.png){kind=icon}
Return
Visual Attention Consistency for Human Attribute Recognition
.png){kind=icon}
PRE
AI
DOI：10.1007/s11263-022-01591-y.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The recognition of a human attribute is usually determined by certain regions of the input image, e.g., certain part of the human body, and such attribute-region relevance plays an important role in human attribute recognition. In deep networks, this attribute-region relevance can be derived as an interpretive attention map, where highlighted areas indicate the most relevant regions that contribute to the final recognition. Based on the assumption that more plausible attention maps indicate better networks, in this paper, we propose a new approach for human attribute recognition by exploring and enforcing two kinds of attention consistency in network learning. One kind of consistency enforces the equivariance of the attention map when the input image undergoes certain spatial transforms, such as scaling, rotation and flipping. The other kind of the consistency is enforced between the attention maps derived from two different networks when both of them are trained for recognizing the same attribute from the same image. We formulate these two kinds of consistency as new loss functions and combine them with the traditional classification loss for network training. Experiments on three datasets of human attribute recognition verify the effectiveness of the proposed method by achieving new state-of-the-art performance.
Keywords:
Attention maps
Human attribute recognition
Attention consistency
Equivariance
Journal
IF:
9.3
Papers:
3.9K
Citations:
2.8W
Organization
Cited Papers
ShareSaveShareSaveShareSaveFree radical induced one-electron oxidation of the phenothiazines chlorpromazine and promethazine
PREAI
ShareSaveShareSaveMore tricks with tetramers: a practical guide to staining T cells with peptide–MHC multimers.png)
Immunology
OAAI
ImmunologyIF0
OAAIShareSaveProperties of the double well potential and relaxation processes in a model glassPhysChemComm
PhysChemCommIF0
PREAI
ShareSaveShareSaveSignificance of nailfold videocapillaroscopy in patients with idiopathic inflammatory myopathiesRheumatologyOAAI
RheumatologyIF0
OAAIShareSave
View more