United States

License plate recognition (LPR) is a fundamental component of various intelligent transportation systems, and is always expected to be accurate and efficient enough in real-world applications. Nowadays, recognition of single character has been sophisticated benefiting from the power of deep learning, and extracting position information for forming a character sequence becomes the main bottleneck of LPR. To tackle this issue, we propose a novel holistic position attention (HPA) in this paper that consists of position network and shared classifier. Specifically, the position network explicitly encodes the character position into the maps of HPA, and then the shared classifier performs the character recognition in a unified and parallel way. Here the extracted features are modulated by the attention maps before feeding into the classifier to yield the final recognition results. Note that our proposed method is end-to-end trainable, character recognition can be concurrently performed, and no post-processing is needed. Thus our LPR system can achieve good effectiveness and efficiency simultaneously. The experimental results on four public datasets, including AOLP, Media Lab, CCPD, and CLPD, well demonstrate the superiority of our method to previous state-of-the-art methods in both accuracy and speed.

AAAI 2021

Efficient License Plate Recognition via Holistic Position Attention

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

technical paper

The stability and generalization of stochastic gradient-based
methods provide valuable insights into understanding the algorithmic performance of machine learning models. As the
main workhorse for deep learning, the stochastic gradient descent has received a considerable amount of studies. Nevertheless, the community paid little attention to its decentralized variants. In this paper, we provide a novel formulation
of the decentralized stochastic gradient descent. Leveraging
this formulation together with (non)convex optimization theory, we establish the first stability and generalization guarantees for the decentralized stochastic gradient descent. Our
theoretical results are built on top of a few common and mild
assumptions and reveal that the decentralization deteriorates
the stability of SGD for the first time. We verify our theoretical findings by using a variety of decentralized settings and
benchmark machine learning models.

Stability and Generalization for Decentralized Stochastic Gradient Descent

In this paper, we propose a domain-general model, termed learning-to-weight (LTW), that guarantees face detection performance across multiple domains, particularly the target domains that are never seen before. However, various face forgery methods cause complex and biased data distributions, making it challenging to detect fake faces in unseen domains. We argue that different faces contribute differently to a detection model trained on multiple domains, making the model likely to fit domain-specific biases. As such, we propose the LTW approach based on the meta-weight learning algorithm, which configures different weights for face images from different domains. The LTW network can balance the model's generalizability across multiple domains. Then, the meta-optimization calibrates the source domain's gradient enabling more discriminative features to be learned. The detection ability of the network is further improved by introducing an intra-class compact loss. Extensive experiments on several commonly used deepfake datasets to demonstrate the effectiveness of our method in detecting synthetic faces. Code and supplemental material are available at https://github.com/skJack/LTW.

Domain General Face Forgery Detection by Learning to Weight

Bilinear pooling has achieved an excellent performance in many computer vision tasks such as fine-grained classification, scene recognition and texture recognition. However, the high-dimension features from bilinear pooling can sometimes be inefficient and prone to over-fitting. Random Maclaurin (RM) is a widely used GPU-friendly approximation method to reduce the dimensionality of bilinear features. However, to achieve good performance, large projection matrices are usually required in practice, making it costly in computation and memory. In this paper, we propose a Shifted Random Maclaurin (SRM) strategy for  fast and compact bilinear pooling. With merely negligible extra computational cost, the proposed SRM provides an estimator with a provably smaller variance than RM, which benefits accurate kernel approximation and thus the learning performance. Using a small projection matrix, the proposed SRM achieves a comparable estimation performance as RM based on a large projection matrix, and thus boosts the efficiency.  Furthermore, we upgrade the proposed SRM to SRM+ to further improve the efficiency and make the compact bilinear pooling compatible with fast matrix normalization.  Fast and Compact Bilinear Network (FCBN) built upon the proposed SRM+ is devised, achieving an end-to-end training. Systematic experiments  conducted on four public datasets demonstrate the effectiveness and efficiency of the proposed FCBN.

Fast and Compact Bilinear Pooling by Shifted Random Maclaurin

LiDAR point cloud analysis is a core task for 3D computer vision, especially for autonomous driving. However, due to the severe sparsity and noise interference in the single sweep LiDAR point cloud, the accurate semantic segmentation is non-trivial to achieve. In this paper, we propose a novel sparse LiDAR point cloud semantic segmentation framework assisted by learned contextual shape priors. In practice, an initial semantic segmentation (SS) of a single sweep point cloud can be achieved by any appealing network and then flows into the semantic scene completion (SSC) module as the input. By merging multiple frames in the LiDAR sequence as supervision, the optimized SSC module has learned the contextual shape priors from sequential LiDAR data, completing the sparse single sweep point cloud to the dense one. Thus, it inherently improves SS optimization through fully end-to-end training. Besides, a Point-Voxel Interaction (PVI) module is proposed to further enhance the knowledge fusion between SS and SSC tasks, i.e., promoting the interaction of incomplete local geometry of point cloud and complete voxel-wise global structure. Furthermore, the auxiliary SSC and PVI modules can be discarded during inference without extra burden for SS. Extensive experiments confirm that our JS3C-Net achieves superior performance on both SemanticKITTI and SemanticPOSS benchmarks, i.e., 4% and 3% improvement correspondingly.

Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion

We consider long-term path forecasting problems in crowds, where future sequence trajectories are generated given a short observation. Recent methods for this problem have focused on modeling social interactions and predicting multi-modal futures. However, it is not easy for machines to successfully consider social interactions, such as avoiding collisions while considering the uncertainty of futures under a highly interactive and dynamic scenario. In this paper, we propose a model that incorporates multiple interacting motion sequences jointly and predicts multi-modal socially acceptable distributions of futures. Specifically, we introduce a new aggregation mechanism for social interactions, which selectively models long-term inter-related dynamics between movements in a shared environment through a message passing mechanism. Moreover, we propose a loss function that not only accesses how accurate the estimated distributions of the futures are but also considers collision avoidance. We further utilize mixture density functions to describe the trajectories and learn the multi-modality of future paths.  Extensive experiments over several trajectory prediction benchmarks demonstrate that our method is able to forecast socially acceptable distributions in complex scenarios.

Social-DPF: Socially Acceptable Distribution Prediction of Futures

Post-hoc explanation methods for machine learning models have been widely used to support decision-making. One of the popular methods is Counterfactual Explanation (CE), also known as Actionable Recourse, which provides a user with a perturbation vector of features that alters the prediction result. Given a perturbation vector, a user can interpret it as an "action" for obtaining one's desired decision result. In practice, however, showing only a perturbation vector is often insufficient for users to execute the action. The reason is that if there is an asymmetric interaction among features, such as causality, the total cost of the action is expected to depend on the order of changing features. Therefore, practical CE methods are required to provide an appropriate order of changing features in addition to a perturbation vector. For this purpose, we propose a new framework called Ordered Counterfactual Explanation (OrdCE). We introduce a new objective function that evaluates a pair of an action and an order based on feature interaction. To extract an optimal pair, we propose a mixed-integer linear optimization approach with our objective function. Numerical experiments on real datasets demonstrated the effectiveness of our OrdCE in comparison with unordered CE methods.

Ordered Counterfactual Explanation by Mixed-Integer Linear Optimization

Traditional studies on recommender systems usually leverage only one type of user behaviors (the optimization target, such as purchase), despite the fact that users also generate a large number of various types of interaction data (e.g., view, click, add-to-cart, etc). Generally, these heterogeneous multi-relational data provide well-structured information and can be used for high-quality recommendation. Early efforts towards leveraging these heterogeneous data fail to capture the high-hop structure of user-item interactions, which are unable to make full use of them and may only achieve constrained recommendation performance. In this work, we propose a new multi-relational recommendation model named Graph Heterogeneous Collaborative Filtering (GHCF). To explore the high-hop heterogeneous user-item interactions, we take the advantages of Graph Convolutional Network (GCN) and further improve it to jointly embed both representations of nodes (users and items) and relations for multi-relational prediction. Moreover, to fully utilize the whole heterogeneous data, we perform the advanced efficient non-sampling optimization under a multi-task learning framework. Experimental results on two public benchmarks show that GHCF significantly outperforms the state-of-the-art recommendation methods, especially for cold-start users who have few primary item interactions. Further analysis verifies the importance of the proposed embedding propagation for modelling high-hop heterogeneous user-item interactions, showing the rationality and effectiveness of GHCF. Our implementation has been released (https://github.com/chenchongthu/GHCF).

Graph Heterogeneous Multi-Relational Recommendation

Deep learning-based semi-supervised learning (SSL) algorithms have led to promising results in medical images segmentation and can alleviate doctors' expensive  annotations by leveraging unlabeled data. However, most of the existing SSL algorithms in literature tend to  regularize  the  model training by perturbing networks and/or data. Observing that multi/dual-task learning attends to various levels of information which have inherent prediction perturbation, we ask the question in this work: can we explicitly build task-level regularization rather than implicitly constructing networks- and/or data-level perturbation and then regularization for SSL? To answer this question, we propose a novel dual-task-consistency semi-supervised framework for the first time. Concretely, we use a dual-task deep network that jointly predicts a pixel-wise segmentation map and a geometry-aware level set representation of the target. The level set representation is converted to an approximated segmentation map through a differentiable task transform layer. Simultaneously, we introduce a dual-task consistency regularization between the level set-derived segmentation maps and directly predicted segmentation maps for both labeled and unlabeled data. Extensive experiments on two public datasets show that our method can largely improve the performance by incorporating the unlabeled data. Meanwhile, our framework outperforms the state-of-the-art semi-supervised learning methods.

Semi-Supervised Medical Image Segmentation through Dual-Task Consistency

We show that an interesting class of feed-forward neural networks can be understood as quantitative argumentation frameworks. 
This connection creates a bridge between research in Formal Argumentation and Machine Learning.
We generalize the semantics of feed-forward neural networks to acyclic graphs and study the resulting
computational and semantical properties in argumentation
graphs. As it turns out, the semantics gives stronger guarantees than existing semantics 
that have been tailor-made for the argumentation setting. 
From a machine-learning perspective, the connection does not seem immediately helpful. While it gives intuitive meaning
to some feed-forward-neural networks, they remain difficult to understand due to their size and density.
However, the connection seems helpful for combining background knowledge in form of
sparse argumentation networks with dense neural networks that have been trained for complementary purposes
and for learning the parameters of quantitative argumentation frameworks in an end-to-end fashion from data.

Interpreting Neural Networks as Quantitative Argumentation Frameworks

Camouflaged objects, similar to the background, show indefinable boundaries and deceptive textures, which increases the difficulty of detection task and makes the model rely on features with more information. Herein, we design a texture label to facilitate our network for accurate camouflaged object segmentation. Motivated by the complementary relationship between texture labels and camouflaged object labels, we propose an interactive guidance framework named TINet, which focuses on finding the indefinable boundary and the texture difference by progressive interactive guidance. It maximizes the guidance effect of refined multi-level texture cues on segmentation. Specifically, texture perception decoder (TPD) makes a comprehensive analysis of texture information in multiple scales. Feature interaction guidance decoder (FGD) interactively refines multi-level features of camouflaged object detection and texture detection level by level. Holistic perception decoder (HPD) enhances FGD results by multi-level holistic perception. In addition, we propose a boundary weight map to help the loss function pay more attention to the object boundary. Sufficient experiments conducted on COD and SOD datasets demonstrate that the proposed method performs favorably against 23 state-of-the-art methods.

Downloads

Next from AAAI 2021

Stability and Generalization for Decentralized Stochastic Gradient Descent

Similar lecture

Dynamic Position-Aware Network for Fine-Grained Image Recognition

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2021

Stability and Generalization for Decentralized Stochastic Gradient Descent

Similar lecture

Dynamic Position-Aware Network for Fine-Grained Image Recognition

Downloads