Leaf disease identification plays a pivotal role in smart agriculture. However, many existing studies still struggle to integrate image and textual modalities to compensate for each other's limitations. Furthermore, many of these approaches rely on pretraining with constrained datasets such as ImageNet, which lack domain-specific information. We propose SCOLD (Soft-target COntrastive learning for Leaf Disease identification), a context-aware vision-language foundation model tailored to address these challenges for agricultural tasks. SCOLD is developed using a diverse corpus of plant leaf images and corresponding symptom descriptions, comprising over 186,000 image-caption pairs aligned with 97 unique concepts. Through task-agnostic pretraining, SCOLD leverages contextual soft targets to mitigate overconfidence in contrastive learning by smoothing labels, thereby improving model generalization and robustness on fine-grained classification tasks. Experimental results demonstrate that SCOLD outperforms existing vision-language models such as OpenAI-CLIP-L, BioCLIP, and SigLIP2 across several benchmarks, including zero-shot and few-shot classification, image-text retrieval, and image classification, while maintaining a competitive parameter footprint. Ablation studies further highlight SCOLD's effectiveness in contrast to its counterparts. The proposed approach significantly advances the agricultural vision-language foundation model, offering strong performance with minimal or no supervised fine-tuning. This work lays a solid groundwork for future research on models trained with long-form and simplified contexts, tasks involving class ambiguity, and multi-modal systems for intelligent plant disease diagnostics. The code for this study is available at https://huggingface.co/enalis/scold
With the inclusion of camera in daily life, an automatic no reference image quality evaluation index is required for automatic classification of images. The present manuscripts proposes a new No Reference Regional Mutual Information based technique for evaluating the quality of an image. We use regional mutual information on subsets of the complete image. Proposed technique is tested on four benchmark natural image databases, and one benchmark synthetic database. A comparative analysis with classical and state-of-art methods indicate superiority of the present technique for high quality images and comparable for other images of the respective databases.
Existing visual explanation generating agents learn to fluently justify a class prediction. However, they may mention visual attributes which reflect a strong class prior, although the evidence may not actually be in the image. This is particularly concerning as ultimately such agents fail in building trust with human users. To overcome this limitation, we propose a phrase-critic model to refine generated candidate explanations augmented with flipped phrases which we use as negative examples while training. At inference time, our phrase-critic model takes an image and a candidate explanation as input and outputs a score indicating how well the candidate explanation is grounded in the image. Our explainable AI agent is capable of providing counter arguments for an alternative prediction, i.e. counterfactuals, along with explanations that justify the correct classification decisions. Our model improves the textual explanation quality of fine-grained classification decisions on the CUB dataset by mentioning phrases that are grounded in the image. Moreover, on the FOIL tasks, our agent detects when there is a mistake in the sentence, grounds the incorrect phrase and corrects it significantly better than other models.
With the wide development of black-box machine learning algorithms, particularly deep neural network (DNN), the practical demand for the reliability assessment is rapidly rising. On the basis of the concept that `Bayesian deep learning knows what it does not know,' the uncertainty of DNN outputs has been investigated as a reliability measure for the classification and regression tasks. However, in the image-caption retrieval task, well-known samples are not always easy-to-retrieve samples. This study investigates two aspects of image-caption embedding-and-retrieval systems. On one hand, we quantify feature uncertainty by considering image-caption embedding as a regression task, and use it for model averaging, which can improve the retrieval performance. On the other hand, we further quantify posterior uncertainty by considering the retrieval as a classification task, and use it as a reliability measure, which can greatly improve the retrieval performance by rejecting uncertain queries. The consistent performance of two uncertainty measures is observed with different datasets (MS COCO and Flickr30k), different deep learning architectures (dropout and batch normalization), and different similarity functions.
This paper provides a proof of concept for an EEG-based reconstruction of a visual image which is on a user's mind. Our approach is based on the Rapid Serial Visual Presentation (RSVP) of polygon primitives and Brain-Computer Interface (BCI) technology. The presentation of polygons that contribute to build a target image (because they match the shape and/or color of the target) trigger attention-related EEG patterns. Accordingly, these target primitives can be determined using BCI classification of Event-Related Potentials (ERPs). They are then accumulated in the display until a satisfactory reconstruction is reached. Selection steps have an average classification accuracy of $75\%$. $25\%$ of the images could be reconstructed completely, while more than $65\%$ of the available visual details could be captured on average. Most of the misclassifications were not misinterpretations of the BCI concerning users' intent; rather, users tried to select polygons that were different than what was intended by the experimenters. Open problems and alternatives to develop a practical BCI-based image reconstruction application are discussed.
Supervised learning is based on the assumption that the ground truth in the training data is accurate. However, this may not be guaranteed in real-world settings. Inaccurate training data will result in some unexpected predictions. In image classification, incorrect labels may cause the classification model to be inaccurate as well. In this paper, I am going to apply unsupervised techniques to the training data before training the classification network. A convolutional autoencoder is applied to encode and reconstruct images. The encoder will project the image data on to latent space. In the latent space, image features are preserved in a lower dimension. The assumption is that data samples with similar features are likely to have the same label. Noised samples can be classified in the latent space by the Density-Base Scan (DBSCAN) clustering algorithm. These incorrectly labeled data are visualized as outliers in the latent space. Therefore, the outliers identified by the DBSCAN algorithm can be classified as incorrectly labeled samples. After the outliers are detected, all the outliers are treated as mislabeled data samples and removed from the dataset. Thus the training data can be directly used in training the supervised learning network. The algorithm can detect and remove above 67\% of mislabeled data in the experimental dataset.
Digital pathology has recently been revolutionized by advancements in artificial intelligence, deep learning, and high-performance computing. With its advanced tools, digital pathology can help improve and speed up the diagnostic process, reduce human errors, and streamline the reporting step. In this paper, we report a new large red blood cell (RBC) image dataset and propose a two-stage deep learning framework for RBC image segmentation and classification. The dataset is a highly diverse dataset of more than 100K RBCs containing eight different classes. The dataset, which is considerably larger than any publicly available hematopathology dataset, was labeled independently by two hematopathologists who also manually created masks for RBC cell segmentation. Subsequently, in the proposed framework, first, a U-Net model was trained to achieve automatic RBC image segmentation. Second, an EfficientNetB0 model was trained to classify RBC images into one of the eight classes using a transfer learning approach with a 5X2 cross-validation scheme. An IoU of 98.03% and an average classification accuracy of 96.5% were attained on the test set. Moreover, we have performed experimental comparisons against several prominent CNN models. These comparisons show the superiority of the proposed model with a good balance between performance and computational cost.
Computer Vision is growing day by day in terms of user specific applications. The first step of any such application is segmenting an image. In this paper, we propose a novel and grass-root level image segmentation algorithm for cases in which the background has uniform color distribution. This algorithm can be used for images of flowers, birds, insects and many more where such background conditions occur. By image segmentation, the visualization of a computer increases manifolds and it can even attain near-human accuracy during classification.
Class imbalance is an inherent problem in many machine learning classification tasks. This often leads to trained models that are unusable for any practical purpose. In this study we explore an unsupervised approach to address these imbalances by leveraging transfer learning from pre-trained image classification models to encoder-based Generative Adversarial Network (eGAN). To the best of our knowledge, this is the first work to tackle this problem using GAN without needing to augment with synthesized fake images. In the proposed approach we use the discriminator network to output a negative or positive score. We classify as minority, test samples with negative scores and as majority those with positive scores. Our approach eliminates epistemic uncertainty in model predictions, as the P(minority) + P(majority) need not sum up to 1. The impact of transfer learning and combinations of different pre-trained image classification models at the generator and discriminator is also explored. Best result of 0.69 F1-score was obtained on CIFAR-10 classification task with imbalance ratio of 1:2500. Our approach also provides a mechanism of thresholding the specificity or sensitivity of our machine learning system. Keywords: Class imbalance, Transfer Learning, GAN, nash equilibrium
Convolutional neural network (CNN) performs well in Hyperspectral Image (HSI) classification tasks, but its high energy consumption and complex network structure make it difficult to directly apply it to edge computing devices. At present, spiking neural networks (SNN) have developed rapidly in HSI classification tasks due to their low energy consumption and event driven characteristics. However, it usually requires a longer time step to achieve optimal accuracy. In response to the above problems, this paper builds a spiking neural network (SNN-SWMR) based on the leaky integrate-and-fire (LIF) neuron model for HSI classification tasks. The network uses the spiking width mixed residual (SWMR) module as the basic unit to perform feature extraction operations. The spiking width mixed residual module is composed of spiking mixed convolution (SMC), which can effectively extract spatial-spectral features. Secondly, this paper designs a simple and efficient arcsine approximate derivative (AAD), which solves the non-differentiable problem of spike firing by fitting the Dirac function. Through AAD, we can directly train supervised spike neural networks. Finally, this paper conducts comparative experiments with multiple advanced HSI classification algorithms based on spiking neural networks on six public hyperspectral data sets. Experimental results show that the AAD function has strong robustness and a good fitting effect. Meanwhile, compared with other algorithms, SNN-SWMR requires a time step reduction of about 84%, training time, and testing time reduction of about 63% and 70% at the same accuracy. This study solves the key problem of SNN based HSI classification algorithms, which has important practical significance for promoting the practical application of HSI classification algorithms in edge devices such as spaceborne and airborne devices.
Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) are two dominant models for image analysis. While CNNs excel at extracting multi-scale features and ViTs effectively capture global dependencies, both suffer from high computational costs, particularly when processing high-resolution images. Recently, state-space models (SSMs) and recurrent neural networks (RNNs) have attracted attention due to their efficiency. However, their performance in image classification tasks remains limited. To address these challenges, this paper introduces VisionGRU, a novel RNN-based architecture designed for efficient image classification. VisionGRU leverages a simplified Gated Recurrent Unit (minGRU) to process large-scale image features with linear complexity. It divides images into smaller patches and progressively reduces the sequence length while increasing the channel depth, thus facilitating multi-scale feature extraction. A hierarchical 2DGRU module with bidirectional scanning captures both local and global contexts, improving long-range dependency modeling, particularly for tasks like semantic segmentation. Experimental results on the ImageNet and ADE20K datasets demonstrate that VisionGRU outperforms ViTs, significantly reducing memory usage and computational costs, especially for high-resolution images. These findings underscore the potential of RNN-based approaches for developing efficient and scalable computer vision solutions. Codes will be available at https://github.com/YangLiu9208/VisionGRU.
We propose a test-time defense mechanism against adversarial attacks: imperceptible image perturbations that significantly alter the predictions of a model. Unlike existing methods that rely on feature filtering or smoothing, which can lead to information loss, we propose to "combat noise with noise" by leveraging stochastic resonance to enhance robustness while minimizing information loss. Our approach introduces small translational perturbations to the input image, aligns the transformed feature embeddings, and aggregates them before mapping back to the original reference image. This can be expressed in a closed-form formula, which can be deployed on diverse existing network architectures without introducing additional network modules or fine-tuning for specific attack types. The resulting method is entirely training-free, architecture-agnostic, and attack-agnostic. Empirical results show state-of-the-art robustness on image classification and, for the first time, establish a generic test-time defense for dense prediction tasks, including stereo matching and optical flow, highlighting the method's versatility and practicality. Specifically, relative to clean (unperturbed) performance, our method recovers up to 68.1% of the accuracy loss on image classification, 71.9% on stereo matching, and 29.2% on optical flow under various types of adversarial attacks.
This paper presents a novel method which simultaneously learns the number of filters and network features repeatedly over multiple epochs. We propose a novel pruning loss to explicitly enforces the optimizer to focus on promising candidate filters while suppressing contributions of less relevant ones. In the meanwhile, we further propose to enforce the diversities between filters and this diversity-based regularization term improves the trade-off between model sizes and accuracies. It turns out the interplay between architecture and feature optimizations improves the final compressed models, and the proposed method is compared favorably to existing methods, in terms of both models sizes and accuracies for a wide range of applications including image classification, image compression and audio classification.
As deep neural networks achieve unprecedented performance in various tasks, neural architecture search (NAS), a research field for designing neural network architectures with automated processes, is actively underway. More recently, differentiable NAS has a great impact by reducing the search cost to the level of training a single network. Besides, the search space that defines candidate architectures to be searched directly affects the performance of the final architecture. In this paper, we propose an adaptation scheme of the search space by introducing a search scope. The effectiveness of proposed method is demonstrated with ProxylessNAS for the image classification task. Furthermore, we visualize the trajectory of architecture parameter updates and provide insights to improve the architecture search.
In recent years, Convolutional Neural Networks (CNNs) have been widely adopted in computer vision. Complex CNN architecture running on CPU or GPU has either insufficient throughput or prohibitive power consumption. Hence, there is a need to have dedicated hardware to accelerate the computation workload to solve these limitations. In this paper, we accelerate a CNN for image classification with the CIFAR-10 dataset using Vitis-AI on Xilinx Zynq UltraScale+ MPSoC ZCU104 FPGA evaluation board. The work achieves 3.33-5.82x higher throughput and 3.39-6.30x higher energy efficiency than CPU and GPU baselines. It shows the potential to extract 2D features for downstream tasks, such as depth estimation and 3D reconstruction.
This paper introduces AdaptoVision, a novel convolutional neural network (CNN) architecture designed to efficiently balance computational complexity and classification accuracy. By leveraging enhanced residual units, depth-wise separable convolutions, and hierarchical skip connections, AdaptoVision significantly reduces parameter count and computational requirements while preserving competitive performance across various benchmark and medical image datasets. Extensive experimentation demonstrates that AdaptoVision achieves state-of-the-art on BreakHis dataset and comparable accuracy levels, notably 95.3\% on CIFAR-10 and 85.77\% on CIFAR-100, without relying on any pretrained weights. The model's streamlined architecture and strategic simplifications promote effective feature extraction and robust generalization, making it particularly suitable for deployment in real-time and resource-constrained environments.
Current rock engineering design in drill and blast tunnelling primarily relies on engineers' observational assessments. Measure While Drilling (MWD) data, a high-resolution sensor dataset collected during tunnel excavation, is underutilised, mainly serving for geological visualisation. This study aims to automate the translation of MWD data into actionable metrics for rock engineering. It seeks to link data to specific engineering actions, thus providing critical decision support for geological challenges ahead of the tunnel face. Leveraging a large and geologically diverse dataset of 500,000 drillholes from 15 tunnels, the research introduces models for accurate rock mass quality classification in a real-world tunnelling context. Both conventional machine learning and image-based deep learning are explored to classify MWD data into Q-classes and Q-values, examples of metrics describing the stability of the rock mass, using both tabular and image data. The results indicate that the K-nearest neighbours algorithm in an ensemble with tree-based models using tabular data, effectively classifies rock mass quality. It achieves a cross-validated balanced accuracy of 0.86 in classifying rock mass into the Q-classes A, B, C, D, E1, E2, and 0.95 for a binary classification with E versus the rest. Classification using a CNN with MWD-images for each blasting round resulted in a balanced accuracy of 0.82 for binary classification. Regressing the Q-value from tabular MWD-data achieved cross-validated R2 and MSE scores of 0.80 and 0.18 for a similar ensemble model as in classification. High performance in regression and classification boosts confidence in automated rock mass assessment. Applying advanced modelling on a unique dataset demonstrates MWD data's value in improving rock mass classification accuracy and advancing data-driven rock engineering design, reducing manual intervention.
Multimodal information processing has become increasingly important for enhancing image classification performance. However, the intricate and implicit dependencies across different modalities often hinder conventional methods from effectively capturing fine-grained semantic interactions, thereby limiting their applicability in high-precision classification tasks. To address this issue, we propose a novel Multimodal Collaborative Fusion Network (MCFNet) designed for fine-grained classification. The proposed MCFNet architecture incorporates a regularized integrated fusion module that improves intra-modal feature representation through modality-specific regularization strategies, while facilitating precise semantic alignment via a hybrid attention mechanism. Additionally, we introduce a multimodal decision classification module, which jointly exploits inter-modal correlations and unimodal discriminative features by integrating multiple loss functions within a weighted voting paradigm. Extensive experiments and ablation studies on benchmark datasets demonstrate that the proposed MCFNet framework achieves consistent improvements in classification accuracy, confirming its effectiveness in modeling subtle cross-modal semantics.
In this paper we combine an approach based on Runge-Kutta Nets considered in [Benning et al., J. Comput. Dynamics, 9, 2019] and a technique on augmenting the input space in [Dupont et al., NeurIPS, 2019] to obtain network architectures which show a better numerical performance for deep neural networks in point and image classification problems. The approach is illustrated with several examples implemented in PyTorch.
While using two-dimensional convolutional neural networks (2D-CNNs) in image processing, it is possible to manipulate domain information using channel statistics, and instance normalization has been a promising way to get domain-invariant features. However, unlike image processing, we analyze that domain-relevant information in an audio feature is dominant in frequency statistics rather than channel statistics. Motivated by our analysis, we introduce Relaxed Instance Frequency-wise Normalization (RFN): a plug-and-play, explicit normalization module along the frequency axis which can eliminate instance-specific domain discrepancy in an audio feature while relaxing undesirable loss of useful discriminative information. Empirically, simply adding RFN to networks shows clear margins compared to previous domain generalization approaches on acoustic scene classification and yields improved robustness for multiple audio devices. Especially, the proposed RFN won the DCASE2021 challenge TASK1A, low-complexity acoustic scene classification with multiple devices, with a clear margin, and RFN is an extended work of our technical report.