Backbone
Alexnet
VGG{16}
ResNet{18,34,50,101,152}
ViT
Swim Transformer
ConvNext
Loss (Method)
Supervised
Method |
Config Template |
Loss Name |
64bit ImageNet AlexNet (mAP@1K) |
---|---|---|---|
adsh |
0.645 |
||
bihalf-supervised |
0.684 |
||
Cross Entropy |
ce |
0.434 |
|
csq |
0.686 |
||
dfh |
0.689 |
||
dpn |
0.692 |
||
dpsh |
0.599 |
||
dtsh |
0.608 |
||
greedyhash |
0.667 |
||
hashnet |
0.588 |
||
jmlh |
0.664 |
||
orthocos |
0.701 |
||
orthoarc |
0.698 |
||
SDH-C |
sdhc |
0.639 |
Unsupervised
Method |
Config Template |
Loss Name |
64bit ImageNet AlexNet (mAP@1K) |
---|---|---|---|
bihalf |
0.403 |
||
cibhash |
0.322 |
||
greedyhash-unsupervised |
0.407 |
||
ssdh |
0.146 |
||
tbh |
0.324 |
Shallow (Non-Deep learning methods)
Method |
Config Template |
Loss Name |
64bit ImageNet AlexNet (mAP@1K) |
---|---|---|---|
imh |
0.467 |
||
itq |
0.402 |
||
lsh |
0.206 |
||
PCAHash |
pca |
0.405 |
|
sh |
0.350 |
Warning
Shallow methods only works with descriptor datasets. We will upload the descriptor datasets and
Datasets
Dataset |
Name in framework |
---|---|
ImageNet100 |
imagenet100 |
NUS-WIDE |
nuswide |
MS-COCO |
coco |
MIRFLICKR/Flickr25k |
mirflickr |
Stanford Online Product |
sop |
Cars dataset |
cars |
CIFAR10 |
cifar10 |