We propose a unified game-theoretical framework to perform classification and conditional image generation given limited supervision. It is formulated as a three-player minimax game consisting of a generator, a classifier and a discriminator, and therefore is referred to as Triple Generative Adversarial Network (Triple-GAN). The generator and the classifier characterize the conditional distributions between images and labels to perform conditional generation and classification, respectively. The discriminator solely focuses on identifying fake image-label pairs. Under a nonparametric assumption, we prove the unique equilibrium of the game is that the distributions characterized by the generator and the classifier converge to the data distribution. As a byproduct of the three-player mechanism, Triple-GAN is flexible to incorporate different semi-supervised classifiers and GAN architectures. We evaluate Triple-GAN in two challenging settings, namely, semi-supervised learning and the extreme low data regime. In both settings, Triple-GAN can achieve excellent classification results and generate meaningful samples in a specific class simultaneously. In particular, using a commonly adopted 13-layer CNN classifier, Triple-GAN outperforms extensive semi-supervised learning methods substantially on more than 10 benchmarks no matter data augmentation is applied or not.
Weakly supervised object detection (WSup-OD) increases the usefulness and interpretability of image classification algorithms without requiring additional supervision. The successes of multiple instance learning in this task for natural images, however, do not translate well to medical images due to the very different characteristics of their objects (i.e. pathologies). In this work, we propose Weakly Supervised ROI Proposal Networks (WSRPN), a new method for generating bounding box proposals on the fly using a specialized region of interest-attention (ROI-attention) module. WSRPN integrates well with classic backbone-head classification algorithms and is end-to-end trainable with only image-label supervision. We experimentally demonstrate that our new method outperforms existing methods in the challenging task of disease localization in chest X-ray images. Code: https://github.com/philip-mueller/wsrpn
Tensor networks provide an efficient approximation of operations involving high dimensional tensors and have been extensively used in modelling quantum many-body systems. More recently, supervised learning has been attempted with tensor networks, primarily focused on tasks such as image classification. In this work, we propose a novel formulation of tensor networks for supervised image segmentation which allows them to operate on high resolution medical images. We use the matrix product state (MPS) tensor network on non-overlapping patches of a given input image to predict the segmentation mask by learning a pixel-wise linear classification rule in a high dimensional space. The proposed model is end-to-end trainable using backpropagation. It is implemented as a Strided Tensor Network to reduce the parameter complexity. The performance of the proposed method is evaluated on two public medical imaging datasets and compared to relevant baselines. The evaluation shows that the strided tensor network yields competitive performance compared to CNN-based models while using fewer resources. Additionally, based on the experiments we discuss the feasibility of using fully linear models for segmentation tasks.
We aim at advancing blind image quality assessment (BIQA), which predicts the human perception of image quality without any reference information. We develop a general and automated multitask learning scheme for BIQA to exploit auxiliary knowledge from other tasks, in a way that the model parameter sharing and the loss weighting are determined automatically. Specifically, we first describe all candidate label combinations (from multiple tasks) using a textual template, and compute the joint probability from the cosine similarities of the visual-textual embeddings. Predictions of each task can be inferred from the joint distribution, and optimized by carefully designed loss functions. Through comprehensive experiments on learning three tasks - BIQA, scene classification, and distortion type identification, we verify that the proposed BIQA method 1) benefits from the scene classification and distortion type identification tasks and outperforms the state-of-the-art on multiple IQA datasets, 2) is more robust in the group maximum differentiation competition, and 3) realigns the quality annotations from different IQA datasets more effectively. The source code is available at https://github.com/zwx8981/LIQE.
Spiking Neural Networks (SNNs) have emerged as a compelling, energy-efficient alternative to traditional Artificial Neural Networks (ANNs) for static image tasks such as image classification and segmentation. However, in the more complex video classification domain, SNN-based methods fall considerably short of ANN-based benchmarks due to the challenges in processing dense frame sequences. To bridge this gap, we propose ReSpike, a hybrid framework that synergizes the strengths of ANNs and SNNs to tackle action recognition tasks with high accuracy and low energy cost. By decomposing film clips into spatial and temporal components, i.e., RGB image Key Frames and event-like Residual Frames, ReSpike leverages ANN for learning spatial information and SNN for learning temporal information. In addition, we propose a multi-scale cross-attention mechanism for effective feature fusion. Compared to state-of-the-art SNN baselines, our ReSpike hybrid architecture demonstrates significant performance improvements (e.g., >30% absolute accuracy improvement on HMDB-51, UCF-101, and Kinetics-400). Furthermore, ReSpike achieves comparable performance with prior ANN approaches while bringing better accuracy-energy tradeoff.
Self-supervised bidirectional transformer models such as BERT have led to dramatic improvements in a wide variety of textual classification tasks. The modern digital world is increasingly multimodal, however, and textual information is often accompanied by other modalities such as images. We introduce a supervised multimodal bitransformer model that fuses information from text and image encoders, and obtain state-of-the-art performance on various multimodal classification benchmark tasks, outperforming strong baselines, including on hard test sets specifically designed to measure multimodal performance.
Data curation is the problem of how to collect and organize samples into a dataset that supports efficient learning. Despite the centrality of the task, little work has been devoted towards a large-scale, systematic comparison of various curation methods. In this work, we take steps towards a formal evaluation of data curation strategies and introduce SELECT, the first large-scale benchmark of curation strategies for image classification. In order to generate baseline methods for the SELECT benchmark, we create a new dataset, ImageNet++, which constitutes the largest superset of ImageNet-1K to date. Our dataset extends ImageNet with 5 new training-data shifts, each approximately the size of ImageNet-1K itself, and each assembled using a distinct curation strategy. We evaluate our data curation baselines in two ways: (i) using each training-data shift to train identical image classification models from scratch (ii) using the data itself to fit a pretrained self-supervised representation. Our findings show interesting trends, particularly pertaining to recent methods for data curation such as synthetic data generation and lookup based on CLIP embeddings. We show that although these strategies are highly competitive for certain tasks, the curation strategy used to assemble the original ImageNet-1K dataset remains the gold standard. We anticipate that our benchmark can illuminate the path for new methods to further reduce the gap. We release our checkpoints, code, documentation, and a link to our dataset at https://github.com/jimmyxu123/SELECT.
Images captured from the real world are often affected by different types of noise, which can significantly impact the performance of Computer Vision systems and the quality of visual data. This study presents a novel approach for defect detection in casting product noisy images, specifically focusing on submersible pump impellers. The methodology involves utilizing deep learning models such as VGG16, InceptionV3, and other models in both the spatial and frequency domains to identify noise types and defect status. The research process begins with preprocessing images, followed by applying denoising techniques tailored to specific noise categories. The goal is to enhance the accuracy and robustness of defect detection by integrating noise detection and denoising into the classification pipeline. The study achieved remarkable results using VGG16 for noise type classification in the frequency domain, achieving an accuracy of over 99%. Removal of salt and pepper noise resulted in an average SSIM of 87.9, while Gaussian noise removal had an average SSIM of 64.0, and periodic noise removal yielded an average SSIM of 81.6. This comprehensive approach showcases the effectiveness of the deep AutoEncoder model and median filter, for denoising strategies in real-world industrial applications. Finally, our study reports significant improvements in binary classification accuracy for defect detection compared to previous methods. For the VGG16 classifier, accuracy increased from 94.6% to 97.0%, demonstrating the effectiveness of the proposed noise detection and denoising approach. Similarly, for the InceptionV3 classifier, accuracy improved from 84.7% to 90.0%, further validating the benefits of integrating noise analysis into the classification pipeline.
This paper investigates strategies that defend against adversarial-example attacks on image-classification systems by transforming the inputs before feeding them to the system. Specifically, we study applying image transformations such as bit-depth reduction, JPEG compression, total variance minimization, and image quilting before feeding the image to a convolutional network classifier. Our experiments on ImageNet show that total variance minimization and image quilting are very effective defenses in practice, in particular, when the network is trained on transformed images. The strength of those defenses lies in their non-differentiable nature and their inherent randomness, which makes it difficult for an adversary to circumvent the defenses. Our best defense eliminates 60% of strong gray-box and 90% of strong black-box attacks by a variety of major attack methods
Semi-supervised learning (SSL) has attracted much attention since it reduces the expensive costs of collecting adequate well-labeled training data, especially for deep learning methods. However, traditional SSL is built upon an assumption that labeled and unlabeled data should be from the same distribution \textit{e.g.,} classes and domains. However, in practical scenarios, unlabeled data would be from unseen classes or unseen domains, and it is still challenging to exploit them by existing SSL methods. Therefore, in this paper, we proposed a unified framework to leverage these unseen unlabeled data for open-scenario semi-supervised medical image classification. We first design a novel scoring mechanism, called dual-path outliers estimation, to identify samples from unseen classes. Meanwhile, to extract unseen-domain samples, we then apply an effective variational autoencoder (VAE) pre-training. After that, we conduct domain adaptation to fully exploit the value of the detected unseen-domain samples to boost semi-supervised training. We evaluated our proposed framework on dermatology and ophthalmology tasks. Extensive experiments demonstrate our model can achieve superior classification performance in various medical SSL scenarios. The code implementations are accessible at: https://github.com/PyJulie/USSL4MIC.
Proximally-sensed laser scanning offers significant potential for automated forest data capture, but challenges remain in automatically identifying tree species without additional ground data. Deep learning (DL) shows promise for automation, yet progress is slowed by the lack of large, diverse, openly available labeled datasets of single tree point clouds. This has impacted the robustness of DL models and the ability to establish best practices for species classification. To overcome these challenges, the FOR-species20K benchmark dataset was created, comprising over 20,000 tree point clouds from 33 species, captured using terrestrial (TLS), mobile (MLS), and drone laser scanning (ULS) across various European forests, with some data from other regions. This dataset enables the benchmarking of DL models for tree species classification, including both point cloud-based (PointNet++, MinkNet, MLP-Mixer, DGCNNs) and multi-view image-based methods (SimpleView, DetailView, YOLOv5). 2D image-based models generally performed better (average OA = 0.77) than 3D point cloud-based models (average OA = 0.72), with consistent results across different scanning platforms and sensors. The top model, DetailView, was particularly robust, handling data imbalances well and generalizing effectively across tree sizes. The FOR-species20K dataset, available at https://zenodo.org/records/13255198, is a key resource for developing and benchmarking DL models for tree species classification using laser scanning data, providing a foundation for future advancements in the field.
Diffusion models have shown remarkable progress in various generative tasks such as image and video generation. This paper studies the problem of leveraging pretrained diffusion models for performing discriminative tasks. Specifically, we extend the discriminative capability of pretrained frozen generative diffusion models from the classification task to the more complex object detection task, by "inverting" a pretrained layout-to-image diffusion model. To this end, a gradient-based discrete optimization approach for replacing the heavy prediction enumeration process, and a prior distribution model for making more accurate use of the Bayes' rule, are proposed respectively. Empirical results show that this method is on par with basic discriminative object detection baselines on COCO dataset. In addition, our method can greatly speed up the previous diffusion-based method for classification without sacrificing accuracy. Code and models are available at https://github.com/LiYinqi/DIVE .
Visual classification can be divided into coarse-grained and fine-grained classification. Coarse-grained classification represents categories with a large degree of dissimilarity, such as the classification of cats and dogs, while fine-grained classification represents classifications with a large degree of similarity, such as cat species, bird species, and the makes or models of vehicles. Unlike coarse-grained visual classification, fine-grained visual classification often requires professional experts to label data, which makes data more expensive. To meet this challenge, many approaches propose to automatically find the most discriminative regions and use local features to provide more precise features. These approaches only require image-level annotations, thereby reducing the cost of annotation. However, most of these methods require two- or multi-stage architectures and cannot be trained end-to-end. Therefore, we propose a novel plug-in module that can be integrated to many common backbones, including CNN-based or Transformer-based networks to provide strongly discriminative regions. The plugin module can output pixel-level feature maps and fuse filtered features to enhance fine-grained visual classification. Experimental results show that the proposed plugin module outperforms state-of-the-art approaches and significantly improves the accuracy to 92.77\% and 92.83\% on CUB200-2011 and NABirds, respectively. We have released our source code in Github https://github.com/chou141253/FGVC-PIM.git.
Lithology discrimination is a crucial activity in characterizing oil reservoirs, and processing lithology microscopic images is an essential technique for investigating fossils and minerals and geological assessment of shale oil exploration. In this way, Deep Learning (DL) technique is a powerful approach for building robust classifier models. However, there is still a considerable challenge to collect and produce a large dataset. Transfer-learning and data augmentation techniques have emerged as popular approaches to tackle this problem. Furthermore, due to different reasons, especially data privacy, individuals, organizations, and industry companies often are not willing to share their sensitive data and information. Federated Learning (FL) has emerged to train a highly accurate central model across multiple decentralized edge servers without transferring sensitive data, preserving sensitive data, and enhancing security. This study involves two phases; the first phase is to conduct Lithology microscopic image classification on a small dataset using transfer learning. In doing so, various pre-trained DL model architectures are comprehensively compared for the classification task. In the second phase, we formulated the classification task to a Federated Transfer Learning (FTL) scheme and proposed a Fine-Tuned Aggregation strategy for Federated Learning (FTA-FTL). In order to perform a comprehensive experimental study, several metrics such as accuracy, f1 score, precision, specificity, sensitivity (recall), and confusion matrix are taken into account. The results are in excellent agreement and confirm the efficiency of the proposed scheme, and show that the proposed FTA-FTL algorithm is capable enough to achieve approximately the same results obtained by the centralized implementation for Lithology microscopic images classification task.
Multi-Label Remote Sensing Image Classification (MLRSIC) has received increasing research interest. Taking the cooccurrence relationship of multiple labels as additional information helps to improve the performance of this task. Current methods focus on using it to constrain the final feature output of a Convolutional Neural Network (CNN). On the one hand, these methods do not make full use of label correlation to form feature representation. On the other hand, they increase the label noise sensitivity of the system, resulting in poor robustness. In this paper, a novel method called Semantic Interleaving Global Channel Attention (SIGNA) is proposed for MLRSIC. First, the label co-occurrence graph is obtained according to the statistical information of the data set. The label co-occurrence graph is used as the input of the Graph Neural Network (GNN) to generate optimal feature representations. Then, the semantic features and visual features are interleaved, to guide the feature expression of the image from the original feature space to the semantic feature space with embedded label relations. SIGNA triggers global attention of feature maps channels in a new semantic feature space to extract more important visual features. Multihead SIGNA based feature adaptive weighting networks are proposed to act on any layer of CNN in a plug-and-play manner. For remote sensing images, better classification performance can be achieved by inserting CNN into the shallow layer. We conduct extensive experimental comparisons on three data sets: UCM data set, AID data set, and DFC15 data set. Experimental results demonstrate that the proposed SIGNA achieves superior classification performance compared to state-of-the-art (SOTA) methods. It is worth mentioning that the codes of this paper will be open to the community for reproducibility research. Our codes are available at https://github.com/kyle-one/SIGNA.
Most recent self-supervised methods for learning image representations focus on either producing a global feature with invariance properties, or producing a set of local features. The former works best for classification tasks while the latter is best for detection and segmentation tasks. This paper explores the fundamental trade-off between learning local and global features. A new method called VICRegL is proposed that learns good global and local features simultaneously, yielding excellent performance on detection and segmentation tasks while maintaining good performance on classification tasks. Concretely, two identical branches of a standard convolutional net architecture are fed two differently distorted versions of the same image. The VICReg criterion is applied to pairs of global feature vectors. Simultaneously, the VICReg criterion is applied to pairs of local feature vectors occurring before the last pooling layer. Two local feature vectors are attracted to each other if their l2-distance is below a threshold or if their relative locations are consistent with a known geometric transformation between the two input images. We demonstrate strong performance on linear classification and segmentation transfer tasks. Code and pretrained models are publicly available at: https://github.com/facebookresearch/VICRegL
While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision, attention is either applied in conjunction with convolutional networks, or used to replace certain components of convolutional networks while keeping their overall structure in place. We show that this reliance on CNNs is not necessary and a pure transformer applied directly to sequences of image patches can perform very well on image classification tasks. When pre-trained on large amounts of data and transferred to multiple mid-sized or small image recognition benchmarks (ImageNet, CIFAR-100, VTAB, etc.), Vision Transformer (ViT) attains excellent results compared to state-of-the-art convolutional networks while requiring substantially fewer computational resources to train.
Deep learning-based models, when trained in a fully-supervised manner, can be effective in performing complex image analysis tasks, although contingent upon the availability of large labeled datasets. Especially in the medical imaging domain, however, expert image annotation is expensive, time-consuming, and prone to variability. Semi-supervised learning from limited quantities of labeled data has shown promise as an alternative. Maximizing knowledge gains from copious unlabeled data benefits semi-supervised learning models. Moreover, learning multiple tasks within the same model further improves its generalizability. We propose MultiMix, a new multi-task learning model that jointly learns disease classification and anatomical segmentation in a semi-supervised manner, while preserving explainability through a novel saliency bridge between the two tasks. Our experiments with varying quantities of multi-source labeled data in the training sets confirm the effectiveness of MultiMix in the simultaneous classification of pneumonia and segmentation of the lungs in chest X-ray images. Moreover, both in-domain and cross-domain evaluations across these tasks further showcase the potential of our model to adapt to challenging generalization scenarios.
Controversial contents largely inundate the Internet, infringing various cultural norms and child protection standards. Traditional Image Content Moderation (ICM) models fall short in producing precise moderation decisions for diverse standards, while recent multimodal large language models (MLLMs), when adopted to general rule-based ICM, often produce classification and explanation results that are inconsistent with human moderators. Aiming at flexible, explainable, and accurate ICM, we design a novel rule-based dataset generation pipeline, decomposing concise human-defined rules and leveraging well-designed multi-stage prompts to enrich short explicit image annotations. Our ICM-Instruct dataset includes detailed moderation explanation and moderation Q-A pairs. Built upon it, we create our ICM-Assistant model in the framework of rule-based ICM, making it readily applicable in real practice. Our ICM-Assistant model demonstrates exceptional performance and flexibility. Specifically, it significantly outperforms existing approaches on various sources, improving both the moderation classification (36.8% on average) and moderation explanation quality (26.6% on average) consistently over existing MLLMs. Code/Data is available at https://github.com/zhaoyuzhi/ICM-Assistant.
Channel Pruning has been long studied to compress CNNs, which significantly reduces the overall computation. Prior works implement channel pruning in an unexplainable manner, which tends to reduce the final classification errors while failing to consider the internal influence of each channel. In this paper, we conduct channel pruning in a white box. Through deep visualization of feature maps activated by different channels, we observe that different channels have a varying contribution to different categories in image classification. Inspired by this, we choose to preserve channels contributing to most categories. Specifically, to model the contribution of each channel to differentiating categories, we develop a class-wise mask for each channel, implemented in a dynamic training manner w.r.t. the input image's category. On the basis of the learned class-wise mask, we perform a global voting mechanism to remove channels with less category discrimination. Lastly, a fine-tuning process is conducted to recover the performance of the pruned model. To our best knowledge, it is the first time that CNN interpretability theory is considered to guide channel pruning. Extensive experiments on representative image classification tasks demonstrate the superiority of our White-Box over many state-of-the-arts. For instance, on CIFAR-10, it reduces 65.23% FLOPs with even 0.62% accuracy improvement for ResNet-110. On ILSVRC-2012, White-Box achieves a 45.6% FLOPs reduction with only a small loss of 0.83% in the top-1 accuracy for ResNet-50.