Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence最新文献_第8页

Mean Estimation of Truncated Mixtures of Two Gaussians: A Gradient Based Approach 截断两高斯混合的均值估计:一种基于梯度的方法

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i8.26110

Sai Ganesh Nagarajan, Gerasimos Palaiopanos, Ioannis Panageas, Tushar Vaidya, Samson Yu

{"title":"Mean Estimation of Truncated Mixtures of Two Gaussians: A Gradient Based Approach","authors":"Sai Ganesh Nagarajan, Gerasimos Palaiopanos, Ioannis Panageas, Tushar Vaidya, Samson Yu","doi":"10.1609/aaai.v37i8.26110","DOIUrl":"https://doi.org/10.1609/aaai.v37i8.26110","url":null,"abstract":"Even though data is abundant, it is often subjected to some form of censoring or truncation which inherently creates biases. Removing such biases and performing parameter estimation is a classical challenge in Statistics. In this paper, we focus on the problem of estimating the means of a mixture of two balanced d-dimensional Gaussians when the samples are prone to truncation. A recent theoretical study on the performance of the Expectation-Maximization (EM) algorithm for the aforementioned problem showed EM almost surely converges for d=1 and exhibits local convergence for d>1 to the true means. Nevertheless, the EM algorithm for the case of truncated mixture of two Gaussians is not easy to implement as it requires solving a set of nonlinear equations at every iteration which makes the algorithm impractical. In this work, we propose a gradient based variant of the EM algorithm that has global convergence guarantees when d=1 and local convergence for d>1 to the true means. Moreover, the update rule at every iteration is easy to compute which makes the proposed method practical. We also provide numerous experiments to obtain more insights into the effect of truncation on the convergence to the true parameters in high dimensions.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"23 1","pages":"9260-9267"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82840151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Robust Feature Rectification of Pretrained Vision Models for Object Recognition 目标识别中预训练视觉模型的鲁棒特征校正

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i3.25492

Shengchao Zhou, Gaofeng Meng, Zhaoxiang Zhang, R. Xu, Shiming Xiang

{"title":"Robust Feature Rectification of Pretrained Vision Models for Object Recognition","authors":"Shengchao Zhou, Gaofeng Meng, Zhaoxiang Zhang, R. Xu, Shiming Xiang","doi":"10.1609/aaai.v37i3.25492","DOIUrl":"https://doi.org/10.1609/aaai.v37i3.25492","url":null,"abstract":"Pretrained vision models for object recognition often suffer a dramatic performance drop with degradations unseen during training. In this work, we propose a RObust FEature Rectification module (ROFER) to improve the performance of pretrained models against degradations. Specifically, ROFER first estimates the type and intensity of the degradation that corrupts the image features. Then, it leverages a Fully Convolutional Network (FCN) to rectify the features from the degradation by pulling them back to clear features. ROFER is a general-purpose module that can address various degradations simultaneously, including blur, noise, and low contrast. Besides, it can be plugged into pretrained models seamlessly to rectify the degraded features without retraining the whole model. Furthermore, ROFER can be easily extended to address composite degradations by adopting a beam search algorithm to find the composition order. Evaluations on CIFAR-10 and Tiny-ImageNet demonstrate that the accuracy of ROFER is 5% higher than that of SOTA methods on different degradations. With respect to composite degradations, ROFER improves the accuracy of a pretrained CNN by 10% and 6% on CIFAR-10 and Tiny-ImageNet respectively.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"1 1","pages":"3796-3804"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88948490","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Data Labeling for Machine Learning Engineers: Project-Based Curriculum and Data-Centric Competitions 机器学习工程师的数据标记:基于项目的课程和以数据为中心的竞赛

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i13.26886

Anastasia Zhdanovskaya, Daria Baidakova, Dmitry Ustalov

{"title":"Data Labeling for Machine Learning Engineers: Project-Based Curriculum and Data-Centric Competitions","authors":"Anastasia Zhdanovskaya, Daria Baidakova, Dmitry Ustalov","doi":"10.1609/aaai.v37i13.26886","DOIUrl":"https://doi.org/10.1609/aaai.v37i13.26886","url":null,"abstract":"The process of training and evaluating machine learning (ML) models relies on high-quality and timely annotated datasets. While a significant portion of academic and industrial research is focused on creating new ML methods, these communities rely on open datasets and benchmarks. However, practitioners often face issues with unlabeled and unavailable data specific to their domain. We believe that building scalable and sustainable processes for collecting data of high quality for ML is a complex skill that needs focused development. To fill the need for this competency, we created a semester course on Data Collection and Labeling for Machine Learning, integrated into a bachelor program that trains data analysts and ML engineers. The course design and delivery illustrate how to overcome the challenge of putting university students with a theoretical background in mathematics, computer science, and physics through a program that is substantially different from their educational habits. Our goal was to motivate students to focus on practicing and mastering a skill that was considered unnecessary to their work. We created a system of inverse ML competitions that showed the students how high-quality and relevant data affect their work with ML models, and their mindset changed completely in the end. Project-based learning with increasing complexity of conditions at each stage helped to raise the satisfaction index of students accustomed to difficult challenges. During the course, our invited industry practitioners drew on their first-hand experience with data, which helped us avoid overtheorizing and made the course highly applicable to the students’ future career paths.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"110 1","pages":"15886-15893"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80561638","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Centerless Multi-View K-means Based on the Adjacency Matrix 基于邻接矩阵的无心多视图k均值

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i7.26075

Han Lu, Quanxue Gao, Qianqian Wang, Ming Yang, Wei Xia

{"title":"Centerless Multi-View K-means Based on the Adjacency Matrix","authors":"Han Lu, Quanxue Gao, Qianqian Wang, Ming Yang, Wei Xia","doi":"10.1609/aaai.v37i7.26075","DOIUrl":"https://doi.org/10.1609/aaai.v37i7.26075","url":null,"abstract":"Although K-Means clustering has been widely studied due to its simplicity, these methods still have the following fatal drawbacks. Firstly, they need to initialize the cluster centers, which causes unstable clustering performance. Secondly, they have poor performance on non-Gaussian datasets. Inspired by the affinity matrix, we propose a novel multi-view K-Means based on the adjacency matrix. It maps the affinity matrix to the distance matrix according to the principle that every sample has a small distance from the points in its neighborhood and a large distance from the points outside of the neighborhood. Moreover, this method well exploits the complementary information embedded in different views by minimizing the tensor Schatten p-norm regularize on the third-order tensor which consists of cluster assignment matrices of different views. Additionally, this method avoids initializing cluster centroids to obtain stable performance. And there is no need to compute the means of clusters so that our model is not sensitive to outliers. Experiment on a toy dataset shows the excellent performance on non-Gaussian datasets. And other experiments on several benchmark datasets demonstrate the superiority of our proposed method.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"99 1","pages":"8949-8956"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80570097","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Long Legal Article Question Answering via Cascaded Key Segment Learning (Student Abstract) 基于级联关键段学习的法律长文问答(学生摘要)

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i13.27042

Shugui Xie, Lin Li, Jingling Yuan, Qing Xie, Xiaohui Tao

引用次数: 1

Human-in-the-Loop Vehicle ReID 人在环车辆ReID

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i5.25747

Zepeng Li, DongXiang Zhang, Yanyan Shen, Gang Chen

{"title":"Human-in-the-Loop Vehicle ReID","authors":"Zepeng Li, DongXiang Zhang, Yanyan Shen, Gang Chen","doi":"10.1609/aaai.v37i5.25747","DOIUrl":"https://doi.org/10.1609/aaai.v37i5.25747","url":null,"abstract":"Vehicle ReID has been an active topic in computer vision, with a substantial number of deep neural models proposed as end-to-end solutions. In this paper, we solve the problem from a new perspective and present an interesting variant called human-in-the-loop vehicle ReID to leverage interactive (and possibly wrong) human feedback signal for performance enhancement. Such human-machine cooperation mode is orthogonal to existing ReID models. To avoid incremental training overhead, we propose an Interaction ReID Network (IRIN) that can directly accept the feedback signal as an input and adjust the embedding of query image in an online fashion. IRIN is offline trained by simulating the human interaction process, with multiple optimization strategies to fully exploit the feedback signal. Experimental results show that even by interacting with flawed feedback generated by non-experts, IRIN still outperforms state-of-the-art ReID models by a considerable margin. If the feedback contains no false positive, IRIN boosts the mAP in Veri776 from 81.6% to 95.2% with only 5 rounds of interaction per query image.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"39 1","pages":"6048-6055"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83267309","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Feature Normalization and Cartography-Based Demonstrations for Prompt-Based Fine-Tuning on Emotion-Related Tasks 特征归一化和基于地图的基于提示的情绪相关任务微调演示

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i11.26514

Mahshid Hosseini, Cornelia Caragea

{"title":"Feature Normalization and Cartography-Based Demonstrations for Prompt-Based Fine-Tuning on Emotion-Related Tasks","authors":"Mahshid Hosseini, Cornelia Caragea","doi":"10.1609/aaai.v37i11.26514","DOIUrl":"https://doi.org/10.1609/aaai.v37i11.26514","url":null,"abstract":"To train a model in a traditional supervised learning classification system for natural language processing (NLP) tasks, it is essential to have labeled data, which is not present in large amounts for many tasks. Prompt-based learning methods attempt to combat the supervised learning need for labeled data by directly adapting pre-trained language models and modeling the probability of text itself. In this paper, we propose a novel data-agnostic strategy for prompt-based fine-tuning that leverages feature moments (a.k.a., mean and standard deviation) as a data augmentation technique and employs training dynamics (i.e., confidence and variability) to allow more informative samples to be concatenated for generating demonstrations as input context. Our approach is a strong method for few-shot learning that forces the language model to pay special attention to the feature moments and allows more informative samples to be concatenated for generating demonstrations as input context by selecting high confidence and low variance samples. To demonstrate its effectiveness given limited training data, we conduct extensive experiments in different few-shot settings on three empathy and emotion classification datasets (from various domains). We further evaluate our method's robustness by introducing noise to our few-shot input data and labels and show that exchanging moments between samples and incorporating cartography-based demonstrations are beneficial when the available data is limited and noisy.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"1 1","pages":"12881-12889"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83396320","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Category-Guided Visual Question Generation (Student Abstract) 类别导向的可视化问题生成(学生摘要)

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i13.26991

Hongfei Liu, Jiali Chen, Wenhao Fang, Jiayuan Xie, Yi Cai

引用次数: 1

Action-Conditioned Generation of Bimanual Object Manipulation Sequences 动作条件下的双手对象操作序列生成

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i2.25308

Haziq Razali, Y. Demiris

{"title":"Action-Conditioned Generation of Bimanual Object Manipulation Sequences","authors":"Haziq Razali, Y. Demiris","doi":"10.1609/aaai.v37i2.25308","DOIUrl":"https://doi.org/10.1609/aaai.v37i2.25308","url":null,"abstract":"The generation of bimanual object manipulation sequences given a semantic action label has broad applications in collaborative robots or augmented reality. This relatively new problem differs from existing works that generate whole-body motions without any object interaction as it now requires the model to additionally learn the spatio-temporal relationship that exists between the human joints and object motion given said label. To tackle this task, we leverage the varying degree each muscle or joint is involved during object manipulation. For instance, the wrists act as the prime movers for the objects while the finger joints are angled to provide a firm grip. The remaining body joints are the least involved in that they are positioned as naturally and comfortably as possible. We thus design an architecture that comprises 3 main components: (i) a graph recurrent network that generates the wrist and object motion, (ii) an attention-based recurrent network that estimates the required finger joint angles given the graph configuration, and (iii) a recurrent network that reconstructs the body pose given the locations of the wrist. We evaluate our approach on the KIT Motion Capture and KIT RGBD Bimanual Manipulation datasets and show improvements over a simplified approach that treats the entire body as a single entity, and existing whole-body-only methods.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"27 3 1","pages":"2146-2154"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83528056","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Progressive Few-Shot Adaptation of Generative Model with Align-Free Spatial Correlation 无对齐空间相关生成模型的渐进式少镜头自适应

Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence Pub Date : 2023-06-26 DOI: 10.1609/aaai.v37i2.25283

J. Moon, Hyunjun Kim, Jae-Pil Heo

{"title":"Progressive Few-Shot Adaptation of Generative Model with Align-Free Spatial Correlation","authors":"J. Moon, Hyunjun Kim, Jae-Pil Heo","doi":"10.1609/aaai.v37i2.25283","DOIUrl":"https://doi.org/10.1609/aaai.v37i2.25283","url":null,"abstract":"In few-shot generative model adaptation, the model for target domain is prone to the mode-collapse. Recent studies attempted to mitigate the problem by matching the relationship among samples generated from the same latent codes in source and target domains. The objective is further extended to image patch-level to transfer the spatial correlation within an instance. However, the patch-level approach assumes the consistency of spatial structure between source and target domains. For example, the positions of eyes in two domains are almost identical. Thus, it can bring visual artifacts if source and target domain images are not nicely aligned. In this paper, we propose a few-shot generative model adaptation method free from such assumption, based on a motivation that generative models are progressively adapting from the source domain to the target domain. Such progressive changes allow us to identify semantically coherent image regions between instances generated by models at a neighboring training iteration to consider the spatial correlation. We also propose an importance-based patch selection strategy to reduce the complexity of patch-level correlation matching. Our method shows the state-of-the-art few-shot domain adaptation performance in the qualitative and quantitative evaluations.","PeriodicalId":74506,"journal":{"name":"Proceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence","volume":"71 1","pages":"1923-1930"},"PeriodicalIF":0.0,"publicationDate":"2023-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80867749","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1