A Deep Learning Object Detection Method for an Efficient Clusters Initialization
Univ. Bourgogne Franche-Comté (UBFC)（勃艮第-弗朗什-孔泰大学（UBFC））；FEMTO-ST Institute（FEMTO-ST研究院）；American University of Beirut（贝鲁特美国大学）；University of Bejaia（贝贾亚大学）
Raphaël Couturier, Hassan N. Noura, Ola Salman, Abderrahmane Sider
Clustering is an unsupervised machine learning method grouping data samples into clusters of similar objects. In practice, clustering has been used in numerous applications such as banking customers profiling, document retrieval, image segmentation, and e-commerce recommendation engines. However, the existing clustering techniques present significant limitations, from which is the dependability of their stability on the initialization parameters (e.g. number of clusters, centroids). Different solutions were presented in the literature to overcome this limitation (i.e. internal and external validation metrics). However, these solutions require high computational complexity and memory consumption, especially when dealing with big data. In this paper, we apply the recent object detection Deep Learning (DL) model, named YOLO-v5, to detect the initial clustering parameters such as the number of clusters with their sizes and centroids. Mainly, the proposed solution consists of adding a DL-based initialization phase making the clustering algorithms free of initialization. Two model solutions are provided in this work, one for isolated clusters and the other one for overlapping clusters. The features of the incoming dataset determine which model to use. Moreover, The results show that the proposed solution can provide near-optimal clusters initialization parameters with low computational and resources overhead compared to existing solutions.
Image segmentation is an essential component in many image processing and computer vision tasks. The primary goal of image segmentation is to simplify an image for easier analysis, and there are two broad approaches for achieving this: edge based methods, which extract the boundaries of specific known objects, and region based methods, which partition the image into regions that are statistically homogeneous. One of the more prominent edge finding methods, known as the level set method, evolves a zero-level contour in the image plane with gradient descent until the contour has converged to the…
Object detection is a central downstream task used to test if pre-trained network parameters confer benefits, such as improved accuracy or training speed. The complexity of object detection methods can make this benchmarking non-trivial when new architectures, such as Vision Transformer (ViT) models, arrive. These difficulties (e.g., architectural incompatibility, slow training, high memory consumption, unknown training formulae, etc.) have prevented recent studies from benchmarking detection transfer learning with standard ViT models. In this paper, we present training techniques that overcom…
Australian National University（澳大利亚国立大学）；Australian Centre for Robotic Vision（澳大利亚机器人视觉中心）；Data61, CSIRO（澳大利亚联邦科学与工业研究组织Data61）
Although deep learning greatly improves the performance of semantic segmentation, its success mainly lies in object central areas without accurate edges. As superpixels are a popular and effective auxiliary to preserve object edges, in this paper, we jointly learn semantic segmentation with trainable superpixels. We achieve it with fully-connected layers with Transparent Initialization (TI) and efficient logit consistency using a sparse encoder. The proposed TI preserves the effects of learned parameters of pretrained networks. This avoids a significant increase of the loss of pretrained netwo…
Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Weakly supervised object detection (WSOD) focuses on training object detector with only image-level annotations, and is challenging due to the gap between the supervision and the objective. Most of existing approaches model WSOD as a multiple instance learning (MIL) problem. However, we observe that the result of MIL based detector is unstable, i.e., the most confident bounding boxes change significantly when using different initializations. We quantitatively demonstrate the instability by introducing a metric to measure it, and empirically analyze the reason of instability. Although the insta…
Understanding how cities visually differ from each others is interesting for planners, residents, and historians. We investigate the interpretation of deep features learned by convolutional neural networks (CNNs) for city recognition. Given a trained city recognition network, we first generate weighted masks using the known Grad-CAM technique and to select the most discriminate regions in the image. Since the image classification label is the city name, it contains no information of objects that are class-discriminate, we investigate the interpretability of deep representations with two method…
The ImageNet pre-training initialization is the de-facto standard for object detection. He et al. found it is possible to train detector from scratch(random initialization) while needing a longer training schedule with proper normalization technique. In this paper, we explore to directly pre-training on target dataset for object detection. Under this situation, we discover that the widely adopted large resizing strategy e.g. resize image to (1333, 800) is important for fine-tuning but it's not necessary for pre-training. Specifically, we propose a new training pipeline for object detection tha…
Convolutional Neural Networks spread through computer vision like a wildfire, impacting almost all visual tasks imaginable. Despite this, few researchers dare to train their models from scratch. Most work builds on one of a handful of ImageNet pre-trained models, and fine-tunes or adapts these for specific tasks. This is in large part due to the difficulty of properly initializing these networks from scratch. A small miscalibration of the initial weights leads to vanishing or exploding gradients, as well as poor convergence properties. In this work we present a fast and simple data-dependent i…
Louisiana State University（路易斯安那州立大学）；Georgia Institute of Technology（佐治亚理工学院）
K-means is undoubtedly the most widely used partitional clustering algorithm. Unfortunately, due to its gradient descent nature, this algorithm is highly sensitive to the initial placement of the cluster centers. Numerous initialization methods have been proposed to address this problem. In this paper, we first present an overview of these methods with an emphasis on their computational efficiency. We then compare eight commonly used linear time complexity initialization methods on a large and diverse collection of data sets using various performance criteria. Finally, we analyze the experimen…
Louisiana State University（路易斯安那州立大学）；Georgia Institute of Technology（佐治亚理工学院）
K-means is undoubtedly the most widely used partitional clustering algorithm. Unfortunately, due to its gradient descent nature, this algorithm is highly sensitive to the initial placement of the cluster centers. Numerous initialization methods have been proposed to address this problem. Many of these methods, however, have superlinear complexity in the number of data points, making them impractical for large data sets. On the other hand, linear methods are often random and/or order-sensitive, which renders their results unrepeatable. Recently, Su and Dy proposed two highly successful hierarch…
Louisiana State University（路易斯安那州立大学）；Georgia Institute of Technology（佐治亚理工学院）
Over the past five decades, k-means has become the clustering algorithm of choice in many application domains primarily due to its simplicity, time/space efficiency, and invariance to the ordering of the data points. Unfortunately, the algorithm's sensitivity to the initial selection of the cluster centers remains to be its most serious drawback. Numerous initialization methods have been proposed to address this drawback. Many of these methods, however, have time complexity superlinear in the number of data points, which makes them impractical for large data sets. On the other hand, linear met…
We propose k^2-means, a new clustering method which efficiently copes with large numbers of clusters and achieves low energy solutions. k^2-means builds upon the standard k-means (Lloyd's algorithm) and combines a new strategy to accelerate the convergence with a new low time complexity divisive initialization. The accelerated convergence is achieved through only looking at k_n nearest clusters and using triangle inequality bounds in the assignment step while the divisive initialization employs an optimal 2-clustering along a direction. The worst-case time complexity per iteration of our k^2-m…
Scene background initialization allows the recovery of a clear image without foreground objects from a video sequence, which is generally the first step in many computer vision and video processing applications. The process may be strongly affected by some challenges such as illumination changes, foreground cluttering, intermittent movement, etc. In this paper, a robust background initialization approach based on superpixel motion detection is proposed. Both spatial and temporal characteristics of frames are adopted to effectively eliminate foreground objects. A subsequence with stable illumin…
Improving Learning of New Diseases through Knowledge-Enhanced Initialization for Federated Adapter Tuning
Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR)（高性能计算研究所（IHPC），科技研究局（A*STAR））；EVYD Technology（EVYD技术）
University of Technology Sydney（悉尼科技大学）；Southern University of Science and Technology（南方科技大学）；University of Birmingham（伯明翰大学）
The K-means algorithm is a widely used clustering algorithm that offers simplicity and efficiency. However, the traditional K-means algorithm uses the random method to determine the initial cluster centers, which make clustering results prone to local optima and then result in worse clustering performance. Many initialization methods have been proposed, but none of them can dynamically adapt to datasets with various characteristics. In our previous research, an initialization method for K-means based on hybrid distance was proposed, and this algorithm can adapt to datasets with different chara…
Institute of Applied Mathematics, AMSS, Chinese Academy of Sciences（中国科学院数学与系统科学研究院应用数学研究所）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
The $k$-means clustering algorithm is popular but has the following main drawbacks: 1) the number of clusters, $k$, needs to be provided by the user in advance, 2) it can easily reach local minima with randomly selected initial centers, 3) it is sensitive to outliers, and 4) it can only deal with well separated hyperspherical clusters. In this paper, we propose a Local Density Peaks Searching (LDPS) initialization framework to address these issues. The LDPS framework includes two basic components: one of them is the local density that characterizes the density distribution of a data set, and t…
Slot Attention with Re-Initialization and Self-Distillation
Department of Electrical Engineering and Automation（电气工程与自动化系）；Aalto University（阿尔托大学）；Department of Computer Science（计算机科学系）；Center for Machine Vision and Signal Analysis（机器视觉与信号分析中心）；University of Oulu（奥卢大学）
本文提出 DIAS 方法，通过槽重初始化和自蒸馏减少冗余槽，提升对象为中心学习的对象发现与识别性能。
Active contour models based on local region fitting energy can segment images with intensity inhomogeneity effectively, but their segmentation results are easy to error if the initial contour is inappropriate. In this paper, we present a simple and universal method of improving the robustness of initial contour for these local fitting-based models. The core idea of proposed method is exchanging the fitting values on the two sides of contour, so that the fitting values inside the contour are always larger (or smaller) than the values outside the contour in the process of curve evolution. In thi…
School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；Yam Pak Charitable Foundation School of Computing and Information Sciences, Saint Francis University（圣弗朗西斯大学计算与信息科学学院（严炳慈善基金会冠名））；Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系）
We consider the problem of consistently matching multiple sets of elements to each other, which is a common task in fields such as computer vision. To solve the underlying NP-hard objective, existing methods often relax or approximate it, but end up with unsatisfying empirical performance due to a misaligned objective. We propose a coordinate update algorithm that directly optimizes the target objective. By using pairwise alignment information to build an undirected graph and initializing the permutation matrices along the edges of its Maximum Spanning Tree, our algorithm successfully avoids b…
One Patient's Annotation is Another One's Initialization: Towards Zero-Shot Surgical Video Segmentation with Cross-Patient Initialization
Center for Biosystems and Biotech Data Science, Ghent University（根特大学生物系统与生物技术数据科学中心）；Ghent University Global Campus（根特大学全球校区）；Ghent University Hospital（根特大学医院）；Department of Human Structure and Repair, Ghent University（根特大学人类结构与修复系）；Department of HPB Surgery & Liver Transplantation, Ghent University Hospital（根特大学医院肝胆胰外科与肝移植科）；Department of Applied Mathematics, Computer Science and Statistics, Ghent University（根特大学应用数学、计算机科学与统计系）
Chongqing University（重庆大学）；Rice University（莱斯大学）；University of Electronic Science and Technology of China（电子科技大学）；The Chinese University of Hong Kong-Shenzhen（香港中文大学（深圳））
The K-means algorithm is arguably the most popular data clustering method, commonly applied to processed datasets in some "feature spaces", as is in spectral clustering. Highly sensitive to initializations, however, K-means encounters a scalability bottleneck with respect to the number of clusters K as this number grows in big data applications. In this work, we promote a closely related model called K-indicators model and construct an efficient, semi-convex-relaxation algorithm that requires no randomized initializations. We present extensive empirical results to show advantages of the new al…
The Ohio State University（俄亥俄州立大学）；University of Georgia（佐治亚大学）
A fundamental problem in computer vision is boundary estimation, where the goal is to delineate the boundary of objects in an image. In this paper, we propose a method which jointly incorporates geometric and topological information within an image to simultaneously estimate boundaries for objects within images with more complex topologies. We use a topological clustering-based method to assist initialization of the Bayesian active contour model. This combines pixel clustering, boundary smoothness, and potential prior shape information to produce an estimated object boundary. Active contour me…
University of Oxford（牛津大学）；NAVER LABS Europe（NAVER欧洲实验室）；The Alan Turing Institute（艾伦·图灵研究所）；Five AI Limited（Five AI有限公司）
Recent studies have shown that skeletonization (pruning parameters) of networks \textit{at initialization} provides all the practical benefits of sparsity both at inference and training time, while only marginally degrading their performance. However, we observe that beyond a certain level of sparsity (approx $95\%$), these approaches fail to preserve the network performance, and to our surprise, in many cases perform even worse than trivial random pruning. To this end, we propose an objective to find a skeletonized network with maximum {\em foresight connection sensitivity} (FORCE) whereby th…
It is often desirable to capture and map semantic information of an environment during simultaneous localization and mapping (SLAM). Such semantic information can enable a robot to better distinguish places with similar low-level geometric and visual features and perform high-level tasks that use semantic information about objects to be manipulated and environments to be navigated. While semantic SLAM has gained increasing attention, there is little research on semanticlevel data association based on semantic objects, i.e., object-level data association. In this paper, we propose a novel objec…
IRSTEA（法国国家环境与农业科技研究院）；UMR TETIS（TETIS联合研究单位）；LIRMM（蒙彼利埃计算机科学与机器人实验室）；Univ. of Montpellier（蒙彼利埃大学）；CIRAD（法国国际农业发展研究中心）
Recurrent Neural Networks (RNNs) can be seriously impacted by the initial parameters assignment, which may result in poor generalization performances on new unseen data. With the objective to tackle this crucial issue, in the context of RNN based classification, we propose a new supervised layer-wise pretraining strategy to initialize network parameters. The proposed approach leverages a data-aware strategy that sets up a taxonomy of classification problems automatically derived by the model behavior. To the best of our knowledge, despite the great interest in RNN-based classification, this is…
Track Initialization and Re-Identification for~3D Multi-View Multi-Object Tracking
GIST（光州科学技术院）；School of Electrical Engineering and Computer Science at GIST（光州科学技术院电气工程与计算机科学学院）；School of Electrical Engineering, Computing and Mathematical Sciences, Curtin University（科廷大学电气、计算与数学科学学院）；LIG Nex1（LIG Nex1公司）
Portland State University（波特兰州立大学）；University of Pennsylvania（宾夕法尼亚大学）；University of California, Berkeley（加州大学伯克利分校）；University of Michigan（密歇根大学）
Subspace clustering is the unsupervised grouping of points lying near a union of low-dimensional linear subspaces. Algorithms based directly on geometric properties of such data tend to either provide poor empirical performance, lack theoretical guarantees, or depend heavily on their initialization. We present a novel geometric approach to the subspace clustering problem that leverages ensembles of the K-subspaces (KSS) algorithm via the evidence accumulation clustering framework. Our algorithm, referred to as ensemble K-subspaces (EKSS), forms a co-association matrix whose (i,j)th entry is th…
Procedural Core: A Compact Recurrent Initialization for Vision Transformers
Australian Institute for Machine Learning (AIML), Adelaide University（阿德莱德大学澳大利亚机器学习研究所）；Bielefeld University（比勒费尔德大学）；Metacognition AI；Idiap Research Institute（Idiap 研究所）
