返回
Visual Attention Consistency for Human Attribute Recognition
DOI:10.1007/s11263-022-01591-y.png)
摘要
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.
Keyword:
Attention maps
Human attribute recognition
Attention consistency
Equivariance
期刊
IF:
9.3
论文数:
3.9K
被引数:
2.8W
机构
引用论文
Caw’s Walking State Recognition Based on Accelerometers and Gyroscopes Installed on Ear-Tags and Collar-Tags基于安装在耳标和项圈上的加速度计和陀螺仪的Caw步行状态识别
More tricks with tetramers: a practical guide to staining T cells with peptide–MHC multimers
Immunology
IF0
Significance of nailfold videocapillaroscopy in patients with idiopathic inflammatory myopathies
Rheumatology
IF0

