Language-guided attention frameworks have significantly enhanced both interpretability and performance in image classification; however, the reliance on deterministic embeddings from pre-trained vision-language foundation models to generate reference attention maps frequently overlooks the intrinsic multivaluedness and ill-posed characteristics of cross-modal mappings. To address these limitations, we introduce PARIC, a probabilistic framework for guiding visual attention via language specifications. Our approach enables pre-trained vision-language models to generate probabilistic reference attention maps, which align textual and visual modalities more effectively while incorporating uncertainty estimates, as compared to their deterministic counterparts. Experiments on benchmark test problems demonstrate that PARIC enhances prediction accuracy, mitigates bias, ensures consistent predictions, and improves robustness across various datasets.
Although neural networks perform very well on the image classification task, they are still vulnerable to adversarial perturbations that can fool a neural network without visibly changing an input image. A paper has shown the existence of Universal Adversarial Perturbations which when added to any image will fool the neural network with a very high probability. In this paper we will try to reproduce the experience of the Universal Adversarial Perturbations paper, but on a smaller neural network architecture and training set, in order to be able to study the efficiency of the computed perturbation.
With the development of deep learning, supervised learning methods perform well in remote sensing images (RSIs) scene classification. However, supervised learning requires a huge number of annotated data for training. When labeled samples are not sufficient, the most common solution is to fine-tune the pre-training models using a large natural image dataset (e.g. ImageNet). However, this learning paradigm is not a panacea, especially when the target remote sensing images (e.g. multispectral and hyperspectral data) have different imaging mechanisms from RGB natural images. To solve this problem, we introduce new self-supervised learning (SSL) mechanism to obtain the high-performance pre-training model for RSIs scene classification from large unlabeled data. Experiments on three commonly used RSIs scene classification datasets demonstrated that this new learning paradigm outperforms the traditional dominant ImageNet pre-trained model. Moreover, we analyze the impacts of several factors in SSL on RSIs scene classification tasks, including the choice of self-supervised signals, the domain difference between the source and target dataset, and the amount of pre-training data. The insights distilled from our studies can help to foster the development of SSL in the remote sensing community. Since SSL could learn from unlabeled massive RSIs which are extremely easy to obtain, it will be a potentially promising way to alleviate dependence on labeled samples and thus efficiently solve many problems, such as global mapping.
Many fine-grained classification tasks, like rare animal identification, have limited training data and consequently classifiers trained on these datasets often fail to generalize to variations in the domain like changes in weather or location. As such, we explore how natural language descriptions of the domains seen in training data can be used with large vision models trained on diverse pretraining datasets to generate useful variations of the training data. We introduce ALIA (Automated Language-guided Image Augmentation), a method which utilizes large vision and language models to automatically generate natural language descriptions of a dataset's domains and augment the training data via language-guided image editing. To maintain data integrity, a model trained on the original dataset filters out minimal image edits and those which corrupt class-relevant information. The resulting dataset is visually consistent with the original training data and offers significantly enhanced diversity. We show that ALIA is able to surpasses traditional data augmentation and text-to-image generated data on fine-grained classification tasks, including cases of domain generalization and contextual bias. Code is available at https://github.com/lisadunlap/ALIA.
In multiclass deep network classifiers, the burden of classifying samples of different classes is put on a single classifier. As the result the optimum classification accuracy is not obtained. Also training times are large due to running the CNN training on single CPU/GPU. However it is known that using ensembles of classifiers increases the performance. Also, the training times can be reduced by running each member of the ensemble on a separate processor. Ensemble learning has been used in the past for traditional methods to a varying extent and is a hot topic. With the advent of deep learning, ensemble learning has been applied to the former as well. However, an area which is unexplored and has potential is One-Versus-All (OVA) deep ensemble learning. In this paper we explore it and show that by using OVA ensembles of deep networks, improvements in performance of deep networks can be obtained. As shown in this paper, the classification capability of deep networks can be further increased by using an ensemble of binary classification (OVA) deep networks. We implement a novel technique for the case of digit image recognition and test and evaluate it on the same. In the proposed approach, a single OVA deep network classifier is dedicated to each category. Subsequently, OVA deep network ensembles have been investigated. Every network in an ensemble has been trained by an OVA training technique using the Stochastic Gradient Descent with Momentum Algorithm (SGDMA). For classification of a test sample, the sample is presented to each network in the ensemble. After prediction score voting, the network with the largest score is assumed to have classified the sample. The experimentation has been done on the MNIST digit dataset, the USPS+ digit dataset, and MATLAB digit image dataset. Our proposed technique outperforms the baseline on digit image recognition for all datasets.
Any-shot image classification allows to recognize novel classes with only a few or even zero samples. For the task of zero-shot learning, visual attributes have been shown to play an important role, while in the few-shot regime, the effect of attributes is under-explored. To better transfer attribute-based knowledge from seen to unseen classes, we argue that an image representation with integrated attribute localization ability would be beneficial for any-shot, i.e. zero-shot and few-shot, image classification tasks. To this end, we propose a novel representation learning framework that jointly learns discriminative global and local features using only class-level attributes. While a visual-semantic embedding layer learns global features, local features are learned through an attribute prototype network that simultaneously regresses and decorrelates attributes from intermediate features. Furthermore, we introduce a zoom-in module that localizes and crops the informative regions to encourage the network to learn informative features explicitly. We show that our locality augmented image representations achieve a new state-of-the-art on challenging benchmarks, i.e. CUB, AWA2, and SUN. As an additional benefit, our model points to the visual evidence of the attributes in an image, confirming the improved attribute localization ability of our image representation. The attribute localization is evaluated quantitatively with ground truth part annotations, qualitatively with visualizations, and through well-designed user studies.
Despite that deep learning methods have achieved remarkable performance in pathology image classification, they heavily rely on labeled data, demanding extensive human annotation efforts. In this study, we present a novel human annotation-free method for pathology image classification by leveraging pre-trained Vision-Language Models (VLMs). Without human annotation, pseudo labels of the training set are obtained by utilizing the zero-shot inference capabilities of VLM, which may contain a lot of noise due to the domain shift between the pre-training data and the target dataset. To address this issue, we introduce VLM-CPL, a novel approach based on consensus pseudo labels that integrates two noisy label filtering techniques with a semi-supervised learning strategy. Specifically, we first obtain prompt-based pseudo labels with uncertainty estimation by zero-shot inference with the VLM using multiple augmented views of an input. Then, by leveraging the feature representation ability of VLM, we obtain feature-based pseudo labels via sample clustering in the feature space. Prompt-feature consensus is introduced to select reliable samples based on the consensus between the two types of pseudo labels. By rejecting low-quality pseudo labels, we further propose High-confidence Cross Supervision (HCS) to learn from samples with reliable pseudo labels and the remaining unlabeled samples. Experimental results showed that our method obtained an accuracy of 87.1% and 95.1% on the HPH and LC25K datasets, respectively, and it largely outperformed existing zero-shot classification and noisy label learning methods. The code is available at https://github.com/lanfz2000/VLM-CPL.
Pavement Distress Recognition (PDR) is an important step in pavement inspection and can be powered by image-based automation to expedite the process and reduce labor costs. Pavement images are often in high-resolution with a low ratio of distressed to non-distressed areas. Advanced approaches leverage these properties via dividing images into patches and explore discriminative features in the scale space. However, these approaches usually suffer from information loss during image resizing and low efficiency due to complex learning frameworks. In this paper, we propose a novel and efficient method for PDR. A light network named the Kernel Inversed Pyramidal Resizing Network (KIPRN) is introduced for image resizing, and can be flexibly plugged into the image classification network as a pre-network to exploit resolution and scale information. In KIPRN, pyramidal convolution and kernel inversed convolution are specifically designed to mine discriminative information across different feature granularities and scales. The mined information is passed along to the resized images to yield an informative image pyramid to assist the image classification network for PDR. We applied our method to three well-known Convolutional Neural Networks (CNNs), and conducted an evaluation on a large-scale pavement image dataset named CQU-BPDD. Extensive results demonstrate that KIPRN can generally improve the pavement distress recognition of these CNN models and show that the simple combination of KIPRN and EfficientNet-B3 significantly outperforms the state-of-the-art patch-based method in both performance and efficiency.
Multiple instance learning (MIL)-based framework has become the mainstream for processing the whole slide image (WSI) with giga-pixel size and hierarchical image context in digital pathology. However, these methods heavily depend on a substantial number of bag-level labels and solely learn from the original slides, which are easily affected by variations in data distribution. Recently, vision language model (VLM)-based methods introduced the language prior by pre-training on large-scale pathological image-text pairs. However, the previous text prompt lacks the consideration of pathological prior knowledge, therefore does not substantially boost the model's performance. Moreover, the collection of such pairs and the pre-training process are very time-consuming and source-intensive.To solve the above problems, we propose a dual-scale vision-language multiple instance learning (ViLa-MIL) framework for whole slide image classification. Specifically, we propose a dual-scale visual descriptive text prompt based on the frozen large language model (LLM) to boost the performance of VLM effectively. To transfer the VLM to process WSI efficiently, for the image branch, we propose a prototype-guided patch decoder to aggregate the patch features progressively by grouping similar patches into the same prototype; for the text branch, we introduce a context-guided text decoder to enhance the text features by incorporating the multi-granular image contexts. Extensive studies on three multi-cancer and multi-center subtyping datasets demonstrate the superiority of ViLa-MIL.
Recent text-to-image generative models such as Stable Diffusion are extremely adept at mimicking and generating copyrighted content, raising concerns amongst artists that their unique styles may be improperly copied. Understanding how generative models copy "artistic style" is more complex than duplicating a single image, as style is comprised by a set of elements (or signature) that frequently co-occurs across a body of work, where each individual work may vary significantly. In our paper, we first reformulate the problem of "artistic copyright infringement" to a classification problem over image sets, instead of probing image-wise similarities. We then introduce ArtSavant, a practical (i.e., efficient and easy to understand) tool to (i) determine the unique style of an artist by comparing it to a reference dataset of works from 372 artists curated from WikiArt, and (ii) recognize if the identified style reappears in generated images. We leverage two complementary methods to perform artistic style classification over image sets, includingTagMatch, which is a novel inherently interpretable and attributable method, making it more suitable for broader use by non-technical stake holders (artists, lawyers, judges, etc). Leveraging ArtSavant, we then perform a large-scale empirical study to provide quantitative insight on the prevalence of artistic style copying across 3 popular text-to-image generative models. Namely, amongst a dataset of prolific artists (including many famous ones), only 20% of them appear to have their styles be at a risk of copying via simple prompting of today's popular text-to-image generative models.
The early detection and timely treatment of breast cancer can save lives. Mammography is one of the most efficient approaches to screening early breast cancer. An automatic mammographic image classification method could improve the work efficiency of radiologists. Current deep learning-based methods typically use the traditional softmax loss to optimize the feature extraction part, which aims to learn the features of mammographic images. However, previous studies have shown that the feature extraction part cannot learn discriminative features from complex data using the standard softmax loss. In this paper, we design a new architecture and propose respective loss functions. Specifically, we develop a double-classifier network architecture that constrains the extracted features’ distribution by changing the classifiers’ decision boundaries. Then, we propose the double-classifier constraint loss function to constrain the decision boundaries so that the feature extraction part can learn discriminative features. Furthermore, by taking advantage of the architecture of two classifiers, the neural network can detect the difficult-to-classify samples. We propose a weighted double-classifier constraint method to make the feature extract part pay more attention to learning difficult-to-classify samples’ features. Our proposed method can be easily applied to an existing convolutional neural network to improve mammographic image classification performance. We conducted extensive experiments to evaluate our methods on three public benchmark mammographic image datasets. The results showed that our methods outperformed many other similar methods and state-of-the-art methods on the three public medical benchmarks. Our code and weights can be found on GitHub.
Food image classification systems play a crucial role in health monitoring and diet tracking through image-based dietary assessment techniques. However, existing food recognition systems rely on static datasets characterized by a pre-defined fixed number of food classes. This contrasts drastically with the reality of food consumption, which features constantly changing data. Therefore, food image classification systems should adapt to and manage data that continuously evolves. This is where continual learning plays an important role. A challenge in continual learning is catastrophic forgetting, where ML models tend to discard old knowledge upon learning new information. While memory-replay algorithms have shown promise in mitigating this problem by storing old data as exemplars, they are hampered by the limited capacity of memory buffers, leading to an imbalance between new and previously learned data. To address this, our work explores the use of neural image compression to extend buffer size and enhance data diversity. We introduced the concept of continuously learning a neural compression model to adaptively improve the quality of compressed data and optimize the bitrates per pixel (bpp) to store more exemplars. Our extensive experiments, including evaluations on food-specific datasets including Food-101 and VFN-74, as well as the general dataset ImageNet-100, demonstrate improvements in classification accuracy. This progress is pivotal in advancing more realistic food recognition systems that are capable of adapting to continually evolving data. Moreover, the principles and methodologies we've developed hold promise for broader applications, extending their benefits to other domains of continual machine learning systems.
Action classification in still images has been a popular research topic in computer vision. Labelling large scale datasets for action classification requires tremendous manual work, which is hard to scale up. Besides, the action categories in such datasets are pre-defined and vocabularies are fixed. However humans may describe the same action with different phrases, which leads to the difficulty of vocabulary expansion for traditional fully-supervised methods. We observe that large amounts of images with sentence descriptions are readily available on the Internet. The sentence descriptions can be regarded as weak labels for the images, which contain rich information and could be used to learn flexible expressions of action categories. We propose a method to learn an Action Concept Tree (ACT) and an Action Semantic Alignment (ASA) model for classification from image-description data via a two-stage learning process. A new dataset for the task of learning actions from descriptions is built. Experimental results show that our method outperforms several baseline methods significantly.
Genuine leather, such as the hides of cows, crocodiles, lizards and goats usually contain natural and artificial defects, like holes, fly bites, tick marks, veining, cuts, wrinkles and others. A traditional solution to identify the defects is by manual defect inspection, which involves skilled experts. It is time consuming and may incur a high error rate and results in low productivity. This paper presents a series of automatic image processing processes to perform the classification of leather defects by adopting deep learning approaches. Particularly, the leather images are first partitioned into small patches,then it undergoes a pre-processing technique, namely the Canny edge detection to enhance defect visualization. Next, artificial neural network (ANN) and convolutional neural network (CNN) are employed to extract the rich image features. The best classification result achieved is 80.3 %, evaluated on a data set that consists of 2000 samples. In addition, the performance metrics such as confusion matrix and Receiver Operating Characteristic (ROC) are reported to demonstrate the efficiency of the method proposed.
With the complexity of the network structure, uncertainty inference has become an important task to improve the classification accuracy for artificial intelligence systems. For image classification tasks, we propose a structured DropConnect (SDC) framework to model the output of a deep neural network by a Dirichlet distribution. We introduce a DropConnect strategy on weights in the fully connected layers during training. In test, we split the network into several sub-networks, and then model the Dirichlet distribution by match its moments with the mean and variance of the outputs of these sub-networks. The entropy of the estimated Dirichlet distribution is finally utilized for uncertainty inference. In this paper, this framework is implemented on LeNet$5$ and VGG$16$ models for misclassification detection and out-of-distribution detection on MNIST and CIFAR-$10$ datasets. Experimental results show that the performance of the proposed SDC can be comparable to other uncertainty inference methods. Furthermore, the SDC is adapted well to different network structures with certain generalization capabilities and research prospects.
Image analysis technologies empowered by artificial intelligence (AI) have proved images and videos to be an opportune source of data to learn about humpback whale (Megaptera novaeangliae) population sizes and dynamics. With the advent of social media, platforms such as YouTube present an abundance of video data across spatiotemporal contexts documenting humpback whale encounters from users worldwide. In our work, we focus on automating the classification of YouTube videos as relevant or irrelevant based on whether they document a true humpback whale encounter or not via deep learning. We use a CNN-RNN architecture pretrained on the ImageNet dataset for classification of YouTube videos as relevant or irrelevant. We achieve an average 85.7% accuracy, and 84.7% (irrelevant)/ 86.6% (relevant) F1 scores using five-fold cross validation for evaluation on the dataset. We show that deep learning can be used as a time-efficient step to make social media a viable source of image and video data for biodiversity assessments.
Optical and hybrid convolutional neural networks (CNNs) recently have become of increasing interest to achieve low-latency, low-power image classification and computer vision tasks. However, implementing optical nonlinearity is challenging, and omitting the nonlinear layers in a standard CNN comes at a significant reduction in accuracy. In this work, we use knowledge distillation to compress modified AlexNet to a single linear convolutional layer and an electronic backend (two fully connected layers). We obtain comparable performance to a purely electronic CNN with five convolutional layers and three fully connected layers. We implement the convolution optically via engineering the point spread function of an inverse-designed meta-optic. Using this hybrid approach, we estimate a reduction in multiply-accumulate operations from 17M in a conventional electronic modified AlexNet to only 86K in the hybrid compressed network enabled by the optical frontend. This constitutes over two orders of magnitude reduction in latency and power consumption. Furthermore, we experimentally demonstrate that the classification accuracy of the system exceeds 93% on the MNIST dataset.
In the field of integrated circuit manufacturing, the detection and classification of nanoscale wafer defects are critical for subsequent root cause analysis and yield enhancement. The complex background patterns observed in scanning electron microscope (SEM) images and the diverse textures of the defects pose significant challenges. Traditional methods usually suffer from insufficient data, labels, and poor transferability. In this paper, we propose a novel few-shot learning approach, SEM-CLIP, for accurate defect classification and segmentation. SEM-CLIP customizes the Contrastive Language-Image Pretraining (CLIP) model to better focus on defect areas and minimize background distractions, thereby enhancing segmentation accuracy. We employ text prompts enriched with domain knowledge as prior information to assist in precise analysis. Additionally, our approach incorporates feature engineering with textual guidance to categorize defects more effectively. SEM-CLIP requires little annotated data, substantially reducing labor demands in the semiconductor industry. Extensive experimental validation demonstrates that our model achieves impressive classification and segmentation results under few-shot learning scenarios.
In this paper, the problem of classifying synthetic and natural texture images is addressed. To tackle this problem, an innovative method is proposed that combines concepts from corrosion modeling and cellular automata to generate a texture descriptor. The core processes of metal (pitting) corrosion are identified and applied to texture images by incorporating the basic mechanisms of corrosion in the transition function of the cellular automaton. The surface morphology of the image is analyzed before and during the application of the transition function of the cellular automaton. In each iteration the cumulative mass of corroded product is obtained to construct each of the attributes of the texture descriptor. In a final step, this texture descriptor is used for image classification by applying Linear Discriminant Analysis. The method was tested on the well-known Brodatz and Vistex databases. In addition, in order to verify the robustness of the method, its invariance to noise and rotation were tested. To that end, different variants of the original two databases were obtained through addition of noise to and rotation of the images. The results showed that the method is effective for texture classification according to the high success rates obtained in all cases. This indicates the potential of employing methods inspired on natural phenomena in other fields.
Recent breakthroughs in object detection and image classification using Convolutional Neural Networks (CNNs) are revolutionizing the state of the art in medical imaging, and microscopy in particular presents abundant opportunities for computer vision algorithms to assist medical professionals in diagnosis of diseases ranging from malaria to cancer. High resolution scans of microscopy slides called Whole Slide Images (WSIs) offer enough information for a cancer pathologist to come to a conclusion regarding cancer presence, subtype, and severity based on measurements of features within the slide image at multiple scales and resolutions. WSIs' extremely high resolutions and feature scales ranging from gross anatomical structures down to cell nuclei preclude the use of standard CNN models for object detection and classification, which have typically been designed for images with dimensions in the hundreds of pixels and with objects on the order of the size of the image itself. We explore parallel approaches based on Reinforcement Learning and Beam Search to learn to progressively zoom into the WSI to detect Regions of Interest (ROIs) in liver pathology slides containing one of two types of liver cancer, namely Hepatocellular Carcinoma (HCC) and Cholangiocarcinoma (CC). These ROIs can then be presented directly to the pathologist to aid in measurement and diagnosis or be used for automated classification of tumor subtype.