A Survey on Self-supervised Contrastive Learning for Multimodal Text-Image Analysis

Self-supervised learning is a machine learning approach that generates implicit labels by learning underlined patterns and extracting discriminative features from unlabeled data without manual labelling. Contrastive learning introduces the concept of "positive" and "negative" samples, where positive pairs (e.g., variation of the same image/object) are brought together in the embedding space, and negative pairs (e.g., views from different images/objects) are pushed farther away. This methodology has shown significant improvements in image understanding and image text analysis without much reliance on labeled data. In this paper, we comprehensively discuss the terminologies, recent developments and applications of contrastive learning with respect to text-image models. Specifically, we provide an overview of the approaches of contrastive learning in text-image models in recent years. Secondly, we categorize the approaches based on different model structures. Thirdly, we further introduce and discuss the latest advances of the techniques used in the process such as pretext tasks for both images and text, architectural structures, and key trends. Lastly, we discuss the recent state-of-art applications of self-supervised contrastive learning Text-Image based models.

A Survey of the Self Supervised Learning Mechanisms for Vision Transformers

Deep supervised learning models require high volume of labeled data to attain sufficiently good results. Although, the practice of gathering and annotating such big data is costly and laborious. Recently, the application of self supervised learning (SSL) in vision tasks has gained significant attention. The intuition behind SSL is to exploit the synchronous relationships within the data as a form of self-supervision, which can be versatile. In the current big data era, most of the data is unlabeled, and the success of SSL thus relies in finding ways to improve this vast amount of unlabeled data available. Thus its better for deep learning algorithms to reduce reliance on human supervision and instead focus on self-supervision based on the inherent relationships within the data. With the advent of ViTs, which have achieved remarkable results in computer vision, it is crucial to explore and understand the various SSL mechanisms employed for training these models specifically in scenarios where there is less label data available. In this survey we thus develop a comprehensive taxonomy of systematically classifying the SSL techniques based upon their representations and pre-training tasks being applied. Additionally, we discuss the motivations behind SSL, review popular pre-training tasks, and highlight the challenges and advancements in this field. Furthermore, we present a comparative analysis of different SSL methods, evaluate their strengths and limitations, and identify potential avenues for future research.

Channel Boosted CNN-Transformer-based Multi-Level and Multi-Scale Nuclei Segmentation

Accurate nuclei segmentation is an essential foundation for various applications in computational pathology, including cancer diagnosis and treatment planning. Even slight variations in nuclei representations can significantly impact these downstream tasks. However, achieving accurate segmentation remains challenging due to factors like clustered nuclei, high intra-class variability in size and shape, resemblance to other cells, and color or contrast variations between nuclei and background. Despite the extensive utilization of Convolutional Neural Networks (CNNs) in medical image segmentation, they may have trouble capturing long-range dependencies crucial for accurate nuclei delineation. Transformers address this limitation but might miss essential low-level features. To overcome these limitations, we utilized CNN-Transformer-based techniques for nuclei segmentation in H&E stained histology images. In this work, we proposed two CNN-Transformer architectures, Nuclei Hybrid Vision Transformer (NucleiHVT) and Channel Boosted Nuclei Hybrid Vision Transformer (CB-NucleiHVT), that leverage the strengths of both CNNs and Transformers to effectively learn nuclei boundaries in multi-organ histology images. The first architecture, NucleiHVT is inspired by the UNet architecture and incorporates the dual attention mechanism to capture both multi-level and multi-scale context effectively. The CB-NucleiHVT network, on the other hand, utilizes the concept of channel boosting to learn diverse feature spaces, enhancing the model's ability to distinguish subtle variations in nuclei characteristics. Detailed evaluation of two medical image segmentation datasets shows that the proposed architectures outperform existing CNN-based, Transformer-based, and hybrid methods. The proposed networks demonstrated effective results both in terms of quantitative metrics, and qualitative visual assessment.

Particle Multi-Axis Transformer for Jet Tagging

Jet tagging is an essential categorization problem in high energy physics. In recent times, Deep Learning has not only risen to the challenge of jet tagging but also significantly improved its performance. In this article, we propose an idea of a new architecture, Particle Multi-Axis transformer (ParMAT) which is a modified version of Particle transformer (ParT). ParMAT contains local and global spatial interactions within a single unit which improves its ability to handle various input lengths. We trained our model on JETCLASS, a publicly available large dataset that contains 100M jets of 10 different classes of particles. By integrating a parallel attention mechanism and pairwise interactions of particles in the attention mechanism,ParMAT achieves robustness and higher accuracy over the ParT and ParticleNet. The scalability of the model to huge datasets and its ability to automatically extract essential features demonstrate its potential for enhancing jet tagging.

A Recent Survey of Vision Transformers for Medical Image Segmentation

Medical image segmentation plays a crucial role in various healthcare applications, enabling accurate diagnosis, treatment planning, and disease monitoring. In recent years, Vision Transformers (ViTs) have emerged as a promising technique for addressing the challenges in medical image segmentation. In medical images, structures are usually highly interconnected and globally distributed. ViTs utilize their multi-scale attention mechanism to model the long-range relationships in the images. However, they do lack image-related inductive bias and translational invariance, potentially impacting their performance. Recently, researchers have come up with various ViT-based approaches that incorporate CNNs in their architectures, known as Hybrid Vision Transformers (HVTs) to capture local correlation in addition to the global information in the images. This survey paper provides a detailed review of the recent advancements in ViTs and HVTs for medical image segmentation. Along with the categorization of ViT and HVT-based medical image segmentation approaches we also present a detailed overview of their real-time applications in several medical image modalities. This survey may serve as a valuable resource for researchers, healthcare practitioners, and students in understanding the state-of-the-art approaches for ViT-based medical image segmentation.

MaxViT-UNet: Multi-Axis Attention for Medical Image Segmentation

Convolutional neural networks have made significant strides in medical image analysis in recent years. However, the local nature of the convolution operator inhibits the CNNs from capturing global and long-range interactions. Recently, Transformers have gained popularity in the computer vision community and also medical image segmentation. But scalability issues of self-attention mechanism and lack of the CNN like inductive bias have limited their adoption. In this work, we present MaxViT-UNet, an Encoder-Decoder based hybrid vision transformer for medical image segmentation. The proposed hybrid decoder, also based on MaxViT-block, is designed to harness the power of convolution and self-attention mechanism at each decoding stage with minimal computational burden. The multi-axis self-attention in each decoder stage helps in differentiating between the object and background regions much more efficiently. The hybrid decoder block initially fuses the lower level features upsampled via transpose convolution, with skip-connection features coming from hybrid encoder, then fused features are refined using multi-axis attention mechanism. The proposed decoder block is repeated multiple times to accurately segment the nuclei regions. Experimental results on MoNuSeg dataset proves the effectiveness of the proposed technique. Our MaxViT-UNet outperformed the previous CNN only (UNet) and Transformer only (Swin-UNet) techniques by a large margin of 2.36% and 5.31% on Dice metric respectively.

A survey of the Vision Transformers and its CNN-Transformer based Variants

Vision transformers have recently become popular as a possible alternative to convolutional neural networks (CNNs) for a variety of computer vision applications. These vision transformers due to their ability to focus on global relationships in images have large capacity, but may result in poor generalization as compared to CNNs. Very recently, the hybridization of convolution and self-attention mechanisms in vision transformers is gaining popularity due to their ability of exploiting both local and global image representations. These CNN-Transformer architectures also known as hybrid vision transformers have shown remarkable results for vision applications. Recently, due to the rapidly growing number of these hybrid vision transformers, there is a need for a taxonomy and explanation of these architectures. This survey presents a taxonomy of the recent vision transformer architectures, and more specifically that of the hybrid vision transformers. Additionally, the key features of each architecture such as the attention mechanisms, positional embeddings, multi-scale processing, and convolution are also discussed. This survey highlights the potential of hybrid vision transformers to achieve outstanding performance on a variety of computer vision tasks. Moreover, it also points towards the future directions of this rapidly evolving field.

CB-HVTNet: A channel-boosted hybrid vision transformer network for lymphocyte assessment in histopathological images

Transformers, due to their ability to learn long range dependencies, have overcome the shortcomings of convolutional neural networks (CNNs) for global perspective learning. Therefore, they have gained the focus of researchers for several vision related tasks including medical diagnosis. However, their multi-head attention module only captures global level feature representations, which is insufficient for medical images. To address this issue, we propose a Channel Boosted Hybrid Vision Transformer (CB HVT) that uses transfer learning to generate boosted channels and employs both transformers and CNNs to analyse lymphocytes in histopathological images. The proposed CB HVT comprises five modules, including a channel generation module, channel exploitation module, channel merging module, region-aware module, and a detection and segmentation head, which work together to effectively identify lymphocytes. The channel generation module uses the idea of channel boosting through transfer learning to extract diverse channels from different auxiliary learners. In the CB HVT, these boosted channels are first concatenated and ranked using an attention mechanism in the channel exploitation module. A fusion block is then utilized in the channel merging module for a gradual and systematic merging of the diverse boosted channels to improve the network's learning representations. The CB HVT also employs a proposal network in its region aware module and a head to effectively identify objects, even in overlapping regions and with artifacts. We evaluated the proposed CB HVT on two publicly available datasets for lymphocyte assessment in histopathological images. The results show that CB HVT outperformed other state of the art detection models, and has good generalization ability, demonstrating its value as a tool for pathologists.

Deep Neural Networks based Meta-Learning for Network Intrusion Detection

Designing an intrusion detection system is difficult as network traffic encompasses various attack types, including new and evolving ones with minor changes. The data used to construct a predictive model has a skewed class distribution and limited representation of attack types, which differ from real network traffic. These limitations result in dataset shift, negatively impacting the machine learning models' predictive abilities and reducing the detection rate against novel attacks. To address the challenge of dataset shift, we introduce the INformation FUsion and Stacking Ensemble (INFUSE) for network intrusion detection. This approach further improves its predictive power by employing a deep neural network-based Meta-Learner on top of INFUSE. First, a hybrid feature space is created by integrating decision and feature spaces. Five different classifiers are utilized to generate a pool of decision spaces. The feature space is then enriched through a deep sparse autoencoder that learns the semantic relationships between attacks. Finally, the deep Meta-Learner acts as an ensemble combiner to analyze the hybrid feature space and make a final decision. Our evaluation on stringent benchmark datasets and comparison to existing techniques showed the effectiveness of INFUSE with an F-Score of 0.91, Accuracy of 91.6%, and Recall of 0.94 on the Test+ dataset, and an F-Score of 0.91, Accuracy of 85.6%, and Recall of 0.87 on the stringent Test-21 dataset. These promising results indicate the proposed technique has strong generalization capability and the potential to detect network attacks.

Traffic Management of Autonomous Vehicles using Policy Based Deep Reinforcement Learning and Intelligent Routing

Deep Reinforcement Learning (DRL) uses diverse, unstructured data and makes RL capable of learning complex policies in high dimensional environments. Intelligent Transportation System (ITS) based on Autonomous Vehicles (AVs) offers an excellent playground for policy-based DRL. Deep learning architectures solve computational challenges of traditional algorithms while helping in real-world adoption and deployment of AVs. One of the main challenges in AVs implementation is that it can worsen traffic congestion on roads if not reliably and efficiently managed. Considering each vehicle's holistic effect and using efficient and reliable techniques could genuinely help optimise traffic flow management and congestion reduction. For this purpose, we proposed a intelligent traffic control system that deals with complex traffic congestion scenarios at intersections and behind the intersections. We proposed a DRL-based signal control system that dynamically adjusts traffic signals according to the current congestion situation on intersections. To deal with the congestion on roads behind the intersection, we used re-routing technique to load balance the vehicles on road networks. To achieve the actual benefits of the proposed approach, we break down the data silos and use all the data coming from sensors, detectors, vehicles and roads in combination to achieve sustainable results. We used SUMO micro-simulator for our simulations. The significance of our proposed approach is manifested from the results.