Attribute Aware Pooling for Pedestrian Attribute Recognition
This work addresses the problem of multi-attribute classification in pedestrian recognition for surveillance and security applications, representing an incremental improvement over existing methods.
The paper tackles pedestrian attribute recognition by proposing an attribute aware pooling algorithm to address challenges like attribute entanglement and correlations in multi-attribute classification, achieving accurate recognition of indistinct or tangled attributes as demonstrated on benchmark datasets.
This paper expands the strength of deep convolutional neural networks (CNNs) to the pedestrian attribute recognition problem by devising a novel attribute aware pooling algorithm. Existing vanilla CNNs cannot be straightforwardly applied to handle multi-attribute data because of the larger label space as well as the attribute entanglement and correlations. We tackle these challenges that hampers the development of CNNs for multi-attribute classification by fully exploiting the correlation between different attributes. The multi-branch architecture is adopted for fucusing on attributes at different regions. Besides the prediction based on each branch itself, context information of each branch are employed for decision as well. The attribute aware pooling is developed to integrate both kinds of information. Therefore, attributes which are indistinct or tangled with others can be accurately recognized by exploiting the context information. Experiments on benchmark datasets demonstrate that the proposed pooling method appropriately explores and exploits the correlations between attributes for the pedestrian attribute recognition.