IndraLab

Statements

CALM1 binds TS. 7 / 7
| 7
sparser
"Gao et al. xref proposed the Token Semantic Coupled Attention Map (TS-CAM) that employs the self-attention mechanism of visual transformers to mitigate the long-range dependency problem in CNNs and avoid partial activation by generating long-range dependency attention maps."
37903879
sparser
"Experiments show that TS-CAM outperforms its CNN-CAM counterpart by 11.6% and 28.9% on ILSVRC and CUB-200-2011 datasets, respectively, improving the state-of-the-art with large margins."
36417732
sparser
"TS-CAM also demonstrates superiority for multicategory object localization on the Pascal VOC dataset."
36417732
sparser
"We propose the token semantic coupled attention map (TS-CAM) method, which first decomposes class-aware semantics and then couples the semantics with attention maps for semantic-aware activation."
36417732
sparser
"To capture object semantics at long distances and avoid partial activation, TS-CAM performs spatial embedding by partitioning an image to a set of patch tokens."
36417732
sparser
"To incorporate object category information to patch tokens, TS-CAM reallocates category-related semantics to each patch token."
36417732
sparser
"By introducing semantic tokens to produce semantic-aware attention maps, we further explore the capability of TS-CAM for multicategory object localization."
36417732