Italy

Person re-identification (Re-ID) has attracted a lot of research attention in recent years. However, supervised methods demand enormous amount of manually annotated data. In this paper, we propose a Self-Paced bottom-up Clustering Network with Side Information (SPCNet-SI) for unsupervised person Re- ID, where the side information comes from the serial number of the camera associated with each image. Specifically, our proposed SPCNet-SI exploits the camera side information to guide the feature learning and uses soft label in bottom-up clustering process, in which the camera association information is used in the repelled loss and the soft label based cluster information is used to select the candidate cluster pairs to merge. Moreover, a self-paced dynamic mechanism is developed to regularize the merging process such that the clustering is implemented in an easy-to-hard way with a slow-to-fast merging process. Experiments on two benchmark datasets Market-1501 and DukeMTMC-ReID demonstrate promising performance.

ICPR 2020

Self-paced Bottom-up Clustering Network with Side Information for Person Re-Identification

side-information

person re-identification

unsupervised learning

ICPR 2020 is the premier international conference on Pattern Recognition, gathering leading researchers from around the world to present their latest achievements in Pattern Analysis and Recognition, applied Artificial Intelligence and Machine Learning. The topic of the year is " Putting Artificial intelligence to work on Patterns". 
For the first time, ICPR has employed a two-round review process similar to journal submissions, with new papers allowed to be submitted in either the first or second round and papers submitted in the first round and not accepted allowed to be revised and re-submitted for second round review. 

In this edition of the **ICPR 2020** Conference, there are 1407 Oral/Poster presentations organized in five Tracks: 
- Artificial Intelligence, Machine Learning for Pattern Analysis; 
- Biometrics, Human Analysis and Behavior Understanding; Computer Vision, Robotics and Intelligent Systems; 
- Document and Media Analysis; and 
- Image and Signal Processing. 

The **ICPR 2020** Main Conference program also includes 7 Keynotes from prominent world-renowned scientists, 8 Tutorials, 28 Demos, 8 Challenges, 2 Panels, as well as an Industry/Sponsor Exhibition. In addition, 41 Workshops on a range of important current and emerging research topics complete the ICPR 2020 program. 


poster

We propose a new optimization framework for aleatoric uncertainty estimation in regression problems. Existing methods can quantify the error in the target estimation, but they tend to underestimate it. To obtain the predictive uncertainty inherent in an observation, we propose a new separable formulation for the estimation of a signal and of its uncertainty, avoiding the effect of overfitting. By decoupling target estimation and uncertainty estimation, we also control the balance between signal estimation and uncertainty estimation. We conduct three types of experiments: regression with simulation data, age estimation, and depth estimation. We demonstrate that the proposed method outperforms a state-of-the-art technique for signal and uncertainty estimation.

The Aleatoric Uncertainty Estimation Using a Separate Formulation with Virtual Residuals

Model efficiency for object detection has become more and more important recently, especially when intelligent mobile devices get more and more popular. Current lightweight object detection model is either migrated from lightweight classification models, or pruned directly from complex object detection models. These pipelines can not match the performance requirements of edge devices. In this work, we propose a neural architecture search (NAS) method to build a detection model automatically that can perform well on edge devices. Specifically, the proposed method supports the search of not only multi-scale feature network, but also backbone network. This enables us to search out a global optimal model. To this end, we've made a special design that the backbone and feature network can share the same search space. This method greatly reduces the search time while ensuring the search accuracy. It can find a good architecture in 14GPU days. Additionally, we add latency information into the main objective during performance estimation. Therefore, we can control between the speed and accuracy to better adapt to the edge environment. Experiments on the PASCAL VOC benchmark indicate that the searched architecture (named NAS-EOD) can get good accuracy even if training from scratch. When using a pre-training scheme, our model is superior to state-of-the-art small object detection models.

NAS-EOD: an end-to-end Neural Architecture Search method for Efficient Object Detection


Deep learning has been widely used in natural image processing, but its application for medical data still needs further investigation. So we focus on nuclear detection and segmentation of pathological images and build an end-to-end network. In order to meet the needs of both nuclear detection and segmentation, our contribution consists of two parts. We will show the design details and effects in this presentation.

Introduction of A Triplet-path Dilated Network for Detection and Segmentation of General Pathological Images


This paper studies the problem of Person Re-Identification (ReID)
for large-scale applications. Recent research efforts have been devoted
to building complicated part models, which introduce considerably
high computational cost and memory consumption, inhibiting its practicability
in large-scale applications. This paper aims to develop a novel learning
strategy to find efficient feature embeddings while maintaining the
balance of accuracy and model complexity. More specifically, we find
by enhancing the classical triplet loss together with cross-entropy
loss, our method can explore the hard examples and build a discriminant
feature embedding yet compact enough for large-scale applications.
Our method is carried out progressively using Bayesian optimization,
and we call it the Progressive Learning Algorithm (PLA). Extensive
experiments on three large-scale datasets show that our PLA is comparable
or better than the state-of-the-arts. Especially, on the challenging
Market-1501 dataset, we achieve Rank-1=94.7%/mAP=89.4% while saving
at least 30\% parameters than strong part models.

Revisiting ImprovedGAN with Metric Learning for Semi-Supervised Learning

VGG-Embedded Adaptive Layer-Normalized Crowd Counting Net with Scale-Shuffling Modules

Despite the success of pedestrian detection, there is still a significant gap in the performance of the detection of pedestrians at different scales. Detecting small-scale pedestrians is extremely challenging due to the low resolution of their convolution features which is essential for downstream classifiers. To address this issue, we observed pedestrian datasets and found that pedestrians often gather together in crowded public places. Then we propose MagnifierNet, a simple but effective small-scale pedestrian detector towards multiple dense regions. MagnifierNet uses our proposed sweep-line based grouping algorithm to find dense regions based on the number of pedestrians in the grouped region. And we adopt a new definition of small-scale pedestrians through grid search and KL-divergence. Besides, our grouping method can also be used as a new strategy for pedestrian data augmentation. The ablation study demonstrates that MagnifierNet improves the representation of small-scale pedestrians. We validate the effectiveness of MagnifierNet on CityPersons and KITTI datasets. Experimental results show that MagnifierNet achieves the best small-scale pedestrian detection performance on CityPersons benchmark without any external data, and also achieves competitive performance for detecting small-scale pedestrians on KITTI dataset without bells and whistles.

MagnifierNet: Learning Efficient Small-scale Pedestrian Detector towards Multiple Dense Regions


Most deep learning-based salient object detection (SOD) methods tried to manipulate the convolution block to effectively capture the context of object. In this paper, we propose a novel method, called progressive and multi-task learning scheme, to extract the context of object by only manipulating the learning scheme without changing the network architecture. The progressive learning scheme is a method to grow the decoder progressively in the train phase. In other words, starting from easier low-resolution layers, it gradually adds high-resolution layers. Although the progressive learning successfully captures the context of object, its output boundary tends to be rough. To solve this problem, we also propose a multi-task learning (MTL) scheme that processes the object saliency map and contour in a
single network jointly. The proposed MTL scheme trains the network in an edge-preserved direction through an auxiliary branch that learns contours. The proposed a learning scheme can be combined with other convolution block manipulation methods. Extensive experiments on five datasets show that the proposed method performs best compared with state-of-the-art methods in most cases.

Coarse to Fine: Progressive and Multi-Task Learning for Salient Object Detection


We present our work on video frame interpolation that directly generates the middle frame without an intermediate step such as motion or kernel estimation. Although simple, our method is able to compete against state-of-the-art methods on several datasets.

Residual Learning of Video Frame Interpolation Using Convolutional LSTM

In this paper, we propose a camera calibration method for surveillance cameras that uses the image projection of parallel 3D line segments of the same length. We assume that vertical line segments are perpendicular to the ground plane and their bottom end points are on the ground plane. Under this assumption, the camera parameters can be directly determined from at least two line segments without estimating vanishing points. By extending the minimal solution, we devise a closed-form solution to the least-squares case with more than two line segments. Lens distortion is jointly optimized in bundle adjustment. Evaluation of synthetic data showed that the optimal depression angle of a camera is around 50 degrees. In real data evaluation, we used the joints of pedestrians as vertical line segments. The experimental results on public datasets showed that the proposed method used with a human pose detector can accurately calibrate wide-angle cameras that have radial distortion.

Camera Calibration Using Parallel Line Segments

This paper addresses the challenging problem of generating videos with human action semantics. Unlike previous work which predict future frames in a single forward pass, this paper introduces the cycle constraints in both forward and backward passes in the generation of human actions. This is achieved by enforcing the appearance and motion consistency across a sequence of frames generated in the future. The approach consists of two stages. In the first stage, the pose of a human body is generated. In the second stage, an image generator is used to generate future frames by using (a) generated human poses in the future from the first stage, (b) the single observed human pose, and (c) the single corresponding future frame. The experiments are performed on three datasets: Weizmann dataset
involving simple human actions, Penn Action dataset and UCF-101 dataset containing complicated human actions, especially in sports. The results from these experiments demonstrate the effectiveness of the proposed approach.

Downloads

Next from ICPR 2020

The Aleatoric Uncertainty Estimation Using a Separate Formulation with Virtual Residuals

Similar lecture

Online Domain Adaptation for Person Re-Identification with a Human in the Loop