Robust classification methods predominantly concentrate on algorithms that address a specific threat model, resulting in ineffective defenses against other threat models. Real-world applications are exposed to this vulnerability, as malicious attackers might exploit alternative threat models. In this work, we propose a novel test-time threat model agnostic algorithm that enhances Adversarial-Trained (AT) models. Our method operates through COnditional image transformation and DIstance-based Prediction (CODIP) and includes two main steps: First, we transform the input image into each dataset class, where the input image might be either clean or attacked. Next, we make a prediction based on the shortest transformed distance. The conditional transformation utilizes the perceptually aligned gradients property possessed by AT models and, as a result, eliminates the need for additional models or additional training. Moreover, it allows users to choose the desired balance between clean and robust accuracy without training. The proposed method achieves state-of-the-art results demonstrated through extensive experiments on various models, AT methods, datasets, and attack types. Notably, applying CODIP leads to substantial robust accuracy improvement of up to $+23\%$, $+20\%$, $+26\%$, and $+22\%$ on CIFAR10, CIFAR100, ImageNet and Flowers datasets, respectively.
Face recognition is a crucial task in various multimedia applications such as security check, credential access and motion sensing games. However, the task is challenging when an input face is noisy (e.g. poor-condition RGB image) or lacks certain information (e.g. 3D face without color). In this work, we propose a Multimodal Training Unimodal Test (MTUT) framework for robust face classification, which exploits the cross-modality relationship during training and applies it as a complementary of the imperfect single modality input during testing. Technically, during training, the framework (1) builds both intra-modality and cross-modality autoencoders with the aid of facial attributes to learn latent embeddings as multimodal descriptors, (2) proposes a novel multimodal embedding divergence loss to align the heterogeneous features from different modalities, which also adaptively avoids the useless modality (if any) from confusing the model. This way, the learned autoencoders can generate robust embeddings in single-modality face classification on test stage. We evaluate our framework in two face classification datasets and two kinds of testing input: (1) poor-condition image and (2) point cloud or 3D face mesh, when both 2D and 3D modalities are available for training. We experimentally show that our MTUT framework consistently outperforms ten baselines on 2D and 3D settings of both datasets.
Vision-language models such as CLIP learn a generic text-image embedding from large-scale training data. A vision-language model can be adapted to a new classification task through few-shot prompt tuning. We find that such a prompt tuning process is highly robust to label noises. This intrigues us to study the key reasons contributing to the robustness of the prompt tuning paradigm. We conducted extensive experiments to explore this property and find the key factors are: 1) the fixed classname tokens provide a strong regularization to the optimization of the model, reducing gradients induced by the noisy samples; 2) the powerful pre-trained image-text embedding that is learned from diverse and generic web data provides strong prior knowledge for image classification. Further, we demonstrate that noisy zero-shot predictions from CLIP can be used to tune its own prompt, significantly enhancing prediction accuracy in the unsupervised setting. The code is available at https://github.com/CEWu/PTNL.
Whole Slide Image (WSI) classification remains a challenge due to their extremely high resolution and the absence of fine-grained labels. Presently, WSI classification is usually regarded as a Multiple Instance Learning (MIL) problem when only slide-level labels are available. MIL methods involve a patch embedding module and a bag-level classification module, but they are prohibitively expensive to be trained in an end-to-end manner. Therefore, existing methods usually train them separately, or directly skip the training of the embedder. Such schemes hinder the patch embedder's access to slide-level semantic labels, resulting in inconsistency within the entire MIL pipeline. To overcome this issue, we propose a novel framework called Iteratively Coupled MIL (ICMIL), which bridges the loss back-propagation process from the bag-level classifier to the patch embedder. In ICMIL, we use category information in the bag-level classifier to guide the patch-level fine-tuning of the patch feature extractor. The refined embedder then generates better instance representations for achieving a more accurate bag-level classifier. By coupling the patch embedder and bag classifier at a low cost, our proposed framework enables information exchange between the two modules, benefiting the entire MIL classification model. We tested our framework on two datasets using three different backbones, and our experimental results demonstrate consistent performance improvements over state-of-the-art MIL methods. The code is available at: https://github.com/Dootmaan/ICMIL.
The need to explain the output of a deep neural network classifier is now widely recognized. While previous methods typically explain a single class in the output, we advocate explaining the whole output, which is a probability distribution over multiple classes. A whole-output explanation can help a human user gain an overall understanding of model behaviour instead of only one aspect of it. It can also provide a natural framework where one can examine the evidence used to discriminate between competing classes, and thereby obtain contrastive explanations. In this paper, we propose a contrastive whole-output explanation (CWOX) method for image classification, and evaluate it using quantitative metrics and through human subject studies. The source code of CWOX is available at https://github.com/vaynexie/CWOX.
Automated classification of human anatomy is an important prerequisite for many computer-aided diagnosis systems. The spatial complexity and variability of anatomy throughout the human body makes classification difficult. "Deep learning" methods such as convolutional networks (ConvNets) outperform other state-of-the-art methods in image classification tasks. In this work, we present a method for organ- or body-part-specific anatomical classification of medical images acquired using computed tomography (CT) with ConvNets. We train a ConvNet, using 4,298 separate axial 2D key-images to learn 5 anatomical classes. Key-images were mined from a hospital PACS archive, using a set of 1,675 patients. We show that a data augmentation approach can help to enrich the data set and improve classification performance. Using ConvNets and data augmentation, we achieve anatomy-specific classification error of 5.9 % and area-under-the-curve (AUC) values of an average of 0.998 in testing. We demonstrate that deep learning can be used to train very reliable and accurate classifiers that could initialize further computer-aided diagnosis.
Can we automatically group images into semantically meaningful clusters when ground-truth annotations are absent? The task of unsupervised image classification remains an important, and open challenge in computer vision. Several recent approaches have tried to tackle this problem in an end-to-end fashion. In this paper, we deviate from recent works, and advocate a two-step approach where feature learning and clustering are decoupled. First, a self-supervised task from representation learning is employed to obtain semantically meaningful features. Second, we use the obtained features as a prior in a learnable clustering approach. In doing so, we remove the ability for cluster learning to depend on low-level features, which is present in current end-to-end learning approaches. Experimental evaluation shows that we outperform state-of-the-art methods by large margins, in particular +26.6% on CIFAR10, +25.0% on CIFAR100-20 and +21.3% on STL10 in terms of classification accuracy. Furthermore, our method is the first to perform well on a large-scale dataset for image classification. In particular, we obtain promising results on ImageNet, and outperform several semi-supervised learning methods in the low-data regime without the use of any ground-truth annotations. The code is made publicly available at https://github.com/wvangansbeke/Unsupervised-Classification.
Efficient extraction of spectral sequences and geospatial information has always been a hot topic in hyperspectral image classification. In terms of spectral sequence feature capture, RNN and Transformer have become mainstream classification frameworks due to their long-range feature capture capabilities. In terms of spatial information aggregation, CNN enhances the receptive field to retain integrated spatial information as much as possible. However, the spectral feature-capturing architectures exhibit low computational efficiency, and CNNs lack the flexibility to perceive spatial contextual information. To address these issues, this paper proposes GraphMamba--an efficient graph structure learning vision Mamba classification framework that fully considers HSI characteristics to achieve deep spatial-spectral information mining. Specifically, we propose a novel hyperspectral visual GraphMamba processing paradigm (HVGM) that preserves spatial-spectral features by constructing spatial-spectral cubes and utilizes linear spectral encoding to enhance the operability of subsequent tasks. The core components of GraphMamba include the HyperMamba module for improving computational efficiency and the SpectralGCN module for adaptive spatial context awareness. The HyperMamba mitigates clutter interference by employing the global mask (GM) and introduces a parallel training inference architecture to alleviate computational bottlenecks. The SpatialGCN incorporates weighted multi-hop aggregation (WMA) spatial encoding to focus on highly correlated spatial structural features, thus flexibly aggregating contextual information while mitigating spatial noise interference. Extensive experiments were conducted on three different scales of real HSI datasets, and compared with the state-of-the-art classification frameworks, GraphMamba achieved optimal performance.
Referring image segmentation aims to segment the target referent in an image conditioning on a natural language expression. Existing one-stage methods employ per-pixel classification frameworks, which attempt straightforwardly to align vision and language at the pixel level, thus failing to capture critical object-level information. In this paper, we propose a mask classification framework, Contrastive Grouping with Transformer network (CGFormer), which explicitly captures object-level information via token-based querying and grouping strategy. Specifically, CGFormer first introduces learnable query tokens to represent objects and then alternately queries linguistic features and groups visual features into the query tokens for object-aware cross-modal reasoning. In addition, CGFormer achieves cross-level interaction by jointly updating the query tokens and decoding masks in every two consecutive layers. Finally, CGFormer cooperates contrastive learning to the grouping strategy to identify the token and its mask corresponding to the referent. Experimental results demonstrate that CGFormer outperforms state-of-the-art methods in both segmentation and generalization settings consistently and significantly.
Most publicly available datasets for image classification are with single labels, while images are inherently multi-labeled in our daily life. Such an annotation gap makes many pre-trained single-label classification models fail in practical scenarios. This annotation issue is more concerned for aerial images: Aerial data collected from sensors naturally cover a relatively large land area with multiple labels, while annotated aerial datasets, which are publicly available (e.g., UCM, AID), are single-labeled. As manually annotating multi-label aerial images would be time/labor-consuming, we propose a novel self-correction integrated domain adaptation (SCIDA) method for automatic multi-label learning. SCIDA is weakly supervised, i.e., automatically learning the multi-label image classification model from using massive, publicly available single-label images. To achieve this goal, we propose a novel Label-Wise self-Correction (LWC) module to better explore underlying label correlations. This module also makes the unsupervised domain adaptation (UDA) from single- to multi-label data possible. For model training, the proposed model only uses single-label information yet requires no prior knowledge of multi-labeled data; and it predicts labels for multi-label aerial images. In our experiments, trained with single-labeled MAI-AID-s and MAI-UCM-s datasets, the proposed model is tested directly on our collected Multi-scene Aerial Image (MAI) dataset.
This paper introduces a new few-shot learning pipeline that casts relevance ranking for image retrieval as binary ranking relation classification. In comparison to image classification, ranking relation classification is sample efficient and domain agnostic. Besides, it provides a new perspective on few-shot learning and is complementary to state-of-the-art methods. The core component of our deep neural network is a simple MLP, which takes as input an image triplet encoded as the difference between two vector-Kronecker products, and outputs a binary relevance ranking order. The proposed RankMLP can be built on top of any state-of-the-art feature extractors, and our entire deep neural network is called the ranking deep neural network, or RankDNN. Meanwhile, RankDNN can be flexibly fused with other post-processing methods. During the meta test, RankDNN ranks support images according to their similarity with the query samples, and each query sample is assigned the class label of its nearest neighbor. Experiments demonstrate that RankDNN can effectively improve the performance of its baselines based on a variety of backbones and it outperforms previous state-of-the-art algorithms on multiple few-shot learning benchmarks, including miniImageNet, tieredImageNet, Caltech-UCSD Birds, and CIFAR-FS. Furthermore, experiments on the cross-domain challenge demonstrate the superior transferability of RankDNN.The code is available at: https://github.com/guoqianyu-alberta/RankDNN.
It is well known that query-based attacks tend to have relatively higher success rates in adversarial black-box attacks. While research on black-box attacks is actively being conducted, relatively few studies have focused on pixel attacks that target only a limited number of pixels. In image classification, query-based pixel attacks often rely on patches, which heavily depend on randomness and neglect the fact that scattered pixels are more suitable for adversarial attacks. Moreover, to the best of our knowledge, query-based pixel attacks have not been explored in the field of object detection. To address these issues, we propose a novel pixel-based black-box attack called Remember and Forget Pixel Attack using Reinforcement Learning(RFPAR), consisting of two main components: the Remember and Forget processes. RFPAR mitigates randomness and avoids patch dependency by leveraging rewards generated through a one-step RL algorithm to perturb pixels. RFPAR effectively creates perturbed images that minimize the confidence scores while adhering to limited pixel constraints. Furthermore, we advance our proposed attack beyond image classification to object detection, where RFPAR reduces the confidence scores of detected objects to avoid detection. Experiments on the ImageNet-1K dataset for classification show that RFPAR outperformed state-of-the-art query-based pixel attacks. For object detection, using the MSCOCO dataset with YOLOv8 and DDQ, RFPAR demonstrates comparable mAP reduction to state-of-the-art query-based attack while requiring fewer query. Further experiments on the Argoverse dataset using YOLOv8 confirm that RFPAR effectively removed objects on a larger scale dataset. Our code is available at https://github.com/KAU-QuantumAILab/RFPAR.
With the progress in AI-based facial forgery (i.e., deepfake), people are increasingly concerned about its abuse. Albeit effort has been made for training classification (also known as deepfake detection) models to recognize such forgeries, existing models suffer from poor generalization to unseen forgery technologies and high sensitivity to changes in image/video quality. In this paper, we advocate adversarial training for improving the generalization ability to both unseen facial forgeries and unseen image/video qualities. We believe training with samples that are adversarially crafted to attack the classification models improves the generalization ability considerably. Considering that AI-based face manipulation often leads to high-frequency artifacts that can be easily spotted by models yet difficult to generalize, we further propose a new adversarial training method that attempts to blur out these specific artifacts, by introducing pixel-wise Gaussian blurring models. With adversarial training, the classification models are forced to learn more discriminative and generalizable features, and the effectiveness of our method can be verified by plenty of empirical evidence. Our code will be made publicly available.
Our research focuses on the critical field of early diagnosis of disease by examining retinal blood vessels in fundus images. While automatic segmentation of retinal blood vessels holds promise for early detection, accurate analysis remains challenging due to the limitations of existing methods, which often lack discrimination power and are susceptible to influences from pathological regions. Our research in fundus image analysis advances deep learning-based classification using eight pre-trained CNN models. To enhance interpretability, we utilize Explainable AI techniques such as Grad-CAM, Grad-CAM++, Score-CAM, Faster Score-CAM, and Layer CAM. These techniques illuminate the decision-making processes of the models, fostering transparency and trust in their predictions. Expanding our exploration, we investigate ten models, including TransUNet with ResNet backbones, Attention U-Net with DenseNet and ResNet backbones, and Swin-UNET. Incorporating diverse architectures such as ResNet50V2, ResNet101V2, ResNet152V2, and DenseNet121 among others, this comprehensive study deepens our insights into attention mechanisms for enhanced fundus image analysis. Among the evaluated models for fundus image classification, ResNet101 emerged with the highest accuracy, achieving an impressive 94.17%. On the other end of the spectrum, EfficientNetB0 exhibited the lowest accuracy among the models, achieving a score of 88.33%. Furthermore, in the domain of fundus image segmentation, Swin-Unet demonstrated a Mean Pixel Accuracy of 86.19%, showcasing its effectiveness in accurately delineating regions of interest within fundus images. Conversely, Attention U-Net with DenseNet201 backbone exhibited the lowest Mean Pixel Accuracy among the evaluated models, achieving a score of 75.87%.
This concept paper aims to provide a brief outline of quantum computers, explore existing methods of quantum image classification techniques, so focusing on remote sensing applications, and discuss the bottlenecks of performing these algorithms on currently available open source platforms. Initial results demonstrate feasibility. Next steps include expanding the size of the quantum hidden layer and increasing the variety of output image options.
Real-world recognition system often encounters the challenge of unseen labels. To identify such unseen labels, multi-label zero-shot learning (ML-ZSL) focuses on transferring knowledge by a pre-trained textual label embedding (e.g., GloVe). However, such methods only exploit single-modal knowledge from a language model, while ignoring the rich semantic information inherent in image-text pairs. Instead, recently developed open-vocabulary (OV) based methods succeed in exploiting such information of image-text pairs in object detection, and achieve impressive performance. Inspired by the success of OV-based methods, we propose a novel open-vocabulary framework, named multi-modal knowledge transfer (MKT), for multi-label classification. Specifically, our method exploits multi-modal knowledge of image-text pairs based on a vision and language pre-training (VLP) model. To facilitate transferring the image-text matching ability of VLP model, knowledge distillation is employed to guarantee the consistency of image and label embeddings, along with prompt tuning to further update the label embeddings. To further enable the recognition of multiple objects, a simple but effective two-stream module is developed to capture both local and global features. Extensive experimental results show that our method significantly outperforms state-of-the-art methods on public benchmark datasets. The source code is available at https://github.com/sunanhe/MKT.
Vision-and-language (VL) models with separate encoders for each modality (e.g., CLIP) have become the go-to models for zero-shot image classification and image-text retrieval. They are, however, mostly evaluated in English as multilingual benchmarks are limited in availability. We introduce Babel-ImageNet, a massively multilingual benchmark that offers (partial) translations of ImageNet labels to 100 languages, built without machine translation or manual annotation. We instead automatically obtain reliable translations by linking them -- via shared WordNet synsets -- to BabelNet, a massively multilingual lexico-semantic network. We evaluate 11 public multilingual CLIP models on zero-shot image classification (ZS-IC) on our benchmark, demonstrating a significant gap between English ImageNet performance and that of high-resource languages (e.g., German or Chinese), and an even bigger gap for low-resource languages (e.g., Sinhala or Lao). Crucially, we show that the models' ZS-IC performance highly correlates with their performance in image-text retrieval, validating the use of Babel-ImageNet to evaluate multilingual models for the vast majority of languages without gold image-text data. Finally, we show that the performance of multilingual CLIP can be drastically improved for low-resource languages with parameter-efficient language-specific training. We make our code and data publicly available: \url{https://github.com/gregor-ge/Babel-ImageNet}
The image-based diagnosis is now a vital aspect of modern automation assisted diagnosis. To enable models to produce pixel-level diagnosis, pixel-level ground-truth labels are essentially required. However, since it is often not straight forward to obtain the labels in many application domains such as in medical image, classification-based approaches have become the de facto standard to perform the diagnosis. Though they can identify class-salient regions, they may not be useful for diagnosis where capturing all of the evidences is important requirement. Alternatively, a counterfactual explanation (CX) aims at providing explanations using a casual reasoning process of form "If X has not happend, Y would not heppend". Existing CX approaches, however, use classifier to explain features that can change its predictions. Thus, they can only explain class-salient features, rather than entire object of interest. This hence motivates us to propose a novel CX strategy that is not reliant on image classification. This work is inspired from the recent developments in generative adversarial networks (GANs) based image-to-image domain translation, and leverages to translate an abnormal image to counterpart normal image (i.e. counterfactual instance CI) to find discrepancy maps between the two. Since it is generally not possible to obtain abnormal and normal image pairs, we leverage Cycle-Consistency principle (a.k.a CycleGAN) to perform the translation in unsupervised way. We formulate CX in terms of a discrepancy map that, when added from the abnormal image, will make it indistinguishable from the CI. We evaluate our method on three datasets including a synthetic, tuberculosis and BraTS dataset. All these experiments confirm the supremacy of propose method in generating accurate CX and CI.
Deep Neural Network has shown great strides in the coarse-grained image classification task. It was in part due to its strong ability to extract discriminative feature representations from the images. However, the marginal visual difference between different classes in fine-grained images makes this very task harder. In this paper, we tried to focus on these marginal differences to extract more representative features. Similar to human vision, our network repetitively focuses on parts of images to spot small discriminative parts among the classes. Moreover, we show through interpretability techniques how our network focus changes from coarse to fine details. Through our experiments, we also show that a simple attention model can aggregate (weighted) these finer details to focus on the most dominant discriminative part of the image. Our network uses only image-level labels and does not need bounding box/part annotation information. Further, the simplicity of our network makes it an easy plug-n-play module. Apart from providing interpretability, our network boosts the performance (up to 2%) when compared to its baseline counterparts. Our codebase is available at https://github.com/TAMU-VITA/Focus-Longer-to-See-Better
We provide a process to modify a neural network to an equivariant one, which we call equivarification. As an illustration, we build an equivariant neural network for image classification by equivarifying a convolutional neural network.