Feature Pool Research Articles

Cross vision transformer with enhanced Growth Optimizer for breast cancer detection in IoMT environment

The recent advances in artificial intelligence modern approaches can play vital roles in the Internet of Medical Things (IoMT). Automatic diagnosis is one of the most important topics in the IoMT, including cancer diagnosis. Breast cancer is one of the top causes of death among women. Accurate diagnosis and early detection of breast cancer can improve the survival rate of patients. Deep learning models have demonstrated outstanding potential in accurately detecting and diagnosing breast cancer. This paper proposes a novel technology for breast cancer detection using CrossViT as the deep learning model and an enhanced version of the Growth Optimizer algorithm (MGO) as the feature selection method. CrossVit is a hybrid deep learning model that combines the strengths of both convolutional neural networks (CNNs) and transformers. The MGO is a meta-heuristic algorithm that selects the most relevant features from a large pool of features to enhance the performance of the model. The developed approach was evaluated on three publicly available breast cancer datasets and achieved competitive performance compared to other state-of-the-art methods. The results show that the combination of CrossViT and the MGO can effectively identify the most informative features for breast cancer detection, potentially assisting clinicians in making accurate diagnoses and improving patient outcomes. The MGO algorithm improves accuracy by approximately 1.59% on INbreast, 5.00% on MIAS, and 0.79% on MiniDDSM compared to other methods on each respective dataset. The developed approach can also be utilized to improve the Quality of Service (QoS) in the healthcare system as a deployable IoT-based intelligent solution or a decision-making assistance service, enhancing the efficiency and precision of the diagnosis.

Hot rolled steel surface defect detection and classification using an automatic ensemble approach

This study introduces an ensemble-based Deep Neural Network (DNN) model for detecting defects on steel surfaces. The method suggested in this study classifies steel surface conditions into six possible fault categories, namely, crazing, inclusion, rolled in, pitted surface, scratches, and patches. The images undergo preprocessing and extraction of features in spatial and frequency domains using image segmentation techniques such as grey level difference method (GLDM), fast Fourier Transform (FFT), grey level co-occurrence matrix (GLCM), texture analysis and discrete wavelet transform (DWT). The ensembling of image features into a fused feature pool is carried out after the preprocessing of input images that are provided as input to a light-weight neural network model for training and testing. The performance of the model is comprehensively evaluated via an ablation study both before and after ensembling. In addition, the model capability is effectively analyzed using receiver operating characteristics (ROC) curve, confusion matrix from which classification accuracy of the model could be obtained and other parameters including precision and f1-score. It was observed that the proposed deep learning network presents phenomenally high accuracy of 99.72% for detection and classification of steel surface faults. This result was found to be superior when compared with the performance of the same neural network over each feature type individually. This study also compares the classification results of the model built based on the ensembled feature set with the results of various other classification approaches available in literature. The ensemble-based model could potentially be integrated into existing inspection systems for real-time, efficient and robust condition monitoring of steel surfaces.

Sparse deep encoded features with enhanced sinogramic red deer optimization for fault inspection in wafer maps

AbstractDue to the complexity and dynamics of the semiconductor manufacturing processes, wafer bin maps (WBM) present various defect patterns caused by various process faults. The defect type detection on wafer maps provides information about the process and equipment in which the defect occurred. Recently, automatic inspection has played a vital role in meeting the high-throughput demand, especially with deep convolutional neural networks (DCNN) which shows promising efficiency. At the same time, the need for a large amount of labeled and balanced datasets limits the performance of such approaches. In addition, complex DCNN in recognition tasks can provide redundant features that cause overfitting and reduce interpretability. In this paper, a new hybrid deep model for wafer map fault detection to get over these challenges is proposed. Firstly, a new convolutional autoencoder (CAE) is employed as a synthetization model to fix the high imbalance problem of the dataset. Secondly, for efficient dimensionality reduction, an embedding procedure is applied to the synthesized maps to get sparse encoded wafer maps by reinforcing a sparsity regularization in an encoder-decoder network to form a sparsity-boosted autoencoder (SBAE). The sparse embedding of wafer maps guarantees more discriminative features with 50% reduction in spatial size compared to the original wafer maps. Then, the 2D encoded sparse maps are converted to 1D sinograms to be fed later into another aggressive feature reduction stage using a new modified red deer algorithm with a new tinkering strategy. The resultant feature pool is reduced to ~ 25 1D feature bases, i.e., ~ 1.5% of the initial size of the 2D wafer maps. Finally, for the prediction stage, a simple 1DCNN model is introduced. The proposed inspection model is tested via different experiments on real-world wafer map dataset (WM-811K). Compared to state-of-the-art techniques, the proposed model outperforms their performance even with small-sized 1D feature pool. The average testing accuracy are 98.77% and 98.8% for 9 and 8 types of faults, respectively.

Cascaded maximum median-margin discriminant projection with its application to face recognition

This paper introduces a novel method called cascaded maximum median-margin discriminant projection (CMMDP) for robust face recognition. Initially, we introduce the maximum median-margin discriminant projection (MMDP) method, which aims to maximize the distances between class medians and their inter-class neighbors, while simultaneously minimizing the distances between class medians and their intra-class samples. To extract features at multiple levels, we extend the MMDP method to its deep version, known as CMMDP. The CMMDP algorithm incorporates the MMDP technique to learn multistage filter banks specifically designed for facial images. Afterward, we utilize straightforward binary hashing techniques for efficient indexing, along with block histograms for effective feature pooling. The CMMDP model is simple and easy to train, while taking full account of the global and local structure of the samples by maximizing the distances between samples that are dissimilar and minimizing the distances between samples that are similar after projection. This results in a low-dimensional data representation with better discriminative performance. We evaluate the performance of CMMDP on face datasets including AR, ORL, ExtYaleB and CMU PIE databases. The results indicate that CMMDP achieves superior performance than most advanced methods.

An attention mechanism module with spatial perception and channel information interaction

In the field of deep learning, the attention mechanism, as a technology that mimics human perception and attention processes, has made remarkable achievements. The current methods combine a channel attention mechanism and a spatial attention mechanism in a parallel or cascaded manner to enhance the model representational competence, but they do not fully consider the interaction between spatial and channel information. This paper proposes a method in which a space embedded channel module and a channel embedded space module are cascaded to enhance the model’s representational competence. First, in the space embedded channel module, to enhance the representational competence of the region of interest in different spatial dimensions, the input tensor is split into horizontal and vertical branches according to spatial dimensions to alleviate the loss of position information when performing 2D pooling. To smoothly process the features and highlight the local features, four branches are obtained through global maximum and average pooling, and the features are aggregated by different pooling methods to obtain two feature tensors with different pooling methods. To enable the output horizontal and vertical feature tensors to focus on different pooling features simultaneously, the two feature tensors are segmented and dimensionally transposed according to spatial dimensions, and the features are later aggregated along the spatial direction. Then, in the channel embedded space module, for the problem of no cross-channel connection between groups in grouped convolution and for which the parameters are large, this paper uses adaptive grouped banded matrices. Based on the banded matrices utilizing the mapping relationship that exists between the number of channels and the size of the convolution kernels, the convolution kernel size is adaptively computed to achieve adaptive cross-channel interaction, enhancing the correlation between the channel dimensions while ensuring that the spatial dimensions remain unchanged. Finally, the output horizontal and vertical weights are used as attention weights. In the experiment, the attention mechanism module proposed in this paper is embedded into the MobileNetV2 and ResNet networks at different depths, and extensive experiments are conducted on the CIFAR-10, CIFAR-100 and STL-10 datasets. The results show that the method in this paper captures and utilizes the features of the input data more effectively than the other methods, significantly improving the classification accuracy. Despite the introduction of an additional computational burden (0.5 M), however, the overall performance of the model still achieves the best results when the computational overhead is comprehensively considered.

A Neoteric Feature Extraction Technique to Predict the Survival of Gastric Cancer Patients.

At the time of cancer diagnosis, it is crucial to accurately classify malignant gastric tumors and the possibility that patients will survive. This study aims to investigate the feasibility of identifying and applying a new feature extraction technique to predict the survival of gastric cancer patients. A retrospective dataset including the computed tomography (CT) images of 135 patients was assembled. Among them, 68 patients survived longer than three years. Several sets of radiomics features were extracted and were incorporated into a machine learning model, and their classification performance was characterized. To improve the classification performance, we further extracted another 27 texture and roughness parameters with 2484 superficial and spatial features to propose a new feature pool. This new feature set was added into the machine learning model and its performance was analyzed. To determine the best model for our experiment, Random Forest (RF) classifier, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Naïve Bayes (NB) (four of the most popular machine learning models) were utilized. The models were trained and tested using the five-fold cross-validation method. Using the area under ROC curve (AUC) as an evaluation index, the model that was generated using the new feature pool yields AUC = 0.98 ± 0.01, which was significantly higher than the models created using the traditional radiomics feature set (p < 0.04). RF classifier performed better than the other machine learning models. This study demonstrated that although radiomics features produced good classification performance, creating new feature sets significantly improved the model performance.

RVS-FDSC: A retinal vessel segmentation method with four-directional strip convolution to enhance feature extraction

Retinal vessel segmentation is important to assist ophthalmologists in the diagnosis and treatment of ophthalmic diseases. However, traditional convolutional neural networks (CNNs) are constrained by using square convolution kernels for retinal vessel feature extraction, thereby overlooking the structural characteristics of retinal vessels, which to some extent limits model performance. Consequently, we propose a retinal vessel segmentation method with four-directional strip convolution to enhance feature extraction (RVS-FDSC). Firstly, due to the shape structure of retinal vessels which have branching paths and appear locally as strips, we have constructed a residual strip convolution (RSC) module by using strip convolutions in four different directions: horizontal, vertical, antidiagonal, and main diagonal. These four directions can roughly simulate the branching directions of vessels, making it possible to better extract vessel features. Furthermore, to more comprehensively understand and utilize both local details and global context, RVS-FDSC introduces a multi-scale pooling feature fusion (MSPF2) module. Finally, to better focus on important features and reduce the attention to unimportant or redundant information, RVS-FDSC introduces a residual parallel dual attention (RPDA) module. We conduct experiments on three retinal vessel segmentation datasets: DRIVE, CHASE-DB1, and STARE. RVS-FDSC achieves excellent results on these three public datasets, with AUC of 0.9856, 0.9867, and 0.9808, Acc of 0.9692, 0.9743, and 0.9718, and Spe of 0.9878, 0.9856 and 0.9882, respectively. These results indicate the superior performance of RVS-FDSC compared to other state-of-the-art methods.

Research on Human Pose Estimation Model Based on Long-Range Fine-Grained Modeling

To address the issues of lacking long-range spatial position learning ability and excessive loss of fine-grained feature information during spatial feature pooling in human pose estimation models, a novel human pose estimation model based on the Yolopose network is proposed. Firstly, an enhanced coordinate attention module is introduced and embedded into the backbone network to endow the model with long-range spatial position modeling capability. Secondly, a fine-grained cascaded spatial pyramid pooling module is proposed to mitigate the loss of fine-grained feature information caused by spatial feature pooling. Finally, an implicit knowledge learning module is incorporated to reduce the model parameter count and enhance the model's capability for multi-task joint optimization.

Multi-visual modality micro drone-based structural damage detection

Accurate detection and resilience of object detectors in structural damage detection are important in ensuring the continuous use of civil infrastructure. However, achieving robustness in object detectors remains a persistent challenge, impacting their ability to generalize effectively. This study proposes DetectorX, a robust framework for structural damage detection coupled with a micro drone. DetectorX addresses the challenges of object detector robustness by incorporating two innovative modules: a stem block and a spiral pooling technique. The stem block introduces a dynamic visual modality by leveraging the outputs of two Deep Convolutional Neural Network (DCNN) models. The framework employs the proposed event-based reward reinforcement learning to constrain the actions of a parent and child DCNN model leading to a reward. This results in the induction of two dynamic visual modalities alongside the Red, Green, and Blue (RGB) data. This enhancement significantly augments DetectorX's perception and adaptability in diverse environmental situations. Further, a spiral pooling technique, an online image augmentation method, strengthens the framework by increasing feature representations by concatenating spiraled and average/max pooled features. In three extensive experiments: (1) comparative and (2) robustness, which use the Pacific Earthquake Engineering Research Hub ImageNet dataset, and (3) field-experiment, DetectorX performed satisfactorily across varying metrics, including precision (0.88), recall (0.84), average precision (0.91), mean average precision (0.76), and mean average recall (0.73), compared to the competing detectors including You Only Look Once X-medium (YOLOX-m) and others. The study's findings indicate that DetectorX can provide satisfactory results and demonstrate resilience in challenging environments.

High-Efficiency and High-Precision Ship Detection Algorithm Based on Improved YOLOv8n

With the development of the intelligent vision industry, ship detection and identification technology has gradually become a research hotspot in the field of marine insurance and port logistics. However, due to the interference of rain, haze, waves, light, and other bad weather, the robustness and effectiveness of existing detection algorithms remain a continuous challenge. For this reason, an improved YOLOv8n algorithm is proposed for the detection of ship targets under unforeseen environmental conditions. In the proposed method, the efficient multi-scale attention module (C2f_EMAM) is introduced to integrate the context information of different scales so that the convolutional neural network can generate better pixel-level attention to high-level feature maps. In addition, a fully-concatenate bi-directional feature pyramid network (Concatenate_FBiFPN) is adopted to replace the simple superposition/addition of feature map, which can better solve the problem of feature propagation and information flow in target detection. An improved spatial pyramid pooling fast structure (SPPF2+1) is also designed to emphasize low-level pooling features and reduce the pooling depth to accommodate the information characteristics of the ship. A comparison experiment was conducted between other mainstream methods and our proposed algorithm. Results showed that our proposed algorithm outperformed other models by achieving 99.4% of accuracy, 98.2% of precision, 98.5% of recall, 99.1% of mAP@.5, and 85.4% of mAP@.5:.95 on the SeaShips dataset.

Diverse Feature-Level Guidance Adjustments for Unsupervised Domain Adaptative Object Detection

Unsupervised Domain Adaptative Object Detection (UDAOD) aims to alleviate the gap between the source domain and the target domain. Previous methods sought to plainly align global and local features across domains but adapted numerous pooled features and overlooked contextual information, which caused incorrect perceptions of foreground information. To tackle these problems, we propose Diverse Feature-level Guidance Adjustments (DFGAs) for two-stage object detection frameworks, including Pixel-wise Multi-scale Alignment (PMA) and Adaptative Threshold Confidence Adjustment (ATCA). Specifically, PMA adapts features within diverse hierarchical levels to capture sufficient contextual information. Through a customized PMA loss, features from different stages of a network facilitate information interaction across domains. Training with this loss function contributes to the generation of more domain-agnostic features. To better recognize foreground and background samples, ATCA employs adaptative thresholds to divide the foreground and background samples. This strategy flexibly instructs the classifier to perceive the significance of box candidates. Comprehensive experiments are conducted on Cityscapes, Foggy Cityscapes, KITTI, and Sim10k datasets to further demonstrate the superior performance of our method compared to the baseline method.

SwiftPillars: High-Efficiency Pillar Encoder for Lidar-Based 3D Detection

Lidar-based 3D Detection is one of the significant components of Autonomous Driving. However, current methods over-focus on improving the performance of 3D Lidar perception, which causes the architecture of networks becoming complicated and hard to deploy. Thus, the methods are difficult to apply in Autonomous Driving for real-time processing. In this paper, we propose a high-efficiency network, SwiftPillars, which includes Swift Pillar Encoder (SPE) and Multi-scale Aggregation Decoder (MAD). The SPE is constructed by a concise Dual-attention Module with lightweight operators. The Dual-attention Module utilizes feature pooling, matrix multiplication, etc. to speed up point-wise and channel-wise attention extraction and fusion. The MAD interconnects multiple scale features extracted by SPE with minimal computational cost to leverage performance. In our experiments, our proposal accomplishes 61.3% NDS and 53.2% mAP in nuScenes dataset. In addition, we evaluate inference time on several platforms (P4, T4, A2, MLU370, RTX3080), where SwiftPillars achieves up to 13.3ms (75FPS) on NVIDIA Tesla T4. Compared with PointPillars, SwiftPillars is on average 26.58% faster in inference speed with equivalent GPUs and a higher mAP of approximately 3.2% in the nuScenes dataset.

Biophysical coupling of seasonal chlorophyll-a bloom variations and phytoplankton assemblages across the Peninsula Front in the Bransfield Strait

Abstract. This study investigates the spatio-temporal variations in the chlorophyll-a (chl-a) blooms in the Bransfield Strait (BS) at a climatological scale (1998–2018). We propose that suitable monitoring of these blooms can be achieved through remotely sensed observations only if the BS is divided following the Peninsula Front (PF), which ultimately influences the phytoplankton assemblage. Our analysis is based on characterizing climatological fields of sea surface temperature (SST), air temperature, sea ice coverage, chl-a concentrations and wind stress, guided by synoptic novel and historical in situ observations which reveal two niches for phytoplankton assemblage: the Transitional Bellingshausen Water (TBW) and Transitional Weddell Water (TWW) pools. The TBW pool features stratified, less saline, warmer waters with shallow mixed layers, while the TWW pool features well-mixed, saltier, and colder waters. We identify that the 0.6 °C isotherm corresponds to the summertime climatological PF location, effectively dividing the BS into two different scenarios. Furthermore, the 0.5 mg m−3 chl-a isoline aligns well with the 0.6 °C isotherm, serving as a threshold for chl-a blooms of the highest concentrations around the South Shetland Islands. For the first time, these thresholds enable the monthly climatological descriptions of the two blooms developing in the BS on both sides of the PF. We think this approach underscores the potential of combining SST and chl-a data to monitor the year-to-year interplay of the chl-a blooms occurring in the TBW and TWW pools contoured by the PF.

PPTtrack: Pyramid pooling based Transformer backbone for visual tracking

In visual tracking, Convolutional Neural Network (CNN) is usually used as feature extractor, and can fully explore local dependencies of image blocks, which is help for improving tracking performance. However, CNN ignores global dependencies in image blocks. The global modeling is crucial in visual tracking. Recently, Transformer has gained attention to fully explore global dependencies on sequential data. However, Transformer’s unique multi-head self-attention mechanism results in high computational complexity. In this paper, we design a pyramid pooling based Transformer backbone network for visual tracking. Pyramid pooling refers to multiple pooling operations for feature map with different receptive fields and strides. The output data of each pooling layer is concatenated to form the final pooled feature map. On the one hand, after flattening the feature map with pyramid pooling, its sequence length will be greatly reduced. This will effectively reduce the computational complexity of the multi-head self-attention. On the other hand, pyramid pooling can extract multi-scale features, makes the feature maps contain more global context information. Finally, we propose a novel tracker with the designed pyramid pooling based Transformer backbone network and the Transformer based model predictor. We train the proposed tracker by end-to-end, and evaluate it on seven tracking benchmarks including UAV123, NFS, Trackingnet, LaSOT, GOT-10K, VOT2020 and RGBT2019. The proposed tracker achieves 79.8% robustness and 35 FPS on the VOT2020 dataset. The experiment demonstrates that proposed tracker achieves superior tracking performance with state-of-the-art trackers.

Fault Diagnosis of a Multistage Centrifugal Pump Using Explanatory Ratio Linear Discriminant Analysis.

This study introduces an innovative approach for fault diagnosis of a multistage centrifugal pump (MCP) using explanatory ratio (ER) linear discriminant analysis (LDA). Initially, the method addresses the challenge of background noise and interference in vibration signals by identifying a fault-sensitive frequency band (FSFB). From the FSFB, raw hybrid statistical features are extracted in time, frequency, and time-frequency domains, forming a comprehensive feature pool. Recognizing that not all features adequately represent MCP conditions and can reduce classification accuracy, we propose a novel ER-LDA method. ER-LDA evaluates feature importance by calculating the explanatory ratio between interclass distance and intraclass scatteredness, facilitating the selection of discriminative features through LDA. This fusion of ER-based feature assessment and LDA yields the novel ER-LDA technique. The resulting selective feature set is then passed into a k-nearest neighbor (K-NN) algorithm for condition classification, distinguishing between normal, mechanical seal hole, mechanical seal scratch, and impeller defect states of the MCP. The proposed technique surpasses current cutting-edge techniques in fault classification.

XCAPT5: protein–protein interaction prediction using deep and wide multi-kernel pooling convolutional neural networks with protein language model

BackgroundPredicting protein–protein interactions (PPIs) from sequence data is a key challenge in computational biology. While various computational methods have been proposed, the utilization of sequence embeddings from protein language models, which contain diverse information, including structural, evolutionary, and functional aspects, has not been fully exploited. Additionally, there is a significant need for a comprehensive neural network capable of efficiently extracting these multifaceted representations.ResultsAddressing this gap, we propose xCAPT5, a novel hybrid classifier that uniquely leverages the T5-XL-UniRef50 protein large language model for generating rich amino acid embeddings from protein sequences. The core of xCAPT5 is a multi-kernel deep convolutional siamese neural network, which effectively captures intricate interaction features at both micro and macro levels, integrated with the XGBoost algorithm, enhancing PPIs classification performance. By concatenating max and average pooling features in a depth-wise manner, xCAPT5 effectively learns crucial features with low computational cost.ConclusionThis study represents one of the initial efforts to extract informative amino acid embeddings from a large protein language model using a deep and wide convolutional network. Experimental results show that xCAPT5 outperforms recent state-of-the-art methods in binary PPI prediction, excelling in cross-validation on several benchmark datasets and demonstrating robust generalization across intra-species, cross-species, inter-species, and stringent similarity contexts.

Optimizing dynamic keystroke pattern recognition with hybrid deep learning technique and multiple soft biometric factors

In this work, we propose an optimization approach for dynamic keystroke pattern recognition by leveraging a hybrid deep learning technique and multiple soft biometric factors. Our methodology begins with the introduction of a novel algorithm called dynamic drone squadron optimization (DDSO) to optimize the selection of optimal features from a pool of multiple keystroke features. We then present an enhanced version of the improved sperm swarm optimization (ISSO) algorithm, which effectively combines the optimal weight features derived from multiple biometric responses. Furthermore, we introduce the multi-stage recurrent neural network (MS-RNN) classifier to accurately recognize and classify keystroke patterns. The performance of our proposed ISSO+MS-RNN technique is evaluated using the benchmark KBOC dataset to validate its effectiveness. Comparative analysis is conducted against existing state-of-the-art techniques, employing various evaluation measures, to demonstrate the superior performance of proposed approach.`

A new CNN-based semantic object segmentation for autonomous vehicles in urban traffic scenes

Semantic segmentation is the most important stage of making sense of the visual traffic scene for autonomous driving. In recent years, convolutional neural networks (CNN)-based methods for semantic segmentation of urban traffic scenes are among the trending studies. However, the methods developed in the studies carried out so far are insufficient in terms of accuracy performance criteria. In this study, a new CNN-based semantic segmentation method with higher accuracy performance is proposed. A new module, the Attentional Atrous Feature Pooling (AAFP) Module, has been developed for the proposed method. This module is located between the encoder and decoder in the general network structure and aims to obtain multi-scale information and add attentional features to large and small objects. As a result of experimental tests with the CamVid data set, an accuracy value of approximately 2% higher was achieved with a mIoU value of 70.59% compared to other state-of-art methods. Therefore, the proposed method can semantically segment objects in the urban traffic scene better than other methods.

A multi-step fast charging-based battery capacity estimation framework of real-world electric vehicles

Accurately evaluating battery degradation is not only crucial for ensuring the safe and reliable operation of electric vehicles (EVs) but also fundamental for their intelligent management and maximum utilization. However, the non-linearity, non-measurability, and multi-stress coupled operating conditions have posed significant challenges for battery health prediction. This paper proposes a battery capacity estimation framework based on real-world operating data. Firstly, a comprehensive feature pool is constructed from the direct external features extracted during multi-step fast charging processes and the quantitative representation of operating conditions. Subsequently, a two-step feature engineering is introduced to select the most relevant features and eliminate the interference components. The battery capacity estimation framework is then implemented using machine learning methods. Validation results demonstrate that the proposed framework achieves superior estimation accuracy with lower computational expense compared to the modelling process without feature engineering. The MAPE and RMSE reach 1.18% and 1.98 Ah, respectively, representing reductions in errors of up to 8.53% and 11.21%. Collectively, the proposed framework paves the foundation for online health prognostics of batteries under practical operating conditions.

Compressive mechanical response and microstructures in low strain rate plastic deformation of stainless steel 316L fabricated by selective laser melting

Characterization of the mechanical properties plays an essential role in the post-processing and evaluation of the functionality of the additively manufactured metallic parts. A number of studies have been focused on the tensile properties of additively manufactured metals. However, the quasi-static compression test of the additively manufactured 316L blocks with different heat-treatment conditions and scanning strategies seems to be overlooked in the literature. This paper aims to provide a comprehensive study of compressive mechanical response in plastic deformation of SS316L fabricated by selective laser melting (SLM). The mechanical response and microstructures in compressive deformation is analyzed for three printing strategies with 0°-, 90°- and 67.5°- scanning and three heat treatment conditions (450 °C for 3 h, 1100 °C for 1 h with furnace cool and 1100 °C for 1 h with water quenching) for selective laser melted (SLMed) stainless steel 316L in comparison with wrought stainless steel 316L in this work. Alteration of mechanical properties, microstructure evolution and compressive deformation mechanism is studied. Melt pool features are not significantly affected by low-temperature heat treatment (450 °C for 3 h) but fully dissolved through high-temperature heat treatment (1100 °C for 1 h). High-temperature heat treatment provides a higher resistance to compressive plastic deformation for SLMed 316L compared with the low-temperature heat-treated and as-built samples where more twinnings are observed. The compressive plastic deformation mechanism of 90°- and 67.5°-scanning samples is similar, which mainly results from twinning-induced plasticity. For 0°-scanning samples, the strong crystallographic texture is the main cause of anisotropic deformation. Modelling and simulation have been conducted to explain the anisotropic deformation mechanism of the 0°-scanning strategy. Simulation results suggest that the morphology difference of laser-scanning tracks and melt pools, which leads to material flow along the laser scanning direction, explains the anisotropic deformation mechanism.