Path attribution methods are a popular tool to interpret a visual model's prediction on an input. They integrate model gradients for the input features over a path defined between the input and a reference, thereby satisfying certain desirable theoretical properties. However, their reliability hinges on the choice of the reference. Moreover, they do not exhibit weak dependence on the input, which leads to counter-intuitive feature attribution mapping. We show that path-based attribution can account for the weak dependence property by choosing the reference from the local distribution of the input. We devise a method to identify the local input distribution and propose a technique to stochastically integrate the model gradients over the paths defined by the references sampled from that distribution. Our local path integration (LPI) method is found to consistently outperform existing path attribution techniques when evaluated on deep visual models. Contributing to the ongoing search of reliable evaluation metrics for the interpretation methods, we also introduce DiffID metric that uses the relative difference between insertion and deletion games to alleviate the distribution shift problem faced by existing metrics. Our code is available at https://github.com/ypeiyu/LPI.

Abstract Despite their great advancement, current pedestrian detection methods focus on single static images, which fail to employ richer information available from the video sequences. Compared with still images, videos can offer temporal information of objects in the time dimension, thus providing the potential to obtain more robust detection performance. Here, a novel pedestrian detection method based on visible part detection and temporal calibration is proposed. Specifically, a part‐aware module to predict the visible body part of each pedestrian instance, which enables us to obtain precise motion information of partially occluded pedestrians in a video sequence, is first developed. Then, the temporal coherence for each pedestrian instance based on the predicted motion information is constructed. After that, an adaptive temporal calibration method is introduced to effectively calibrate the final detection result. This method on two video pedestrian detection benchmarks, that is, Caltech‐New and MOT17Det, is evaluated. Experimental results show that this method performs favourably against existing pedestrian detection approaches.

Given a classification problem with a large number of classes, humans often compare features at different granularities from coarse to fine to gradually recognize an object. However, current deep models are generally trained to directly make the final prediction, focusing on improving the ability of the network to extract features without considering the interpretability of the model. In this paper, we propose a multi-grained interpretable network to imitate the reasoning process of humans. The proposed network is equipped with techniques to assign images with multi-grained labels, so as to train a tree-structured classifier that learns features at different levels of granularity. The proposed method can hierarchically classify objects in images at different granularities, while providing a decision pathway with multi-grained explanations for practitioners. Experimental results demonstrate that our method achieves competitive prediction accuracy on CUB-200-2011 and Stanford Cars datasets, and simultaneously produces high-quality explanations of its decisions. Moreover, our method shows higher robustness of the learned features to adversarial examples generated by the FGSM and PGD attacks.

Pedestrian detection is a crucial task in intelligent transportation systems, which can be applied in autonomous vehicles and traffic scene video surveillance systems. The past few years have witnessed much progress on the research of pedestrian detection methods, especially through the successful use of the deep learning based techniques. However, occlusion and large scale variation remain the challenging issues for pedestrian detection. In this work, we propose a Part-Aware Multi-Scale Fully Convolutional Network (PAMS-FCN) to tackle these difficulties. Specifically, we present a part-aware Region-of-Interest (RoI) pooling module to mine body parts with different responses, and select the part with the strongest response via voting. As such, a partially visible pedestrian instance can receive a high detection confidence score, making it less likely to become a missing detection. This module operates in parallel with an instance RoI pooling module to combine local parts and global context information. To handle vast scale variation, we construct a fully convolutional network in which multi-scale feature maps are generated efficiently, and small-scale and large-scale pedestrians are detected separately. By integrating these structures, the proposed detector achieves the state-of-the-art performance on the Caltech, KITTI, INRIA and ETH pedestrian detection datasets.

Call detail records (CDRs) containing mass position information allow us to reveal characteristics about the city dynamics and human behaviors, which are crucial for policy decisions such as urban planning and transportation engineering. Being able to identify the trajectory and significant places is of prime importance. In this paper, we aim to extract trajectory from anonymized call detail records and adopt two-step clustering to obtain significant places from multi-day data. We propose a new method for mining trajectory by identifying users' stop and move state based on location gradient, which can be applied to users with low communication frequency. We analyze the feature of real CDR data and propose novel methods for noise handling. Home Time and Work Time are extracted from statistics of users' mobility pattern to recognize their significant places including home and work of a single day. Utilizing the characteristic of cyclical mobility, we conduct a cluster analysis to identify users' significant places which are not limited to one home or one work based on multi-day data. We run four experiments to show the robustness and stability of our method. During both typical stop and move period, our method performs better than state-of-art method.