United States

Convolution is the main building block of a convolutional neural network (CNN).  We observe that an optimized CNN often has highly correlated filters as the number of channels increases with depth, reducing the expressive power of feature representations.   

We propose Tied Block Convolution (TBC) that shares the same thinner filter over equal blocks of channels and produces multiple responses with a single filter. The concept of TBC can also be extended to group convolution and fully connected layers, and can be applied to various backbone networks and attention modules.

Our extensive experimentation on classification, detection, instance segmentation, and attention demonstrates that TBC is consistently leaner and significantly better than standard convolution and group convolution. On attention, with 64 times fewer parameters, our TiedSE performs on par with the standard SE. 

On detection and segmentation, TBC can effectively handle highly overlapping instances, whereas standard CNNs often fail to accurately aggregate information in the presence of occlusion and result in multiple redundant partial object proposals.  By sharing filters across channels, TBC reduces correlation and delivers a sizable gain of 6% in the average precision for object detection on MS-COCO when the occlusion ratio is 80%.

AAAI 2021

Tied Block Convolution: Leaner and Better CNNs with Shared Thinner Filters

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

With the increase of available time series data, predicting their class labels has been one of the most important challenges in a wide range of disciplines. Recent studies on time series classification show that convolutional neural networks (CNN) achieved the state-of-the-art performance as a single classifier. In this work, pointing out that the global pooling layer that is usually adopted by existing CNN classifiers discards the temporal information of high-level features, we present a dynamic temporal pooling (DTP) technique that reduces the temporal size of hidden representations by aggregating the features at the segment-level. For the partition of a whole series into multiple segments, we utilize dynamic time warping (DTW) to align each time point in a temporal order with the prototypical features of the segments, which can be optimized simultaneously with the network parameters of CNN classifiers. The DTP layer combined with a fully-connected layer helps to extract further discriminative features considering their temporal position within an input time series. Extensive experiments on both univariate and multivariate time series datasets show that our proposed pooling significantly improves the classification performance.

Learnable Dynamic Temporal Pooling for Time Series Classification

Contract consistency is important in ensuring the legal validity of the contract. In many scenarios, a contract is written by filling the blanks in a precompiled form. Due to carelessness, two blanks that should be filled with the same (or different) content may be incorrectly filled with different (or same) content. This will result in the issue of contract inconsistencies, which may severely impair the legal validity of the contract. Traditional methods to address this issue mainly rely on manual contract review, which is labor-intensive and costly. In this work, we formulate a novel Contract Inconsistency Checking (CIC) problem, and design an end-to-end framework, called Pair-wise Blank Resolution (PBR), to solve the CIC problem with high accuracy. Our PBR model contains a novel BlankCoder to address the challenge of modeling meaningless blanks. BlankCoder adopts a two-stage attention mechanism that adequately associates a meaningless blank with its relevant descriptions while avoiding the incorporation of irrelevant context words. Experiments conducted on real-world datasets show the promising performance of our method with a balanced accuracy of 94.05% and an F1 score of 90.90% in the CIC problem.

Learning to Check Contract Inconsistencies

Generative adversarial networks (GANs) are known to benefit from regularization or normalization of their critic (discriminator) network during training. In this paper, we analyze the popular spectral normalization scheme, find a significant drawback and introduce sparsity aware normalization (SAN), a new alternative approach for stabilizing GAN training. As opposed to other normalization methods, our approach explicitly accounts for the sparse nature of the feature maps in convolutional networks with ReLU activations. We illustrate the effectiveness of our method through extensive experiments with a variety of network architectures. As we show, sparsity is particularly dominant in critics used for image-to-image translation settings. In these cases our approach improves upon existing methods, in less training epochs and with smaller capacity networks, while requiring practically no computational overhead.

Sparsity Aware Normalization for GANs

Generative moment matching networks (GMMN) present a theoretically sound approach to learning deep generative mod-els. However, such methods are typically limited by the high sample complexity, thereby impractical in generating complex data. In this paper, we present a new strategy to train GMMN with a low sample complexity while retaining the theoretical soundness. Our method introduces some auxiliary variables, whose values are provided by a pre-trained model such as an encoder network in practice. Conditioned on these variables, we partition the distribution into a set of conditional distributions, which can be effectively matched with a low sample complexity. We instantiate this strategy by presenting an amortized network called GMMN-DP with shared auxiliary variable information for the data generation task, as well as developing an efficient stochastic training algorithm.The experimental results show that GMMN-DP can generate complex samples on datasets such as CelebA and CIFAR-10, where the vanilla GMMN fails.

Improving Generative Moment Matching Networks with Distribution Partition

Catastrophic forgetting refers to the tendency that a neural network ``forgets'' the previous learned knowledge upon learning new tasks. Prior methods have been focused on overcoming this problem on convolutional neural networks (CNNs), where the input samples like images lie in a grid domain, but have largely overlooked graph neural networks (GNNs) that handle non-grid data. In this paper, we propose a novel scheme dedicated to overcoming catastrophic forgetting problem and hence strengthen continual learning in GNNs. At the heart of our approach is a generic module, termed as topology-aware weight preserving (TWP), applicable to arbitrary form of GNNs in a plug-and-play fashion. Unlike the main stream of CNN-based continual learning methods that rely on solely slowing down the updates of parameters important to the downstream task, TWP explicitly explores the local structures of the input graph, and attempts to stabilize the parameters playing pivotal roles in the topological aggregation. We evaluate TWP on different GNN backbones over several datasets, and demonstrate that it yields performances superior to the state of the art. Code is publicly available at https://github.com/hhliu79/TWP.

Overcoming Catastrophic Forgetting in Graph Neural Networks

Time-series is ubiquitous across applications, such as transportation, finance and healthcare. Time-series is often influenced by external factors, especially in the form of asynchronous events, making forecasting difficult. However, existing models are mainly designated for either synchronous time-series or asynchronous event sequence, and can hardly provide a synthetic way to capture the relation between them. We propose Variational Synergetic Multi-Horizon Network (VSMHN), a novel deep conditional generative model. To learn complex correlations across heterogeneous sequences, a tailored encoder is devised to combine the advances in deep point processes models and variational recurrent neural networks. In addition, an aligned time coding and an auxiliary transition scheme are carefully devised for batched training on unaligned sequences. Our model can be trained effectively using stochastic variational inference and generates probabilistic predictions with Monte-Carlo simulation. Furthermore, our model produces accurate, sharp and more realistic probabilistic forecasts. We also show that modeling asynchronous event sequences is crucial for multi-horizon time-series forecasting.

Synergetic Learning of Heterogeneous Temporal Sequences for Multi-Horizon Probabilistic Forecasting

In this paper, we propose an adaptive kNN method for classification, in which different k are selected for different test samples. Our selection rule is easy to implement since it is completely adaptive and does not require any knowledge of
the underlying distribution. The convergence rate of the risk of this classifier to the Bayes risk is shown to be minimax optimal for various settings. Moreover, under some special assumptions, the convergence rate is especially fast and does
not decay with the increase of dimensionality.

Efficient Classification with Adaptive KNN

Mitigating the risk arising from extreme events is a fundamental goal with many applications, such as the modelling of natural disasters, financial crashes, epidemics, and many others. To manage this risk, a vital step is to be able to understand or generate a wide range of extreme scenarios. Existing approaches based on Generative Adversarial Networks (GANs) excel at generating realistic samples, but seek to generate typical samples, rather than extreme samples. Hence, in this work, we propose ExGAN, a GAN-based approach to generate realistic and extreme samples. To model the extremes of the training distribution in a principled way, our work draws from Extreme Value Theory (EVT), a probabilistic approach for modelling the extreme tails of distributions. For practical utility, our framework allows the user to specify both the desired extremeness measure, as well as the desired extremeness probability they wish to sample at. Experiments on real US Precipitation data show that our method generates realistic samples, based on visual inspection and quantitative measures, in an efficient manner. Moreover, generating increasingly extreme examples using ExGAN can be done in constant time (with respect to the extremeness probability Ï„), as opposed to the O(1/Ï„) time required by the baseline approach.

ExGAN: Adversarial Generation of Extreme Samples

We study Stackelberg security game (SSG) with multiple defenders, where heterogeneous defenders need to allocate security resources to protect a set of targets against a strategic attacker. 
In such games, coordination and cooperation between the defenders can increase their ability to protect their assets, but the heterogeneous preferences of the self-interested defenders often make such cooperation very difficult. 
In this paper, we approach the problem from the perspective of cooperative game theory and study coalition formation among the defenders.
Our main contribution is a number of algorithmic results for the computation problems that arise in this model.
We provide a poly-time algorithm for computing a solution in the core of the game and show that all of the elements in the core are Pareto efficient.
We show that the problem of computing the entire core is NP-hard and then delve into a special setting where the size of a coalition is limited up to some threshold. 
We analyse the parameterized complexity of deciding if a coalition structure is in the core under this special setting, and provide a poly-time algorithm for computing successful deviation strategies for a given coalition.

Coalition Formation in Multi-Defender Security Games

This paper represents object instance as a terrace, where the height of terrace corresponds to object attention while the evolution of layers from peak to sea level represents the complexity in drawing the finer boundary of an object. A multitask neural network is presented to learn the terrace representation. The attention of terrace is leveraged for instance counting, and the layers provide prior for easy-to-hard pathway of progressive instance segmentation. We study the model for counting and segmentation for a variety of food instances, ranging from Chinese, Japanese to Western food. This paper presents how the terrace model deals with arbitrary shape, size, obscure boundary and occlusion of instances, where other techniques are currently short of.

Downloads

Next from AAAI 2021

Learnable Dynamic Temporal Pooling for Time Series Classification

Similar lecture

Compressing Deep Convolutional Neural Networks by Stacking Low-Dimensional Binary Convolution Filters

.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

Learnable Dynamic Temporal Pooling for Time Series Classification

Similar lecture

Compressing Deep Convolutional Neural Networks by Stacking Low-Dimensional Binary Convolution Filters

Downloads