A Novel Pyramid Network with Feature Fusion and Disentanglement for Object Detection

In order to alleviate the scale variation problem in object detection, many feature pyramid networks are developed. In this paper, we rethink the issues existing in current methods and design a more effective module for feature fusion, called multiflow feature fusion module (MF3M). We first construct gate modules and multiple information flows in MF3M to avoid information redundancy and enhance the completeness and accuracy of information transfer between feature maps. Furtherore, in order to reduce the discrepancy of classification and regression in object detection, a modified deformable convolution which is termed task adaptive convolution (TaConv) is proposed in this study. Different offsets and masks are predicted to achieve the disentanglement of features for classification and regression in TaConv. By integrating the above two designs, we build a novel feature pyramid network with feature fusion and disentanglement (FFAD) which can mitigate the scale misalignment and task misalignment simultaneously. Experimental results show that FFAD can boost the performance in most models.

VARIATION PROBLEM CONTAINING SECOND DERIVATIVES OF UNKNOWN FUNCTIONS

The property subdifferential of an integral and terminal functional in a space of the type of absolutely continuous functions is studied. Necessary and sufficient conditions for an extremum for a variational problem containing the second derivatives of unknown functions are obtained. With the help of the subdifferential introduced by the author, a nonconvex generalized variational problem containing the second derivatives of unknown functions is considered, and the necessary condition for an extremum is obtained.

Improved Upper Bound to Product Rate Variation Problem

The sequencing problem which minimizes the deviation between the actual (integral) and the ideal (rational) cumulative production of a variety of models of a common base product is called the product rate variation problem. If the objective is to minimize the maximum deviation, the problem is bottleneck product rate variation problem and the problem with the objective of minimizing all the deviations is the total product rate variation problem. The problem has been widely studied with several pseudo-polynomial time exact algorithms and heurism-tics. The lower bound of a feasible solution to the problem has been investigated to be tight. However, the upper bound of a feasible solution had been established in the literature which could further be improved. In this paper, we propose the improved upper bound for BPRVP and TPRVP.

Pose-Guided Part-Based Adaptive Pyramid Features for Occluded Person Reidentification

Reidentifying an occluded person across nonoverlapping cameras is still a challenging task. In this work, we propose a novel pose-guided part-based adaptive pyramid neural network for occluded person reidentification. Firstly, to alleviate the impact of occlusion, we utilize pose landmarks to generate pose-guided attention maps. The attention maps will help the model focus on the nonoccluded regions. Secondly, we use pyramid pooling to extract multiscale features in order to address the scale variation problem. The generated pyramid features are then multiplied by attention maps to achieve pose-guided adaptive pyramid features. Thirdly, we propose a pose-guided body part partition scheme to deal with the alignment problem. Accordingly, the adaptive pyramid features are divided into partitions and fed into individual fully connected layers. In the end, all the part-based matching scores are fused with a weighted sum rule for person reidentification. The effectiveness of our method is clearly validated by the experimental results on two popular occluded and holistic datasets, i.e., Occluded-DukeMTMC and the Market-1501.