Author name cluster

Ziye Chen

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers

1 author row

AAAI Conference 2020 Conference Paper

Compressed Self-Attention for Deep Metric Learning

Ziye Chen
Mingming Gong
Yanwu Xu
Chaohui Wang
Kun Zhang
Bo Du

In this paper, we aim to enhance self-attention (SA) mechanism for deep metric learning in visual perception, by capturing richer contextual dependencies in visual data. To this end, we propose a novel module, named compressed selfattention (CSA), which signiﬁcantly reduces the computation and memory cost with a neglectable decrease in accuracy with respect to the original SA mechanism, thanks to the following two characteristics: i) it only needs to compute a small number of base attention maps for a small number of base feature vectors; and ii) the output at each spatial location can be simply obtained by an adaptive weighted average of the outputs calculated from the base attention maps. The high computational efﬁciency of CSA enables the application to high-resolution shallow layers in convolutional neural networks with little additional cost. In addition, CSA makes it practical to further partition the feature maps into groups along the channel dimension and compute attention maps for features in each group separately, thus increasing the diversity of long-range dependencies and accordingly boosting the accuracy. We evaluate the performance of CSA via extensive experiments on two metric learning tasks: person re-identiﬁcation and local descriptor learning. Qualitative and quantitative comparisons with latest methods demonstrate the signiﬁcance of CSA in this topic.

PDF Details

IJCAI Conference 2020 Conference Paper

Compressed Self-Attention for Deep Metric Learning with Low-Rank Approximation

Ziye Chen
Mingming Gong
Lingjuan Ge
Bo Du

In this paper, we apply self-attention (SA) mechanism to boost the performance of deep metric learning. However, due to the pairwise similarity measurement, the cost of storing and manipulating the complete attention maps makes it infeasible for large inputs. To solve this problem, we propose a compressed self-attention with low-rank approximation (CSALR) module, which significantly reduces the computation and memory costs without sacrificing the accuracy. In CSALR, the original attention map is decomposed into a landmark attention map and a combination coefficient map with a small number of landmark feature vectors sampled from the input feature map by average pooling. Thanks to the efficiency of CSALR, we can apply CSALR to high-resolution shallow convolutional layers and implement a multi-head form of CSALR, which further boosts the performance. We evaluate the proposed CSALR on person reidentification which is a typical metric learning task. Extensive experiments shows the effectiveness and efficiency of CSALR in deep metric learning and its superiority over the baselines.

PDF Details DOI