Few-shot Methods Research Articles

Achieving High-Accuracy Target Recognition Using Few ISAR Images via Multi-Prototype Network with Attention Mechanism

Inverse synthetic aperture radar (ISAR) is a significant means of detection in space of non-cooperative targets, which means that the imaging geometry and associated parameters between the ISAR platform and the detection targets are unknown. In this way, a large number of ISAR images for high-accuracy target recognition are difficult to obtain. Recently, prototypical networks (PNs) have gained considerable attention as an effective method for few-shot learning. However, due to the specificity of the ISAR imaging mechanism, ISAR images often have unknown range and azimuth distortions, resulting in a poor imaging effect. Therefore, this condition poses a challenge for a PN to represent a class through a prototype. To address this issue, we use a multi-prototype network (MPN) with attention mechanism for ISAR image target recognition. The use of multiple prototypes eases the uncertainty associated with the fixed structure of a single prototype, enabling the capture of more comprehensive target information. Furthermore, to maximize the feature extraction capability of MPN for ISAR images, this method introduces the classical convolutional block attention module (CBAM) attentional mechanism, where CBAM generates attentional feature maps along channel and spatial dimensions to generate multiple robust prototypes. Experimental results demonstrate that this method outperforms state-of-the-art few-shot methods. In a four-class classification task, it achieved a target recognition accuracy of 95.08%, representing an improvement of 9.94–17.49% over several other few-shot approaches.

Related Work on Few-shot Method: A Review

Abstract. As Natural Language Processing (NLP) technologies continue to expand into novel domains, few-shot learning emerges as a pivotal approach to addressing the challenge of data scarcity. Traditional neural networks, due to their strong reliance on abundant data, have posed limitations in their applicability to new domains. Consequently, there is a pressing need to introduce fresh research perspectives and solutions within this realm, aiming to propel its development towards greater practicality and efficiency. Firstly, solving the zero or few-shot Dialogue State Tracking problem has become necessary as the demand for deploying such systems in new domains continues to grow. This article explores the performance of D-REPTILE, a meta learner for Destination Address (DST) problems, in unknown domains. Then PET is extensively studied. Real-world tests on RAFT show cue-based learning works in low-sample settings, reinforcing the importance of instruction-based learning for human-like few-shot capabilities. Thirdly, to address the overfitting problem, this paper also explores the LA- UCL model, as well as its application, development, and challenges, which enables the LA-UCL model to enhance the Large Language Model data expansion effect through two modules. Finally, CausalCollab is introduced, which uses Incremental Stylistic Effects (ISE) as a guiding estimator for assessing the effectiveness of LM-human cooperation tactics through time.

Few-shot SAR target classification via meta-learning with hybrid models

Currently, in Synthetic Aperture Radar Automatic Target Recognition (SAR ATR), few-shot methods can save cost and resources while enhancing adaptability. However, due to the limitations of SAR imaging environments and observation conditions, obtaining a large amount of high-value target data is challenging, leading to a severe shortage of datasets. This paper proposes the use of an Adaptive Dynamic Weight Hybrid Model (ADW-HM) meta-learning framework to address the problem of poor recognition accuracy for unknown classes caused by sample constraints. By dynamically weighting and learning model parameters independently, the framework dynamically integrates model results to improve recognition accuracy for unknown classes. Experiments conducted on the TASK-MSTAR and OpenSARShip datasets demonstrate that the ADW-HM framework can obtain more comprehensive and integrated feature representations, reduce overfitting, and enhance generalization capability for unknown classes. The accuracy is improved in both 1-shot and 5-shot scenarios, indicating that ADW-HM is feasible for addressing few-shot problems.

Residual channel attention based sample adaptation few-shot learning for hyperspectral image classification.

Few-shot learning (FSL) uses prior knowledge and supervised experience to effectively classify hyperspectral images (HSIs), thereby reducing the cost of large numbers of labeled samples. However, existing few-shot methods ignore the correlation between cross-domain feature channels, and the feature representation ability is insufficient. To address above issue, this paper proposes a novel Residual Channel Attention Based Sample Adaptation Few-Shot Learning for Hyperspectral Image Classification(RCASA-FSL) for hyperspectral image classification (HSIC), which can capture and enhance cross-domain dependencies through multi-layer residual connection and random-based feature recalibration. Specifically, a Deep Residual Feature Channel Attention Mechanism (DRFCAM) is designed to obtain cross-domain dependencies by residual concatenation, and further the residual structure is stacked for mining depth discrimination information. Furthermore, a new Random-based Feature Recalibration Module (RFRM) is proposed to reassign the feature weights via random matrix, which fully explore feature weight relationships to guide the sample adaptation process. Besides, we design a joint loss function with combining the FSL loss and domain adaptive loss for further optimization model. Experiments conducted on several standard hyperspectral datasets demonstrate that the proposed RCASA-FSL is superior to other FSL techniques in both quantitative and qualitative aspects.

Few-Shot Methods for Aspect-Level Sentiment Analysis

In this paper, we explore the approaches to the problem of cross-domain few-shot classification of sentiment aspects. By cross-domain few-shot, we mean a setting where the model is trained on large data in one domain (for example, hotel reviews) and is intended to perform on another (for example, restaurant reviews) with only a few labelled examples in the target domain. We start with pre-trained monolingual language models. Using the Polish language dataset AspectEmo, we compare model training using standard gradient-based learning to a zero-shot approach and two dedicated few-shot methods: ProtoNet and NNShot. We find both dedicated methods much superior to both gradient learning and zero-shot setup, with a small advantage held by NNShot. Overall, we find few-shot to be a compelling alternative, achieving a surprising amount of performance compared to gradient training on full-size data.

Prompt-guided and multimodal landscape scenicness assessments with vision-language models.

Recent advances in deep learning and Vision-Language Models (VLM) have enabled efficient transfer to downstream tasks even when limited labelled training data is available, as well as for text to be directly compared to image content. These properties of VLMs enable new opportunities for the annotation and analysis of images. We test the potential of VLMs for landscape scenicness prediction, i.e., the aesthetic quality of a landscape, using zero- and few-shot methods. We experiment with few-shot learning by fine-tuning a single linear layer on a pre-trained VLM representation. We find that a model fitted to just a few hundred samples performs favourably compared to a model trained on hundreds of thousands of examples in a fully supervised way. We also explore the zero-shot prediction potential of contrastive prompting using positive and negative landscape aesthetic concepts. Our results show that this method outperforms a linear probe with few-shot learning when using a small number of samples to tune the prompt configuration. We introduce Landscape Prompt Ensembling (LPE), which is an annotation method for acquiring landscape scenicness ratings through rated text descriptions without needing an image dataset during annotation. We demonstrate that LPE can provide landscape scenicness assessments that are concordant with a dataset of image ratings. The success of zero- and few-shot methods combined with their ability to use text-based annotations highlights the potential for VLMs to provide efficient landscape scenicness assessments with greater flexibility.

Few-shot bronze vessel classification via siamese fourier networks

Exploring ancient Chinese artifacts is crucial for analyzing East Asian technological development, with bronze vessel being the critical element. Bronze vessels, typically featuring intricate carvings, hold historical significance and provide valuable insights into past civilizations. However, identifying bronze patterns can be challenging for human vision, and most RGB-domain methods fail to capture periodic designs. Addressing these issues, we propose the Siamese Fourier Networks (SFN), a parallel network model designed for few-shot regular pattern classification. The Siamese network can differentiate between intricate shapes, while Fourier features enable the extraction of regular textures. To optimize parallel networks, we combine the BCE loss and focal contrastive loss, balancing positive and negative samples. Moreover, we introduce the Bronze Vessel Dataset, featuring 527 samples with diverse shapes and unbalanced distributions. Extensive experiments with advanced few-shot methods demonstrate the superiority of SFN and focal mechanism, significantly improving accuracy.

A Self-Supervised Few-Shot Semantic Segmentation Method Based on Multi-Task Learning and Dense Attention Computation.

Nowadays, autonomous driving technology has become widely prevalent. The intelligent vehicles have been equipped with various sensors (e.g., vision sensors, LiDAR, depth cameras etc.). Among them, the vision systems with tailored semantic segmentation and perception algorithms play critical roles in scene understanding. However, the traditional supervised semantic segmentation needs a large number of pixel-level manual annotations to complete model training. Although few-shot methods reduce the annotation work to some extent, they are still labor intensive. In this paper, a self-supervised few-shot semantic segmentation method based on Multi-task Learning and Dense Attention Computation (dubbed MLDAC) is proposed. The salient part of an image is split into two parts; one of them serves as the support mask for few-shot segmentation, while cross-entropy losses are calculated between the other part and the entire region with the predicted results separately as multi-task learning so as to improve the model's generalization ability. Swin Transformer is used as our backbone to extract feature maps at different scales. These feature maps are then input to multiple levels of dense attention computation blocks to enhance pixel-level correspondence. The final prediction results are obtained through inter-scale mixing and feature skip connection. The experimental results indicate that MLDAC obtains 55.1% and 26.8% one-shot mIoU self-supervised few-shot segmentation on the PASCAL-5i and COCO-20i datasets, respectively. In addition, it achieves 78.1% on the FSS-1000 few-shot dataset, proving its efficacy.

TAJ-Net: a two-stage clustered cell segmentation network with adaptive joint learning of spatial and spectral information.

Pulmonary adenocarcinoma is the primary cause of cancer-related death worldwide and pathological diagnosis is the "golden standard" based on the regional distribution of cells. Thus, regional cell segmentation is a key step while it is challenging due to the following reasons: 1) It is hard for pure semantic and instance segmentation methods to obtain a high-quality regional cell segmentation result; 2) Since the spatial appearances of pulmonary cells are very similar which even confuse pathologists, annotation errors are usually inevitable. Considering these challenges, we propose a two-stage 3D adaptive joint training framework (TAJ-Net) to segment-then-classify cells with extra spectral information as the supplementary information of spatial information. Firstly, we propose to leverage a few-shot method with limited data for cell mask acquisition to avoid the disturbance of cluttered backgrounds. Secondly, we introduce an adaptive joint training strategy to remove noisy samples through two 3D networks and one 1D network for cell type classification rather than segmentation. Subsequently, we propose a patch mapping method to map classification results to the original images to obtain regional segmentation results. In order to verify the effectiveness of TAJ-Net, we build two 3D hyperspectral datasets, i.e., pulmonary adenocarcinoma (3,660 images) and thyroid carcinoma (4623 images) with 40 bands. The first dataset will be released for further research. Experiments show that TAJ-Net achieves much better performance in clustered cell segmentation, and it can regionally segment different kinds of cells with high overlap and blurred edges, which is a difficult task for the state-of-the-art methods. Compared to 2D models, the hyperspectral image-based 3D model reports a significant improvement of up to 11.5% in terms of the Dice similarity coefficient in the pulmonary adenocarcinoma dataset.

Unlocking the capabilities of explainable few-shot learning in remote sensing

Recent advancements have significantly improved the efficiency and effectiveness of deep learning methods for image-based remote sensing tasks. However, the requirement for large amounts of labeled data can limit the applicability of deep neural networks to existing remote sensing datasets. To overcome this challenge, few-shot learning has emerged as a valuable approach for enabling learning with limited data. While previous research has evaluated the effectiveness of few-shot learning methods on satellite-based datasets, little attention has been paid to exploring the applications of these methods to datasets obtained from Unmanned Aerial Vehicles (UAVs), which are increasingly used in remote sensing studies. In this review, we provide an up-to-date overview of both existing and newly proposed few-shot classification techniques, along with appropriate datasets that are used for both satellite-based and UAV-based data. We demonstrate few-shot learning can effectively handle the diverse perspectives in remote sensing data. As an example application, we evaluate state-of-the-art approaches on a UAV disaster scene dataset, yielding promising results. Furthermore, we highlight the significance of incorporating explainable AI (XAI) techniques into few-shot models. In remote sensing, where decisions based on model predictions can have significant consequences, such as in natural disaster response or environmental monitoring, the transparency provided by XAI is crucial. Techniques like attention maps and prototype analysis can help clarify the decision-making processes of these complex models, enhancing their reliability. We identify key challenges including developing flexible few-shot methods to handle diverse remote sensing data effectively. This review aims to equip researchers with an improved understanding of few-shot learning’s capabilities and limitations in remote sensing, while pointing out open issues to guide progress in efficient, reliable and interpretable data-efficient techniques.

CRTED: Few-Shot Object Detection via Correlation-RPN and Transformer Encoder–Decoder

Few-shot object detection (FSOD) aims to address the challenge of requiring a substantial number of annotations for training in conventional object detection, which is very labor-intensive. However, the existing few-shot methods achieve high precision with the sacrifice of time for exhaustive fine-tuning or have poor performance in novel-class adaptation. We presume the major reason is that the valuable correlation feature among different categories is insufficiently exploited, hindering the generalization of knowledge from base to novel categories for object detection. In this paper, we propose few-shot object detection via Correlation-RPN and transformer encoder–decoder (CRTED), a novel training network to learn object-relevant features of inter-class correlation and intra-class compactness while suppressing object-agnostic features in the background with limited annotated samples. And we also introduce a four-way tuple-contrast training strategy to positively activate the training progress of our object detector. Experiments over two few-shot benchmarks (Pascal VOC, MS-COCO) demonstrate that our proposed CRTED without further fine-tuning can achieve comparable performance with current state-of-the-art fine-tuned works. The codes and pre-trained models will be released.

Ta-Adapter: Enhancing few-shot CLIP with task-aware encoders

Contrastive Language-Image Pre-training (CLIP) has shown impressive zero-shot transfer capabilities, but its potential for specific downstream tasks is not fully utilized. To further enhance CLIP’s few-shot capability for specific datasets, some subsequent works have been proposed, such as methods based on lightweight adapters and prompt learning. However, since CLIP is pretrained on a diverse collection of image and text pairs sourced from the internet, it is difficult to sufficiently tune models to specific datasets using only lightweight adaptions. In this paper, we argue that largely modifying the internal representations within CLIP’s encoders can yield better results on downstream datasets. In this work, we introduce Ta-Adapter, a method that equips both the visual and textual encoders of CLIP with task-specific prompts. These prompts are generated using a collaborative prompt learning approach, which allows the encoders to produce representations that are better aligned with specific downstream datasets. Then, we initialize an adapter module using the optimized features generated by the task-aware visual encoder for further feature alignment, and this module can also be further fine-tuned. Our extensive experiments on image classification datasets show that compared to the state-of-the-art few-shot methods Tip-Adapter-F and MaPLe, our model exhibits good performance and obtains an average absolute gain of 2.04% and 1.62% on 11 different image recognition datasets, respectively. In conclusion, this work presents a unique and effective approach to unlocking the full potential of CLIP’s few-shot learning capabilities.

Self-reconstruction network for fine-grained few-shot classification

Metric-based methods are one of the most common methods to solve the problem of few-shot image classification. However, traditional metric-based few-shot methods suffer from overfitting and local feature misalignment. The recently proposed feature reconstruction-based approach, which reconstructs query image features from the support set features of a given class and compares the distance between the original query features and the reconstructed query features as the classification criterion, effectively solves the feature misalignment problem. However, the issue of overfitting still has not been considered. To this end, we propose a self-reconstruction metric module for diversifying query features and a restrained cross-entropy loss for avoiding over-confident predictions. By introducing them, the proposed self-reconstruction network can effectively alleviate overfitting. Extensive experiments on five benchmark fine-grained datasets demonstrate that our proposed method achieves state-of-the-art performance on both 5-way 1-shot and 5-way 5-shot classification tasks. Code is available at https://github.com/liz-lut/SRM-main.

Simple few-shot method for spectrally resolving the wavefront of an ultrashort laser pulse.

We present a novel, to the best of our knowledge, and straightforward approach for the spatio-spectral characterization of ultrashort pulses. This minimally intrusive method relies on placing a mask with specially arranged pinholes in the beam path before the focusing optic and retrieving the spectrally resolved laser wavefront from the speckle pattern produced at focus. We test the efficacy of this new method by accurately retrieving chromatic aberrations, such as pulse-front tilt (PFT), pulse-front curvature (PFC), and higher-order aberrations introduced by a spherical lens. The simplicity and scalability of this method, combined with its compatibility with single-shot operation, make it a strong complement to existing tools for high-intensity laser facilities.

Where It Really Matters: Few-Shot Environmental Conservation Media Monitoring for Low-Resource Languages

Environmental conservation organizations routinely monitor news content on conservation in protected areas to maintain situational awareness of developments that can have an environmental impact. Existing automated media monitoring systems require large amounts of data labeled by domain experts, which is only feasible at scale for high-resource languages like English. However, such tools are most needed in the global south where the news of interest is mainly in local low-resource languages, and far fewer experts are available to annotate datasets on a sustainable basis. In this paper, we propose NewsSerow, a method to automatically recognize environmental conservation content in low-resource languages. NewsSerow is a pipeline of summarization, in-context few-shot classification, and self-reflection using large language models (LLMs). Using at most 10 demonstration example news articles in Nepali, NewsSerow significantly outperforms other few-shot methods and can achieve comparable performance with models fully fine-tuned using thousands of examples. With NewsSerow, Organization X has been able to deploy the media monitoring tool in Nepal, significantly reducing their operational burden, and ensuring that AI tools for conservation actually reach the communities that need them the most. NewsSerow has also been deployed for countries with other languages like Colombia.

Learning Better Registration to Learn Better Few-Shot Medical Image Segmentation: Authenticity, Diversity, and Robustness.

In this work, we address the task of few-shot medical image segmentation (MIS) with a novel proposed framework based on the learning registration to learn segmentation (LRLS) paradigm. To cope with the limitations of lack of authenticity, diversity, and robustness in the existing LRLS frameworks, we propose the better registration better segmentation (BRBS) framework with three main contributions that are experimentally shown to have substantial practical merit. First, we improve the authenticity in the registration-based generation program and propose the knowledge consistency constraint strategy that constrains the registration network to learn according to the domain knowledge. It brings the semantic-aligned and topology-preserved registration, thus allowing the generation program to output new data with great space and style authenticity. Second, we deeply studied the diversity of the generation process and propose the space-style sampling program, which introduces the modeling of the transformation path of style and space change between few atlases and numerous unlabeled images into the generation program. Therefore, the sampling on the transformation paths provides much more diverse space and style features to the generated data effectively improving the diversity. Third, we first highlight the robustness in the learning of segmentation in the LRLS paradigm and propose the mix misalignment regularization, which simulates the misalignment distortion and constrains the network to reduce the fitting degree of misaligned regions. Therefore, it builds regularization for these regions improving the robustness of segmentation learning. Without any bells and whistles, our approach achieves a new state-of-the-art performance in few-shot MIS on two challenging tasks that outperform the existing LRLS-based few-shot methods. We believe that this novel and effective framework will provide a powerful few-shot benchmark for the field of medical image and efficiently reduce the costs of medical image research. All of our code will be made publicly available online.

An Investigation of Applying Large Language Models to Spoken Language Learning

People have long desired intelligent conversational systems that can provide assistance in practical scenarios. The latest advancements in large language models (LLMs) are making significant strides toward turning this aspiration into a tangible reality. LLMs are believed to hold the most potential and value in education, especially in the creation of AI-driven virtual teachers that facilitate language learning. This study focuses on assessing the effectiveness of LLMs within the educational domain, specifically in the areas of spoken language learning, which encompass phonetics, phonology, and second language acquisition. To this end, we first introduced a new multiple-choice question dataset to evaluate the effectiveness of LLMs in the aforementioned scenarios, including the understanding and application of spoken language knowledge. Moreover, we investigated the influence of various prompting techniques such as zero- and few-shot methods (prepending the question with question-answer exemplars), chain-of-thought (CoT) prompting, in-domain exemplars, and external tools. We conducted a comprehensive evaluation of popular LLMs (20 distinct models) using these methods. The experimental results showed that the task of extracting conceptual knowledge posed few challenges for these LLMs, whereas the task of application questions was relatively difficult. In addition, some widely proven effective prompting methods combined with domain-specific examples resulted in significant performance improvements compared to the zero-shot baselines. Additionally, some other preliminary experiments also demonstrated the strengths and weaknesses of different LLMs. The findings of this study can shed light on the application of LLMs to spoken language learning.

MMT: Cross Domain Few-Shot Learning via Meta-Memory Transfer.

Few-shot learning aims to recognize novel categories solely relying on a few labeled samples, with existing few-shot methods primarily focusing on the categories sampled from the same distribution. Nevertheless, this assumption cannot always be ensured, and the actual domain shift problem significantly reduces the performance of few-shot learning. To remedy this problem, we investigate an interesting and challenging cross-domain few-shot learning task, where the training and testing tasks employ different domains. Specifically, we propose a Meta-Memory scheme to bridge the domain gap between source and target domains, leveraging style-memory and content-memory components. The former stores intra-domain style information from source domain instances and provides a richer feature distribution. The latter stores semantic information through exploration of knowledge of different categories. Under the contrastive learning strategy, our model effectively alleviates the cross-domain problem in few-shot learning. Extensive experiments demonstrate that our proposed method achieves state-of-the-art performance on cross-domain few-shot semantic segmentation tasks on the COCO-20 i, PASCAL-5 i, FSS-1000, and SUIM datasets and positively affects few-shot classification tasks on Meta-Dataset.

Arabic Emotion Recognition in Low-Resource Settings: A Novel Diverse Model Stacking Ensemble with Self-Training

Emotion recognition is a vital task within Natural Language Processing (NLP) that involves automatically identifying emotions from text. As the need for specialized and nuanced emotion recognition models increases, the challenge of fine-grained emotion recognition with limited labeled data becomes prominent. Moreover, emotion recognition for some languages, such as Arabic, is a challenging task due to the limited availability of labeled data. This scarcity exists in both size and the granularity of emotions. Our research introduces a novel framework for low-resource fine-grained emotion recognition, which uses an iterative process that integrates a stacking ensemble of diverse base models and self-training. The base models employ different learning paradigms, including zero-shot classification, few-shot methods, machine learning algorithms, and transfer learning. Our proposed method eliminates the need for a large labeled dataset to initiate the training process by gradually generating labeled data through iterations. During our experiments, we evaluated the performance of each base model and our proposed method in low-resource scenarios. Our experimental findings indicate our approach outperforms the individual performance of each base model. It also outperforms the state-of-the-art Arabic emotion recognition models in the literature, achieving a weighted average F1-score equal to 83.19% and 72.12% when tested on the AETD and ArPanEmo benchmark datasets, respectively.

Deep Learning Methods for Semantic Segmentation in Remote Sensing with Small Data: A Survey

The annotations used during the training process are crucial for the inference results of remote sensing images (RSIs) based on a deep learning framework. Unlabeled RSIs can be obtained relatively easily. However, pixel-level annotation is a process that necessitates a high level of expertise and experience. Consequently, the use of small sample training methods has attracted widespread attention as they help alleviate reliance on large amounts of high-quality labeled data and current deep learning methods. Moreover, research on small sample learning is still in its infancy owing to the unique challenges faced when completing semantic segmentation tasks with RSI. To better understand and stimulate future research that utilizes semantic segmentation tasks with small data, we summarized the supervised learning methods and challenges they face. We also reviewed the supervised approaches with data that are currently popular to help elucidate how to efficiently utilize a limited number of samples to address issues with semantic segmentation in RSI. The main methods discussed are self-supervised learning, semi-supervised learning, weakly supervised learning and few-shot methods. The solution of cross-domain challenges has also been discussed. Furthermore, multi-modal methods, prior knowledge constrained methods, and future research required to help optimize deep learning models for various downstream tasks in relation to RSI have been identified.