Italy

Fine-grained visual categorization aims to learn a robust image representation modeling subtle differences from similar categories. Existing methods in this ﬁeld tackle the problem by designing complex frameworks, which produce high-level features by performing ﬁrst-order or second-order pooling. Despite the impressive performance achieved by these strategies, the single-ordernetworksonlycarrylinearornon-linearinformation of the last convolutional layer, neglecting the fact that features from different orders are mutually complementary. In this paper, we propose a multi-order feature statistical method (MOFS), whichlearnsﬁne-grainedfeaturescharacterizingmultipleorders. Speciﬁcally, the MOFS consists of two sub-modules: (i) a ﬁrstorder module modeling both mid-level and high-level features. (ii) a covariance feature statistical module capturing high-order features. By deploying these two sub-modules on the top of existing backbone networks, MOFS simultaneously captures multi-level of discriminative patters including local, global and co-related patters. We evaluate the proposed method on three challenging benchmarks, namely CUB-200-2011, Stanford Cars, and FGVC-Aircraft. Compared with state-of-the-art methods, experiment results exhibit superior performance in recognizing ﬁne-grained objects.

ICPR 2020

Multi-Order Feature Statistical Model for Fine-Grained Visual Categorization

feature learning

covariance pooling

fine-grained learning

image recognition

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


The existing research in action recognition is mostly focused on high-quality videos where the action is distinctly visible. In real-world surveillance environments, the actions in videos are captured at a wide range of resolutions. Most activities occur at a distance with a small resolution and recognizing such activities is a challenging problem. In this work, we focus on recognizing tiny actions in videos. We introduce a benchmark dataset, TinyVIRAT, which contains natural low-resolution activities. The actions in TinyVIRAT videos have multiple labels and they are extracted from surveillance videos which makes them realistic and more challenging. We propose a novel method for recognizing tiny actions in videos which utilizes a progressive generative approach to improve the quality of low-resolution actions. The proposed method also consists of a weakly trained attention mechanism which helps in focusing on the activity regions in the video. We perform extensive experiments to benchmark the proposed TinyVIRAT dataset and observe that the proposed method significantly improves the action recognition performance over baselines. We also evaluate the proposed approach on synthetically resized action recognition datasets and achieve state-of-the-art results when compared with existing methods. The dataset and code will be publicly available.

TinyVIRAT: Low-resolution Video Action Recognition

Following the tracking-by-detection paradigm, multiple object tracking deals with challenging scenarios, occlusions or even missing detections; the priority is often given to quality measures instead of speed, and a good trade-off between the two
is hard to achieve. Based on recent work, we propose a fast, light-weight tracker able to predict targets position and reidentify them at once, when it is usually done with two sequential steps. To do so, we combine a bounding box regressor with a target-oriented appearance learner in a newly designed and unified architecture.
This way, our tracker can infer the targets’ image pose but also provide us with a confidence level about target identity. Most of the time, it is also common to filter out the detector outputs with a preprocessing step, throwing away precious
information about what has been seen in the image. We propose a tracks management strategy able to balance efficiently between detection and tracking outputs and their associated likelihoods. Simply put, we spotlight a full siamese based single object tracker able to predict both position and appearance features
at once with a light-weight and all-in-one architecture, within a balanced overall multi-target management strategy. We demonstrate the efficiency and speed of our system w.r.t the literature on the well-known MOT17 challenge benchmark, and bring to the fore qualitative evaluations as well as state-of-the-art quantitative
results.

Compact and discriminative multi-object tracking with siamese CNNs

Although recent works have brought some insights into the performance improvement of techniques used in state-of-the-art deep-learning models, more work is needed to understand their generalization properties. We shed light on this matter by linking the loss function to the output’s sensitivity to its input. We find a rather strong empirical relation between the output sensitivity and the variance in the bias-variance decomposition of the loss function, which hints on using sensitivity as a metric for comparing the generalization performance of networks, without requiring labeled data. We find that sensitivity is decreased by applying popular methods which improve the generalization performance of the model, such as (1) using a deep network rather than a wide one, (2) adding convolutional layers to baseline classifiers instead of adding fully-connected layers, (3) using batch normalization, dropout and max-pooling, and (4) applying parameter initialization techniques.

Generalization Comparison of Deep Neural Networks via Output Sensitivity

In this paper we investigate how to effectively deploy deep learning in practical industrial settings, such as robotic grasping applications. When a deep-learning based solution is proposed, usually lacks of any simple method to generate the training data. In the industrial field, where automation is the main goal, not bridging this gap is one of the main reasons why deep learning is not as widespread as it is in the academic world. For this reason, in this work we developed a system composed by a 3-DoF Pose Estimator based on Convolutional Neural Networks (CNNs) and an effective procedure to gather massive amounts of training images in the field with minimal human intervention. By automating the labeling stage, we also obtain very robust systems suitable for production-level usage. An open source implementation of our solution is provided, alongside with the dataset used for the experimental evaluation.

Effective Deployment of CNNs for 3DoF Pose Estimation and Grasping in Industrial Settings

Sketch recognition is essential in sketch-related researches. Different from the natural image, the sparse pixel distribution of sketch discards the visual texture which encourages researchers to explore the temporal information of sketch. Using of million-scale datasets, we explore the invariable structure and specific order of strokes in sketch. Prior works based on Recurrent Neural Network (RNN) output different features with changed stroke orders. In particular, we adopt a novel method by employing a Graph Convolutional Network (GCN) to extract invariable structural feature under any orders of strokes. Compared with traditional comprehension of sketch, we further split the temporal information of sketch into two types of feature, invariable structural feature (ISF) and drawing habits feature (DHF) with the aim of finer feature extraction in temporal information. We propose a two-branch GCN-RNN network, Sketch-SNet, to extract two types of feature respectively. The GCN branch is used to extract the ISF through receiving various shuffled strokes of an input sketch. The RNN branch takes the original order to extract DHF by learning the pattern of strokes’ order. Extensive experiments on the Quick-Draw dataset demonstrate that our further subdivision of temporal information improves the performance of sketch recognition which surpasses state-of-the-art by a large margin.

Sketch-SNet: Deeper Subdivision of Temporal Cues for Sketch Recognition


We first review the previous work about superpixel algorithm for RGB-D and RGB image. Then we introduce the our proposed deep neural network called BP-net for RGB-D superpixel segmentation. A novel loss function and a adaptive seeds initialization is also presented. Finally, we show the experimental results of the comparisons between our algorithm and serveral state-of-the-art algorithms and the ablation studies on the RGB-D dataset.

BP-net: deep learning-based superpixel segmentation for RGB-D image


Point cloud analysis is an important field for 3D scene understanding. It has applications in self driving cars and robotics (via LIDAR sensors), 3D graphics, and computer-aided design. Neural networks have recently achieved strong results on point cloud analysis problems such as classification and segmentation. Each point cloud network has the challenge of defining a convolution that can learn useful features on unstructured points. Some recent point cloud convolutions create separate weight matrices for separate directions like a CNN, but apply every weight matrix to every neighbor with soft assignments. This increases computational complexity and makes relatively small neighborhood aggregations expensive to compute. We propose Hard Directional Graph Networks (HDGN), a point cloud model that both learns directional weight matrices and assigns a single matrix to each neighbor, achieving directional convolutions at lower computational cost. HDGN's directional modeling achieves state-of-the-art results on multiple point cloud vision benchmarks.

Directional Graph Networks with Hard Weight Assignments


Atrial fibrillation is the most common heart rhythm disease. Due to a lack of understanding in matter of underlying atrial structures, current treatments are still not satisfying.Recently, with the popularity of deep learning, many segmentation methods based on fully convolutional networks have been proposed to analyze atrial structures, especially from late gadolinium-enhanced magnetic resonance imaging. However, two problems still occur: 1) segmentation results include the atrial-like background; 2) boundaries are very hard to segment. Most segmentation approaches design a specific network that mainly focuses on the regions, to the detriment of the boundaries.Therefore, this paper proposes an attention full convolutional network framework based on the ResNet-101 architecture, which focuses on boundaries as much as on regions. The additional attention module is added to have the network pay more attention on regions and then to reduce the impact of the misleading similarity of neighboring tissues. We also use a hybrid loss composed of a region loss and a boundary loss to treat boundaries and regions at the same time. We demonstrate the efficiency of the proposed approach on the MICCAI 2018 Atrial Segmentation Challenge public dataset.

Do not Treat Boundaries and Regions Differently: An Example on Heart Left Atrial Segmentation


In this paper, we address the problem of utilizing web images in training robust joint embedding models for the image-text retrieval task. Prior webly supervised approaches directly leverage weakly annotated web images in the joint embedding learning framework. The objective of these approaches would suffer significantly when the ratio of noisy and missing tags associated with the web images is very high. In this regard, we propose a CP decomposition based tensor completion framework to refine the tags of web images by modeling observed ternary inter-relations between the sets of labeled images, tags, and web images as a tensor. To effectively deal with the high ratio of missing entries likely in our case, we incorporate intra-modal correlation as side information in the proposed framework. Our tag refinement approach combined with existing web supervised image-text embedding approaches provide a more principled way for learning the joint embedding models in the presence of significant noise from web data and limited clean labeled data. Experiments on benchmark datasets demonstrate that the proposed approach helps to achieve a significant performance gain in image-text retrieval.

Webly Supervised Image-Text Embedding with Noisy Tag Refinement


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.

Downloads

Next from ICPR 2020

TinyVIRAT: Low-resolution Video Action Recognition

Similar lecture

Feature-Dependent Cross-Connections in Multi-Path Neural Networks