arXiv subjects

Kai Wang

Publications and source records attributed to Kai Wang.

At least 595 records · Page 33Linked to original sources

arXiv2022

Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation

We propose a simple but effective source-free domain adaptation (SFDA) method. Treating SFDA as an unsupervised clustering problem and following the intuition that local neighbors in feature space should have more similar predictions than other features, we propose to optimize an objective of prediction consistency. This objective encourages local neighborhood features in feature space to have similar predictions while features farther away in feature space have dissimilar predictions, leading to efficient feature clustering and cluster assignment simultaneously. For efficient training, we seek to optimize an upper-bound of the objective resulting in two simple terms. Furthermore, we relate popular existing methods in domain adaptation, source-free domain adaptation and contrastive learning via the perspective of discriminability and diversity. The experimental results prove the superiority of our method, and our method can be adopted as a simple but strong baseline for future research in SFDA. Our method can be also adapted to source-free open-set and partial-set DA which further shows the generalization ability of our method. Code is available in https://github.com/Albert0147/AaD_SFDA.

cs.CV↗

arXiv2022

Attention Distillation: self-supervised vision transformer students need more guidance

Self-supervised learning has been widely applied to train high-quality vision transformers. Unleashing their excellent performance on memory and compute constraint devices is therefore an important research topic. However, how to distill knowledge from one self-supervised ViT to another has not yet been explored. Moreover, the existing self-supervised knowledge distillation (SSKD) methods focus on ConvNet based architectures are suboptimal for ViT knowledge distillation. In this paper, we study knowledge distillation of self-supervised vision transformers (ViT-SSKD). We show that directly distilling information from the crucial attention mechanism from teacher to student can significantly narrow the performance gap between both. In experiments on ImageNet-Subset and ImageNet-1K, we show that our method AttnDistill outperforms existing self-supervised knowledge distillation (SSKD) methods and achieves state-of-the-art k-NN accuracy compared with self-supervised learning (SSL) methods learning from scratch (with the ViT-S model). We are also the first to apply the tiny ViT-T model on self-supervised learning. Moreover, AttnDistill is independent of self-supervised learning algorithms, it can be adapted to ViT based SSL methods to improve the performance in future research. The code is here: https://github.com/wangkai930418/attndistill

cs.CV↗

arXiv2022

Uncertainty estimations methods for a deep learning model to aid in clinical decision-making -- a clinician's perspective

Prediction uncertainty estimation has clinical significance as it can potentially quantify prediction reliability. Clinicians may trust 'blackbox' models more if robust reliability information is available, which may lead to more models being adopted into clinical practice. There are several deep learning-inspired uncertainty estimation techniques, but few are implemented on medical datasets -- fewer on single institutional datasets/models. We sought to compare dropout variational inference (DO), test-time augmentation (TTA), conformal predictions, and single deterministic methods for estimating uncertainty using our model trained to predict feeding tube placement for 271 head and neck cancer patients treated with radiation. We compared the area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) trends for each method at various cutoffs that sought to stratify patients into 'certain' and 'uncertain' cohorts. These cutoffs were obtained by calculating the percentile "uncertainty" within the validation cohort and applied to the testing cohort. Broadly, the AUC, sensitivity, and NPV increased as the predictions were more 'certain' -- i.e., lower uncertainty estimates. However, when a majority vote (implementing 2/3 criteria: DO, TTA, conformal predictions) or a stricter approach (3/3 criteria) were used, AUC, sensitivity, and NPV improved without a notable loss in specificity or PPV. Especially for smaller, single institutional datasets, it may be important to evaluate multiple estimations techniques before incorporating a model into clinical practice.

cs.LG↗

arXiv2022

RIGA: Rotation-Invariant and Globally-Aware Descriptors for Point Cloud Registration

Successful point cloud registration relies on accurate correspondences established upon powerful descriptors. However, existing neural descriptors either leverage a rotation-variant backbone whose performance declines under large rotations, or encode local geometry that is less distinctive. To address this issue, we introduce RIGA to learn descriptors that are Rotation-Invariant by design and Globally-Aware. From the Point Pair Features (PPFs) of sparse local regions, rotation-invariant local geometry is encoded into geometric descriptors. Global awareness of 3D structures and geometric context is subsequently incorporated, both in a rotation-invariant fashion. More specifically, 3D structures of the whole frame are first represented by our global PPF signatures, from which structural descriptors are learned to help geometric descriptors sense the 3D world beyond local regions. Geometric context from the whole scene is then globally aggregated into descriptors. Finally, the description of sparse regions is interpolated to dense point descriptors, from which correspondences are extracted for registration. To validate our approach, we conduct extensive experiments on both object- and scene-level data. With large rotations, RIGA surpasses the state-of-the-art methods by a margin of 8\degree in terms of the Relative Rotation Error on ModelNet40 and improves the Feature Matching Recall by at least 5 percentage points on 3DLoMatch.

cs.CV↗

arXiv2022

Recurrence-free Survival Prediction under the Guidance of Automatic Gross Tumor Volume Segmentation for Head and Neck Cancers

For Head and Neck Cancers (HNC) patient management, automatic gross tumor volume (GTV) segmentation and accurate pre-treatment cancer recurrence prediction are of great importance to assist physicians in designing personalized management plans, which have the potential to improve the treatment outcome and quality of life for HNC patients. In this paper, we developed an automated primary tumor (GTVp) and lymph nodes (GTVn) segmentation method based on combined pre-treatment positron emission tomography/computed tomography (PET/CT) scans of HNC patients. We extracted radiomics features from the segmented tumor volume and constructed a multi-modality tumor recurrence-free survival (RFS) prediction model, which fused the prediction results from separate CT radiomics, PET radiomics, and clinical models. We performed 5-fold cross-validation to train and evaluate our methods on the MICCAI 2022 HEad and neCK TumOR segmentation and outcome prediction challenge (HECKTOR) dataset. The ensemble prediction results on the testing cohort achieved Dice scores of 0.77 and 0.73 for GTVp and GTVn segmentation, respectively, and a C-index value of 0.67 for RFS prediction. The code is publicly available (https://github.com/wangkaiwan/HECKTOR-2022-AIRT). Our team's name is AIRT.

cs.CV↗

arXiv2022

Recursive Feasibility of Stochastic Model Predictive Control with Mission-Wide Probabilistic Constraints

This paper is concerned with solving chance-constrained finite-horizon optimal control problems, with a particular focus on the recursive feasibility issue of stochastic model predictive control (SMPC) in terms of mission-wide probability of safety (MWPS). MWPS assesses the probability that the entire state trajectory lies within the constraint set, and the objective of the SMPC controller is to ensure that it is no less than a threshold value. This differs from classic SMPC where the probability that the state lies in the constraint set is enforced independently at each time instant. Unlike robust MPC, where strict recursive feasibility is satisfied by assuming that the uncertainty is supported by a compact set, the proposed concept of recursive feasibility for MWPS is based on the notion of remaining MWPSs, which is conserved in the expected value sense. We demonstrate the idea of mission-wide SMPC in the linear SMPC case by deploying a scenario-based algorithm.

math.OC↗

arXiv2022

Time reflection and refraction in synthetic frequency dimension

The duality of space and time in Maxwell's equations has prompted interest in time boundaries and the accompanying temporal analog of spatial reflection and refraction. However, achieving observable time boundary effects at optical frequencies in real materials is challenging. In this work, we demonstrate that time reflection and refraction can be observed in a two-band model centered around a non-zero reference energy. Our model can be physically implemented in the synthetic frequency dimension as a system of two coupled dynamically-modulated ring resonators. We find that modulation at microwave frequencies is sufficient to observe time boundary effects for optical waves in synthetic frequency dimension. Our work shows that implementing multi-band models in synthetic dimensions opens a new avenue for further exploration of time boundaries.

physics.optics↗

arXiv2022

Solving Mission-Wide Chance-Constrained Optimal Control Using Dynamic Programming

This paper aims to provide a Dynamic Programming (DP) approach to solve the Mission-Wide Chance-Constrained Optimal Control Problems (MWCC-OCP). The mission-wide chance constraint guarantees that the probability that the entire state trajectory lies within a constraint/safe region is higher than a prescribed level, and is different from the stage-wise chance constraints imposed at individual time steps. The control objective is to find an optimal policy sequence that achieves both (i) satisfaction of a mission-wide chance constraint, and (ii) minimization of a cost function. By transforming the stage-wise chance-constrained problem into an unconstrained counterpart via Lagrangian method, standard DP can then be deployed. Yet, for MWCC-OCP, this methods fails to apply, because the mission-wide chance constraint cannot be easily formulated using stage-wise chance constraints due to the time-correlation between the latter (individual states are coupled through the system dynamics). To fill this gap, firstly, we detail the conditions required for a classical DP solution to exist for this type of problem; secondly, we propose a DP solution to the MWCC-OCP through state augmentation by introducing an additional functional state variable.

math.OC↗

arXiv2022

Towards reliable head and neck cancers locoregional recurrence prediction using delta-radiomics and learning with rejection option

A reliable locoregional recurrence (LRR) prediction model is important for the personalized management of head and neck cancers (HNC) patients. This work aims to develop a delta-radiomics feature-based multi-classifier, multi-objective, and multi-modality (Delta-mCOM) model for post-treatment HNC LRR prediction and adopting a learning with rejection option (LRO) strategy to boost the prediction reliability by rejecting samples with high prediction uncertainties. In this retrospective study, we collected PET/CT image and clinical data from 224 HNC patients. We calculated the differences between radiomics features extracted from PET/CT images acquired before and after radiotherapy as the input features. Using clinical parameters, PET and CT radiomics features, we built and optimized three separate single-modality models. We used multiple classifiers for model construction and employed sensitivity and specificity simultaneously as the training objectives. For testing samples, we fused the output probabilities from all these single-modality models to obtain the final output probabilities of the Delta-mCOM model. In the LRO strategy, we estimated the epistemic and aleatoric uncertainties when predicting with Delta-mCOM model and identified patients associated with prediction of higher reliability. Predictions with higher epistemic uncertainty or higher aleatoric uncertainty than given thresholds were deemed unreliable, and they were rejected before providing a final prediction. Different thresholds corresponding to different low-reliability prediction rejection ratios were applied. The inclusion of the delta-radiomics feature improved the accuracy of HNC LRR prediction, and the proposed Delta-mCOM model can give more reliable predictions by rejecting predictions for samples of high uncertainty using the LRO strategy.

physics.med-ph↗

arXiv2022

Prompt Vision Transformer for Domain Generalization

Though vision transformers (ViTs) have exhibited impressive ability for representation learning, we empirically find that they cannot generalize well to unseen domains with previous domain generalization algorithms. In this paper, we propose a novel approach DoPrompt based on prompt learning to embed the knowledge of source domains in domain prompts for target domain prediction. Specifically, domain prompts are prepended before ViT input tokens from the corresponding source domain. Each domain prompt learns domain-specific knowledge efficiently since it is optimized only for one domain. Meanwhile, we train a prompt adapter to produce a suitable prompt for each input image based on the learned source domain prompts. At test time, the adapted prompt generated by the prompt adapter can exploit the similarity between the feature of the out-of-domain image and source domains to properly integrate the source domain knowledge. Extensive experiments are conducted on four benchmark datasets. Our approach achieves 1.4% improvements in the averaged accuracy, which is 3.5 times the improvement of the state-of-the-art algorithm with a ViT backbone.

cs.CV↗

arXiv2022

QuickSkill: Novice Skill Estimation in Online Multiplayer Games

Matchmaking systems are vital for creating fair matches in online multiplayer games, which directly affects players' satisfactions and game experience. Most of the matchmaking systems largely rely on precise estimation of players' game skills to construct equitable games. However, the skill rating of a novice is usually inaccurate, as current matchmaking rating algorithms require considerable amount of games for learning the true skill of a new player. Using these unreliable skill scores at early stages for matchmaking usually leads to disparities in terms of team performance, which causes negative game experience. This is known as the ''cold-start'' problem for matchmaking rating algorithms. To overcome this conundrum, this paper proposes QuickSKill, a deep learning based novice skill estimation framework to quickly probe abilities of new players in online multiplayer games. QuickSKill extracts sequential performance features from initial few games of a player to predict his/her future skill rating with a dedicated neural network, thus delivering accurate skill estimation at the player's early game stage. By employing QuickSKill for matchmaking, game fairness can be dramatically improved in the initial cold-start period. We conduct experiments in a popular mobile multiplayer game in both offline and online scenarios. Results obtained with two real-world anonymized gaming datasets demonstrate that proposed QuickSKill delivers precise estimation of game skills for novices, leading to significantly lower team skill disparities and better player game experience. To the best of our knowledge, proposed QuickSKill is the first framework that tackles the cold-start problem for traditional skill rating algorithms.

cs.LG↗

arXiv2022

Skeleton-based Action Recognition via Temporal-Channel Aggregation

Skeleton-based action recognition methods are limited by the semantic extraction of spatio-temporal skeletal maps. However, current methods have difficulty in effectively combining features from both temporal and spatial graph dimensions and tend to be thick on one side and thin on the other. In this paper, we propose a Temporal-Channel Aggregation Graph Convolutional Networks (TCA-GCN) to learn spatial and temporal topologies dynamically and efficiently aggregate topological features in different temporal and channel dimensions for skeleton-based action recognition. We use the Temporal Aggregation module to learn temporal dimensional features and the Channel Aggregation module to efficiently combine spatial dynamic channel-wise topological features with temporal dynamic topological features. In addition, we extract multi-scale skeletal features on temporal modeling and fuse them with an attention mechanism. Extensive experiments show that our model results outperform state-of-the-art methods on the NTU RGB+D, NTU RGB+D 120, and NW-UCLA datasets.

cs.CV↗

arXiv2022

Cohomology theory of Rota-Baxter pre-Lie algebras of arbitrary weights

This paper is devoted to studying deformation, cohomology theory of Rota-Baxter pre-Lie algebras of arbitrary weights. First we give the notion of a new representation of a Rota-Baxter pre-Lie algebra of arbitrary weight and define the cohomology theory of a Rota-Baxter pre-Lie algebra of arbitrary weight. Then we study formal deformations by lower degree cohomology groups. Finally, we classify abelian extensions of Rota-Baxter pre-Lie algebras of arbitrary weight using the second cohomology group, and classify skeletal Rota-Baxter pre-Lie 2-algebra of arbitrary weight using the third cohomology group as applications.

math.RA↗

arXiv2022

Investigation of variable temperature Mössbauer spectrum of YFe$_{0.5}$Cr$_{0.5}$O$_3$ perovskite

In this paper, we reported the preparation of YFe$_{0.5}$Cr$_{0.5}$O$_3$ by the sol-gel method and studied its structure and Mössbauer spectrum at variable temperatures. X-ray diffraction(XRD) analysis exhibits that the sample has the orthorhombic structure with the Pnma space group, and the energy dispersive spectroscopy (EDS) analysis shows that the sample has Fe/Cr = 1:1, indicating that the sample is Fe half-doped YCrO$_3$. The hyperfine parameters of the Mössbauer spectrum at room temperature confirm that the characteristics of 57Fe in the sample were trivalent hexacoordinated high-spin(s=5/2), and the coexistence of doublet and the sextets at 250K indicate that the sample has superparamagnetic relaxation. The Mössbauer spectrum records the magnetic phase transition in the temperature range of 250K-300K.

cond-mat.mtrl-sci↗

arXiv2022

The Shape Part Slot Machine: Contact-based Reasoning for Generating 3D Shapes from Parts

We present the Shape Part Slot Machine, a new method for assembling novel 3D shapes from existing parts by performing contact-based reasoning. Our method represents each shape as a graph of ``slots,'' where each slot is a region of contact between two shape parts. Based on this representation, we design a graph-neural-network-based model for generating new slot graphs and retrieving compatible parts, as well as a gradient-descent-based optimization scheme for assembling the retrieved parts into a complete shape that respects the generated slot graph. This approach does not require any semantic part labels; interestingly, it also does not require complete part geometries -- reasoning about the slots proves sufficient to generate novel, high-quality 3D shapes. We demonstrate that our method generates shapes that outperform existing modeling-by-assembly approaches regarding quality, diversity, and structural complexity.

cs.GR↗

arXiv2022

Reliable Label Correction is a Good Booster When Learning with Extremely Noisy Labels

Learning with noisy labels has aroused much research interest since data annotations, especially for large-scale datasets, may be inevitably imperfect. Recent approaches resort to a semi-supervised learning problem by dividing training samples into clean and noisy sets. This paradigm, however, is prone to significant degeneration under heavy label noise, as the number of clean samples is too small for conventional methods to behave well. In this paper, we introduce a novel framework, termed as LC-Booster, to explicitly tackle learning under extreme noise. The core idea of LC-Booster is to incorporate label correction into the sample selection, so that more purified samples, through the reliable label correction, can be utilized for training, thereby alleviating the confirmation bias. Experiments show that LC-Booster advances state-of-the-art results on several noisy-label benchmarks, including CIFAR-10, CIFAR-100, Clothing1M and WebVision. Remarkably, under the extreme 90\% noise ratio, LC-Booster achieves 92.9\% and 48.4\% accuracy on CIFAR-10 and CIFAR-100, surpassing state-of-the-art methods by a large margin.

cs.CV↗

arXiv2022

Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Problems by Reinforcement Learning

In the predict-then-optimize framework, the objective is to train a predictive model, mapping from environment features to parameters of an optimization problem, which maximizes decision quality when the optimization is subsequently solved. Recent work on decision-focused learning shows that embedding the optimization problem in the training pipeline can improve decision quality and help generalize better to unseen tasks compared to relying on an intermediate loss function for evaluating prediction quality. We study the predict-then-optimize framework in the context of sequential decision problems (formulated as MDPs) that are solved via reinforcement learning. In particular, we are given environment features and a set of trajectories from training MDPs, which we use to train a predictive model that generalizes to unseen test MDPs without trajectories. Two significant computational challenges arise in applying decision-focused learning to MDPs: (i) large state and action spaces make it infeasible for existing techniques to differentiate through MDP problems, and (ii) the high-dimensional policy space, as parameterized by a neural network, makes differentiating through a policy expensive. We resolve the first challenge by sampling provably unbiased derivatives to approximate and differentiate through optimality conditions, and the second challenge by using a low-rank approximation to the high-dimensional sample-based derivatives. We implement both Bellman--based and policy gradient--based decision-focused learning on three different MDP problems with missing parameters, and show that decision-focused learning performs better in generalization to unseen tasks.

cs.LG↗

arXiv2022

Deformations and Cohomology Theory of Rota-Baxter Systems

Inspired by the work of Wang and Zhou [4] for Rota-Baxter algebras, we develop a cohomology theory of Rota-Baxter systems and justify it by interpreting the lower degree cohomology groups as formal deformations and as abelian extensions of Rota-Baxter systems. A further study on an $L_\infty$-algebra structure associated to this cohomology theory will be given in a subsequent paper.

math.RA↗