United States

How to properly reduce the annotation cost for panoptic segmentation? How to leverage and optimize the cost-quality trade-off for training data and model? These questions are key challenges towards a label-efficient and scalable panoptic segmentation system due to its expensive instance/semantic pixel-level annotation requirements. By closely examining different kinds of cheaper labels, we introduce a novel multi-objective framework to automatically determine the allocation of different annotations, so as to reach a better segmentation quality with a lower annotation cost. Specifically, we design a Cost-Quality Balanced Network (CQB-Net) to generate the panoptic segmentation map, which distills the crucial relations between various supervisions including panoptic labels, image-level classification labels, bounding boxes, and the semantic coherence information between the foreground and background. Instead of ad-hoc allocation during training, we formulate the optimization of cost-quality trade-off as a Multi-Objective Optimization Problem (MOOP). We model the marginal quality improvement of each annotation and approximate the Pareto-front to enable a label-efficient allocation ratio. Extensive experiments on COCO benchmark show the superiority of our method, e.g. achieving a segmentation quality of 43.4% compared to 43.0% of OCFusion while saving 2.4x annotation cost.

AAAI 2021

How to Save your Annotation Cost for Panoptic Segmentation?

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

Time-series clustering is an essential unsupervised technique for data analysis, applied to many real-world fields, such as medical analysis and DNA microarray. Existing clustering methods are usually based on the assumption that the data is complete. However, time series in real-world applications often contain missing values. Traditional strategy (imputing first and then clustering) does not optimize the imputation and clustering process as a whole, which not only makes per- formance dependent on the combination of imputation and clustering methods but also fails to achieve satisfactory re- sults. How to best improve the clustering performance on incomplete time series remains a challenge. This paper pro- poses a novel unsupervised temporal representation learning model, named Clustering Representation Learning on Incom- plete time-series data (CRLI). CRLI jointly optimizes the im- putation and clustering process to impute more discrimina- tive values for clustering and make the learned representa- tions possessed good clustering property. Also, to reduce the error propagation from imputation to clustering, we introduce a discriminator to make the distribution of imputation values close to the true one and train CRLI in an alternating train- ing manner. An experiment conducted on eight real-world in- complete time-series datasets shows that CRLI outperforms existing methods. We demonstrates the effectiveness of the learned representations and the convergence of the model through visualization analysis. Moreover, we reveal that the joint training strategy can impute values close to the true ones in those important sub-sequences, and impute more discrim- inative values in those less important sub-sequences at the same time, making the imputed sequence cluster-friendly.

Learning Representations for Incomplete Time Series Clustering

Human gesture recognition has drawn much attention in the area of computer vision. However, the performance of gesture recognition is always influenced by some gesture-irrelevant factors like the background and the clothes of performers. Therefore, focusing on the regions of hand/arm is important to the gesture recognition. Meanwhile, a more adaptive architecture-searched network structure can also perform better than the block-fixed ones like ResNet since it increases the diversity of features in different stages of the network better. In this paper, we propose a regional attention with architecture-rebuilt 3D network (RAAR3DNet) for gesture recognition. We replace the fixed Inception modules with the automatically rebuilt structure through the network via Neural Architecture Search (NAS), owing to the different shape and representation ability of features in the early, middle, and late stage of the network.  It enables the network to capture different levels of feature representations at different layers more adaptively. Meanwhile, we also design a stackable regional attention module called Dynamic-Static Attention (DSA), which derives a Gaussian guidance heatmap and dynamic motion map to highlight the hand/arm regions and the motion information in the spatial and temporal domains, respectively. Extensive experiments on two recent large-scale RGB-D gesture datasets validate the effectiveness of the proposed method and show it outperforms state-of-the-art methods. The codes of our method are available at:  https://github.com/zhoubenjia/RAAR3DNet.

Regional Attention with Architecture-Rebuilt 3D Network for RGB-D Gesture Recognition

Online platforms sell advertisements via auctions (e.g., VCG and GSP auction) and revenue maximization is one of the most important tasks for them. Many revenue increment methods are proposed, like reserve pricing, boosting, coupons and so on. The novelty of coupons rests on the fact that coupons are optional for advertisers while the others are compulsory. Recent studies on coupons have limited applications in advertising systems because they only focus on second price auctions and do not consider the combination with other methods. In this work, we study the coupon design problem for revenue maximization in the widely used VCG auction. Firstly, we examine the bidder strategies in the VCG auction with coupons. Secondly, we cast the coupon design problem into a learning framework and propose corresponding algorithms using the properties of VCG auction. Then we further study how to combine coupons with reserve pricing in our framework. Finally, extensive experiments are conducted to demonstrate the effectiveness of our algorithms based on both synthetic data and industrial data.

Coupon Design in Advertising Systems

Node representation learning for directed graphs is critically important to facilitate many graph mining tasks. To capture the directed edges between nodes, existing methods mostly learn two embedding vectors for each node, source vector and target vector. However, these methods learn the source and target vectors separately. For the node with very low indegree or outdegree, the corresponding target vector or source vector cannot be effectively learned. In this paper, we propose a novel Directed Graph embedding framework based on Generative Adversarial Network, called DGGAN. The main idea is to use adversarial mechanisms to deploy a discriminator and two generators that jointly learn each nodeâ€™s source and target vectors. For a given node, the two generators are trained to generate its fake target and source neighbor nodes from the same underlying distribution, and the discriminator aims to distinguish whether a neighbor node is real or fake. The two generators are formulated into a unified framework and could mutually reinforce each other to learn more robust source and target vectors. Extensive experiments show that DGGAN consistently and significantly outperforms existing state-of-the-art methods across multiple graph mining tasks on directed graphs.

Adversarial Directed Graph Embedding

Tournament solutions are standard tools for identifying winners based on pairwise comparisons between competing alternatives. The recently studied notion of margin of victory (MoV) offers a general method for refining the winner set of any given tournament solution, thereby increasing the discriminative power of the solution. In this paper, we reveal a number of structural insights on the MoV by investigating fundamental properties such as monotonicity and consistency with respect to the covering relation. Furthermore, we provide experimental evidence on the extent to which the MoV notion refines winner sets in tournaments generated according to various stochastic models.

Margin of Victory in Tournaments: Structural and Experimental Results

Portfolio management via reinforcement learning is at the forefront of fintech research, which explores how to optimally reallocate a fund into different financial assets over the long term by trial-and-error. Existing methods are impractical since they usually assume each reallocation can be finished immediately and thus ignoring the price slippage as part of the trading cost. To address these issues, we propose a hierarchical reinforced stock trading system for portfolio management (HRPM). Concretely, we decompose the trading process into a hierarchy of portfolio management over trade execution and train the corresponding policies. The high-level policy gives portfolio weights at a lower frequency to maximize the long-term profit and invokes the low-level policy to sell or buy the corresponding shares within a short time window at a higher frequency to minimize the trading cost. We train two levels of policies via a pre-training scheme and an iterative training scheme for data efficiency. Extensive experimental results in the U.S. market and the China market demonstrate that HRPM achieves significant improvement against many state-of-the-art approaches.

Commission Fee Is Not Enough: A Hierarchical Reinforced Framework for Portfolio Management

Learning representations for graphs plays a critical role in a wide spectrum of downstream applications. In this paper, we summarize the limitations of the prior works in three folds: representation space, modeling dynamics and modeling uncertainty. To bridge this gap, we propose to learn dynamic graph representations  in hyperbolic space, for the first time, which aims to infer stochastic node representations. Working with hyperbolic space, we present a novel Hyperbolic Variational Graph Neural Network, referred to as HVGNN. In particular, to model the dynamics, we introduce a Temporal GNN (TGNN) based on a theoretically grounded time encoding approach. To model the uncertainty, we devise a hyperbolic graph variational autoencoder built upon the proposed TGNN to generate stochastic node representations of hyperbolic normal distributions. Furthermore, we introduce a reparameterisable sampling algorithm for the hyperbolic normal distribution to enable the gradient-based learning of HVGNN.  Extensive experiments show that HVGNN outperforms state-of-the-art baselines on real-world datasets.

Hyperbolic Variational Graph Neural Network for Modeling Dynamic Graphs

There is a growing concern that the recent progress made in AI, especially regarding the predictive competence of deep learning models, will be undermined by a failure to properly explain their operation and outputs. In response to this disquiet, counterfactual explanations have become very popular in eXplainable AI (XAI) due to their asserted computational, psychological, and legal benefits. In contrast however, semi-factuals (which appear to be equally useful) have surprisingly received no attention. Most counterfactual methods address tabular rather than image data, partly because the non-discrete nature of images makes good counterfactuals difficult to define; indeed, generating plausible counterfactual images which lie on the data manifold is also problematic. This paper advances a novel method for generating plausible counterfactuals and semi-factuals for black-box CNN classifiers doing computer vision. The present method, called PlausIble Exceptionality-based Contrastive Explanations (PIECE), modifies all â€œexceptionalâ€ features in a test image to be â€œnormalâ€ from the perspective of the counterfactual class, to generate plausible counterfactual images. Two controlled experiments compare this method to others in the literature, showing that PIECE generates highly plausible counterfactuals (and the best semi-factuals) on several benchmark measures.

On Generating Plausible Counterfactual and Semi-Factual Explanations for Deep Learning

We propose a novel image-to-pencil translation method that could not only generate high-quality pencil sketches but also offer the drawing process. Existing pencil sketch algorithms are based on texture rendering rather than the direct imitation of strokes, making them unable to show the drawing process but only a final result. To address this challenge, we first establish a pencil stroke imitation mechanism. Next, we develop a framework with three branches to guide stroke drawing: the first branch guides the direction of the strokes, the second branch determines the shade of the strokes, and the third branch enhances the details further. Under this framework's guidance, we can produce a pencil sketch by drawing one stroke every time. Our method is fully interpretable. Comparison with existing pencil drawing algorithms shows that our method is superior to others in terms of texture quality, style, and user evaluation. Our code and supplementary material are now available at: https://github.com/TZYSJTU/Sketch-Generation-withDrawing-Process-Guided-by-Vector-Flow-and-Grayscale

Sketch Generation with Drawing Process Guided by Vector Flow and Grayscale

We study the computational complexity of abstract argumentation
semantics based on weak admissibility, a recently introduced concept 
to deal with arguments of self-defeating nature.
Our results reveal that semantics based
on weak admissibility are of much higher complexity
(under typical assumptions) compared to all
argumentation semantics which have been analysed in 
terms of complexity so far. In fact, we show 
PSPACE-completeness of
all non-trivial standard decision problems for weak-admissible based semantics.
We then investigate potential tractable fragments and show that
restricting the frameworks under consideration to certain graph-classes 
significantly reduces the complexity.            
As a strategy for implementation we also provide a polynomial-time reduction 
to DATALOG with stratified negation.

Downloads

Next from AAAI 2021

Learning Representations for Incomplete Time Series Clustering

Similar lecture

REFINE: Prediction Fusion Network for Panoptic Segmentation

.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

Learning Representations for Incomplete Time Series Clustering

Similar lecture

REFINE: Prediction Fusion Network for Panoptic Segmentation

Downloads