Object detection is a fundamental task in computer vision, consisting of both classification and localization tasks. Previous works mostly perform classification and localization with shared feature extractor like Con...
详细信息
Object detection is a fundamental task in computer vision, consisting of both classification and localization tasks. Previous works mostly perform classification and localization with shared feature extractor like Convolution Neural Network. However, the tasks of classification and localization exhibit different sensitivities with regard to the same feature, hence the "task spatial misalignment" issue. This issue can result in a hedge issue between the performances of localizer and classifier. To address these issues, we first propose a novel Dynamic Coefficient Loss to simultaneously consider and balance the performances of classification and localization tasks. To well address anchor label misjudgment issue in irregular- shaped object detection, we define a new classification-aware IoU metric to assign anchors intelligently. Finally, we further introduce the localization factor into NMS by proposing a Classification-Localization balanced NMS. Extensive experiments on MS COCO and PASCAL VOC demonstrate that our proposals can improve RetinaNet by around 1.5% AP with various backbones.
Offline model-based optimization (MBO) aims to identify a design that maximizes a black-box function using only a fixed, pre-collected dataset of designs and their corresponding scores. This problem has garnered signi...
详细信息
Offline model-based optimization (MBO) aims to identify a design that maximizes a black-box function using only a fixed, pre-collected dataset of designs and their corresponding scores. This problem has garnered significant attention from both scientific and industrial domains. A common approach in offline MBO is to train a regression-based surrogate model by minimizing mean squared error (MSE) and then find the best design within this surrogate model by different optimizers (e.g., gradient ascent). However, a critical challenge is the risk of out-of-distribution errors, i.e., the surrogate model may typically overestimate the scores and mislead the optimizers into suboptimal regions. Prior works have attempted to address this issue in various ways, such as using regularization techniques and ensemble learning to enhance the robustness of the model, but it still remains. In this paper, we argue that regression models trained with MSE are not well-aligned with the primary goal of offline MBO, which is to select promising designs rather than to predict their scores precisely. Notably, if a surrogate model can maintain the order of candidate designs based on their relative score relationships, it can produce the best designs even without precise predictions. To validate it, we conduct experiments to compare the relationship between the quality of the final designs and MSE, finding that the correlation is really very weak. In contrast, a metric that measures order-maintaining quality shows a significantly stronger correlation. Based on this observation, we propose learning a ranking-based model that leverages learning to rank techniques to prioritize promising designs based on their relative scores. We show that the generalization error on ranking loss can be well bounded. Empirical results across diverse tasks demonstrate the superior performance of our proposed ranking-based method than twenty existing methods. Our implementation is available at https://***/lam
Deep multiple instance learning (MIL) has attracted considerable attention in medical image analysis, since it only requires image-level labels for model training without using fine-grained (or patch) annotations. Unf...
详细信息
ISBN:
(数字)9798350386226
ISBN:
(纸本)9798350386233
Deep multiple instance learning (MIL) has attracted considerable attention in medical image analysis, since it only requires image-level labels for model training without using fine-grained (or patch) annotations. Unfortunately, MIL-based methods might lose some significant patch features. Although pseudo-label-based methods, which assign a pre-defined label to each patch, can explore more patch-level features, they might bring label noise and make the patch-level features lose diversity, thereby possibly restricting the model performance. To overcome this issue, we propose a novel gradient-based patch target generation (PTG) module to dynamically produce a feature vector for each patch as its target. Additionally, based on the PTG module, we propose a patch-target guided dual-branch deep MIL framework for 3D MRI data analysis, where both the two branches consist of a CNN model to extract patch-level features, an attention module to interpret the significance of patches, and a bag-level classifier, while the second branch also contains the PTG module to generate patch targets of patches. Moreover, the two branches are alternatively updated in our framework, resulting in a bi-level optimization problem, and thus we design a bi-level optimization algorithm to solve our proposed objective function. Extensive experiments demonstrate the superior classification and interpretation performance of the proposed framework over recent state-of-the-art methods. Codes are available at https://***/daimz1213/mil2024.
Multi-Object Tracking (MOT) presents promising applications in intelligent sports event analysis. Existing models primarily cater to pedestrian-dominant scenarios with fixed camera placements and linear motion traject...
详细信息
Personalized recommendation algorithms,which are effective means to solve information overload,are popular topics in current *** this paper,a recommender system combining popularity and novelty(RSCPN)based on one-mode...
详细信息
Personalized recommendation algorithms,which are effective means to solve information overload,are popular topics in current *** this paper,a recommender system combining popularity and novelty(RSCPN)based on one-mode projection of weighted bipartite network is *** edge between a user and item is weighted with the item’s rating,and we consider the difference in the ratings of different users for an item to obtain a reasonable method of measuring the similarity between *** can be used in the same model for popularity and novelty recommendation by setting different parameter values and analyzing how a change in parameters affects the popularity and novelty of the recommender *** verify and compare the accuracy,diversity and novelty of the proposed model with those of other models,and results show that RSCPN is feasible.
Credit Scoring takes a prominent part in the finance of small and medium-sized enterprises (SMEs), and it is also an invaluable tool to predict credit default. However, due to the variety of market size, capital scale...
详细信息
China has the largest number of lung cancer cases worldwide,and the heavy burden of lung cancer in China will grow substantially with the rapid aging of the *** number of lung cancer deaths in China almost tripled fro...
详细信息
China has the largest number of lung cancer cases worldwide,and the heavy burden of lung cancer in China will grow substantially with the rapid aging of the *** number of lung cancer deaths in China almost tripled from 1990 to ***,novel strategies targeting the risk factors ignored by clinicians are warranted to conquer the increase in the lung cancer *** fine particulate matter(PM_(2.5))has been recognized as a first-class carcinogen;more than half of the PM_(2.5)-attributable lung cancer deaths occur in China[1].
The imbalanced data classification problem has aroused lots of concerns from both academia and industry since data imbalance is a widespread phenomenon in many real-world scenarios. Although this problem has been well...
详细信息
ISBN:
(数字)9798350317152
ISBN:
(纸本)9798350317169
The imbalanced data classification problem has aroused lots of concerns from both academia and industry since data imbalance is a widespread phenomenon in many real-world scenarios. Although this problem has been well researched from the view of imbalanced class samples, we further argue that graph neural networks (GNNs) expose a unique source of imbalance from the influenced nodes of different classes of labeled nodes, i.e., labeled nodes are imbalanced in terms of the number of nodes they influenced during the influence propagation in GNNs. To tackle this previously unexplored influence-imbalance issue, we connect social influence maximization with the imbalanced node classification problem and propose balanced influence maximization (BIM). Specifically, BIM greedily assigns the pseudo label to the node which can maximize the number of influenced nodes in GNN training while making the influence of each class more balance. Experimental results on five public datasets demonstrate the effectiveness of our method in relieving the influence-imbalance issue. For example, when training a GCN with an imbalance ratio of 0.1, BIM significantly outperforms the most competitive baseline by 0.6% -9.8% in five public datasets in terms of the F1 score.
Deciding on an uncertain event may lead to risk. Uncertainty occurs due to the lack of knowledge of a particular event or a situation. The only way to avoid this is to analyze the Risk. The risk analyzed properly will...
详细信息
Crankpin is a mechanical part which links the crankshaft to the connecting rod to each cylinder. Normally, crankpins are made up of low carbon material which results in unexpected fracture on the crankpin material due...
详细信息
ISBN:
(数字)9798331529352
ISBN:
(纸本)9798331529390
Crankpin is a mechanical part which links the crankshaft to the connecting rod to each cylinder. Normally, crankpins are made up of low carbon material which results in unexpected fracture on the crankpin material due its chemical composition, high engine temperature, high operating oil temperature, improper lubrication and lower hardness. Recently, researchers are developing crankpins with different materials for the better performance such as alloy steel and the mild steel materials which have similar chemical compositions of low carbon material. The primary object of this study is to develop an improved crankpin which will alleviate the current crankpin used in the connecting rod. In this work we have selected 16MnCr5 as a replacement of the presently used crankpin in the connecting rod. 16MnCr5 is a low carbon steel widely used for several applications in many of the automobile industries. 16MnCr5 is hardened by a case hardening process which is carried out through the sealed quench furnace for the set of process parameters. The results of the prepared material were analyzed using hardness, microstructure examination and the economic conditions of the materials. In future, another set of two materials such as SCM420H and EN1A will be used for alternating material for crankpin which are processed with the same set of parameters and compared with the 16MnCr5 material to check the suitable crank pin material to avoid unexpected damage.
暂无评论