_decay 5.00E-04 --cutmix_beta 0.08 --cutmix_prob 0.49 --override_cache FALSE --workers 8 --box_v2_metric FALSE --iou_threshold_list 50 --eval_checkpoint_type last --cam_curve_interval 0.001

[Panxjia]

@chuangchuangtan I checked our code and models. The main differences compared with your configuration are: we used 8V100 GPUs and set bacth_size=1024, lr=0.005, lr_decay=10,15, total_epoch=20, cutmix_beta=1.0, cutmix_prob=0.5

[chuangchuangtan]

It is confusing in section 4.1 that "For fair comparisons, we adopt the same training strategy with SEM."

[Panxjia]

Sorry for the confusing description. It means that we add SEM and SPA on the same model re-implemented by us, respectively. Since both methods work in the testing phase, it is a fair comparison on the basis of the same model in our opinion.

[chuangchuangtan]

Thank you for your attention.