Person re-identification (re-id), which aims to retrieve images of the same person in a given image from a database, is one of the most practical image recognition applications. In the real world, however, the environments that the images are taken from change over time. This causes a distribution shift between training and testing and degrades the performance of re-id. To maintain re-id performance, models should continue adapting to the test environment's temporal changes. Test-time adaptation (TTA), which aims to adapt models to the test environment with only unlabeled test data, is a promising way to handle this problem because TTA can adapt models instantly in the test environment. However, the previous TTA methods are designed for classification and cannot be directly applied to re-id. This is because the set of people's identities in the dataset differs between training and testing in re-id, whereas the set of classes is fixed in the current TTA methods designed for classification. To improve re-id performance in changing test environments, we propose TEst-time similarity Modification for Person re-identification (TEMP), a novel TTA method for re-id. TEMP is the first fully TTA method for re-id, which does not require any modification to pre-training. Inspired by TTA methods that refine the prediction uncertainty in classification, we aim to refine the uncertainty in re-id. However, the uncertainty cannot be computed in the same way as classification in re-id since it is an open-set task, which does not share person labels between training and testing. Hence, we propose re-id entropy, an alternative uncertainty measure for re-id computed based on the similarity between the feature vectors. Experiments show that the re-id entropy can measure the uncertainty on re-id and TEMP improves the performance of re-id in online settings where the distribution changes over time.
Convolutional neural networks (CNNs) are widely used for image recognition and text analysis, and have been suggested for application on one-dimensional data as a way to reduce the need for pre-processing steps. Pre-processing is an integral part of multivariate analysis, but determination of the optimal pre-processing methods can be time-consuming due to the large number of available methods. In this work, the performance of a CNN was investigated for classification and regression analysis of spectral data. The CNN was compared with various other chemometric methods, including support vector machines (SVMs) for classification and partial least squares regression (PLSR) for regression analysis. The comparisons were made both on raw data, and on data that had gone through pre-processing and/or feature selection methods. The models were used on spectral data acquired with methods based on near-infrared, mid-infrared, and Raman spectroscopy. For the classification datasets the models were evaluated based on the percentage of correctly classified observations, while for regression analysis the models were assessed based on the coefficient of determination (R$^2$). Our results show that CNNs can outperform standard chemometric methods, especially for classification tasks where no pre-processing is used. However, both CNN and the standard chemometric methods see improved performance when proper pre-processing and feature selection methods are used. These results demonstrate some of the capabilities and limitations of CNNs used on one-dimensional data.
Research connecting text and images has recently seen several breakthroughs, with models like CLIP, DALL-E 2, and Stable Diffusion. However, the connection between text and other visual modalities, such as lidar data, has received less attention, prohibited by the lack of text-lidar datasets. In this work, we propose LidarCLIP, a mapping from automotive point clouds to a pre-existing CLIP embedding space. Using image-lidar pairs, we supervise a point cloud encoder with the image CLIP embeddings, effectively relating text and lidar data with the image domain as an intermediary. We show the effectiveness of LidarCLIP by demonstrating that lidar-based retrieval is generally on par with image-based retrieval, but with complementary strengths and weaknesses. By combining image and lidar features, we improve upon both single-modality methods and enable a targeted search for challenging detection scenarios under adverse sensor conditions. We also explore zero-shot classification and show that LidarCLIP outperforms existing attempts to use CLIP for point clouds by a large margin. Finally, we leverage our compatibility with CLIP to explore a range of applications, such as point cloud captioning and lidar-to-image generation, without any additional training. Code and pre-trained models are available at https://github.com/atonderski/lidarclip.
Vision-language models, such as contrastive language-image pre-training (CLIP), have demonstrated impressive results in natural image domains. However, these models often struggle when applied to specialized domains like remote sensing, and adapting to such domains is challenging due to the limited number of image-text pairs available for training. To address this, we propose S-CLIP, a semi-supervised learning method for training CLIP that utilizes additional unpaired images. S-CLIP employs two pseudo-labeling strategies specifically designed for contrastive learning and the language modality. The caption-level pseudo-label is given by a combination of captions of paired images, obtained by solving an optimal transport problem between unpaired and paired images. The keyword-level pseudo-label is given by a keyword in the caption of the nearest paired image, trained through partial label learning that assumes a candidate set of labels for supervision instead of the exact one. By combining these objectives, S-CLIP significantly enhances the training of CLIP using only a few image-text pairs, as demonstrated in various specialist domains, including remote sensing, fashion, scientific figures, and comics. For instance, S-CLIP improves CLIP by 10% for zero-shot classification and 4% for image-text retrieval on the remote sensing benchmark, matching the performance of supervised CLIP while using three times fewer image-text pairs.
Small on-device models have been successfully trained with user-level differential privacy (DP) for next word prediction and image classification tasks in the past. However, existing methods can fail when directly applied to learn embedding models using supervised training data with a large class space. To achieve user-level DP for large image-to-embedding feature extractors, we propose DP-FedEmb, a variant of federated learning algorithms with per-user sensitivity control and noise addition, to train from user-partitioned data centralized in the datacenter. DP-FedEmb combines virtual clients, partial aggregation, private local fine-tuning, and public pretraining to achieve strong privacy utility trade-offs. We apply DP-FedEmb to train image embedding models for faces, landmarks and natural species, and demonstrate its superior utility under same privacy budget on benchmark datasets DigiFace, EMNIST, GLD and iNaturalist. We further illustrate it is possible to achieve strong user-level DP guarantees of $\epsilon<4$ while controlling the utility drop within 5%, when millions of users can participate in training.
In this work, we present a novel approach to multi-label chest X-ray (CXR) image classification that enhances clinical interpretability while maintaining a streamlined, single-model, single-run training pipeline. Leveraging the CheXpert dataset and VisualCheXbert-derived labels, we incorporate hierarchical label groupings to capture clinically meaningful relationships between diagnoses. To achieve this, we designed a custom hierarchical binary cross-entropy (HBCE) loss function that enforces label dependencies using either fixed or data-driven penalty types. Our model achieved a mean area under the receiver operating characteristic curve (AUROC) of 0.903 on the test set. Additionally, we provide visual explanations and uncertainty estimations to further enhance model interpretability. All code, model configurations, and experiment details are made available.
Deep learning for radiologic image analysis is a rapidly growing field in biomedical research and is likely to become a standard practice in modern medicine. On the publicly available NIH ChestX-ray14 dataset, containing X-ray images that are classified by the presence or absence of 14 different diseases, we reproduced an algorithm known as CheXNet, as well as explored other algorithms that outperform CheXNet's baseline metrics. Model performance was primarily evaluated using the F1 score and AUC-ROC, both of which are critical metrics for imbalanced, multi-label classification tasks in medical imaging. The best model achieved an average AUC-ROC score of 0.85 and an average F1 score of 0.39 across all 14 disease classifications present in the dataset.
Recent state-of-the-art active learning methods have mostly leveraged Generative Adversarial Networks (GAN) for sample acquisition; however, GAN is usually known to suffer from instability and sensitivity to hyper-parameters. In contrast to these methods, we propose in this paper a novel active learning framework that we call Maximum Classifier Discrepancy for Active Learning (MCDAL) which takes the prediction discrepancies between multiple classifiers. In particular, we utilize two auxiliary classification layers that learn tighter decision boundaries by maximizing the discrepancies among them. Intuitively, the discrepancies in the auxiliary classification layers' predictions indicate the uncertainty in the prediction. In this regard, we propose a novel method to leverage the classifier discrepancies for the acquisition function for active learning. We also provide an interpretation of our idea in relation to existing GAN based active learning methods and domain adaptation frameworks. Moreover, we empirically demonstrate the utility of our approach where the performance of our approach exceeds the state-of-the-art methods on several image classification and semantic segmentation datasets in active learning setups.
Multimodal sentiment analysis has a wide range of applications due to its information complementarity in multimodal interactions. Previous works focus more on investigating efficient joint representations, but they rarely consider the insufficient unimodal features extraction and data redundancy of multimodal fusion. In this paper, a Video-based Cross-modal Auxiliary Network (VCAN) is proposed, which is comprised of an audio features map module and a cross-modal selection module. The first module is designed to substantially increase feature diversity in audio feature extraction, aiming to improve classification accuracy by providing more comprehensive acoustic representations. To empower the model to handle redundant visual features, the second module is addressed to efficiently filter the redundant visual frames during integrating audiovisual data. Moreover, a classifier group consisting of several image classification networks is introduced to predict sentiment polarities and emotion categories. Extensive experimental results on RAVDESS, CMU-MOSI, and CMU-MOSEI benchmarks indicate that VCAN is significantly superior to the state-of-the-art methods for improving the classification accuracy of multimodal sentiment analysis.
Open vocabulary models (e.g. CLIP) have shown strong performance on zero-shot classification through their ability generate embeddings for each class based on their (natural language) names. Prior work has focused on improving the accuracy of these models through prompt engineering or by incorporating a small amount of labeled downstream data (via finetuning). However, there has been little focus on improving the richness of the class names themselves, which can pose issues when class labels are coarsely-defined and are uninformative. We propose Classification with Hierarchical Label Sets (or CHiLS), an alternative strategy for zero-shot classification specifically designed for datasets with implicit semantic hierarchies. CHiLS proceeds in three steps: (i) for each class, produce a set of subclasses, using either existing label hierarchies or by querying GPT-3; (ii) perform the standard zero-shot CLIP procedure as though these subclasses were the labels of interest; (iii) map the predicted subclass back to its parent to produce the final prediction. Across numerous datasets with underlying hierarchical structure, CHiLS leads to improved accuracy in situations both with and without ground-truth hierarchical information. CHiLS is simple to implement within existing zero-shot pipelines and requires no additional training cost. Code is available at: https://github.com/acmi-lab/CHILS.
Deep learning models are complex due to their size, structure, and inherent randomness in training procedures. Additional complexity arises from the selection of datasets and inductive biases. Addressing these challenges for explainability, Kim et al. (2018) introduced Concept Activation Vectors (CAVs), which aim to understand deep models' internal states in terms of human-aligned concepts. These concepts correspond to directions in latent space, identified using linear discriminants. Although this method was first applied to image classification, it was later adapted to other domains, including natural language processing. In this work, we attempt to apply the method to electroencephalogram (EEG) data for explainability in Kostas et al.'s BENDR (2021), a large-scale transformer model. A crucial part of this endeavor involves defining the explanatory concepts and selecting relevant datasets to ground concepts in the latent space. Our focus is on two mechanisms for EEG concept formation: the use of externally labeled EEG datasets, and the application of anatomically defined concepts. The former approach is a straightforward generalization of methods used in image classification, while the latter is novel and specific to EEG. We present evidence that both approaches to concept formation yield valuable insights into the representations learned by deep EEG models.
When training a deep neural network for image classification, one can broadly distinguish between two types of latent features of images that will drive the classification. We can divide latent features into (i) "core" or "conditionally invariant" features $X^\text{core}$ whose distribution $X^\text{core}\vert Y$, conditional on the class $Y$, does not change substantially across domains and (ii) "style" features $X^{\text{style}}$ whose distribution $X^{\text{style}} \vert Y$ can change substantially across domains. Examples for style features include position, rotation, image quality or brightness but also more complex ones like hair color, image quality or posture for images of persons. Our goal is to minimize a loss that is robust under changes in the distribution of these style features. In contrast to previous work, we assume that the domain itself is not observed and hence a latent variable. We do assume that we can sometimes observe a typically discrete identifier or "$\mathrm{ID}$ variable". In some applications we know, for example, that two images show the same person, and $\mathrm{ID}$ then refers to the identity of the person. The proposed method requires only a small fraction of images to have $\mathrm{ID}$ information. We group observations if they share the same class and identifier $(Y,\mathrm{ID})=(y,\mathrm{id})$ and penalize the conditional variance of the prediction or the loss if we condition on $(Y,\mathrm{ID})$. Using a causal framework, this conditional variance regularization (CoRe) is shown to protect asymptotically against shifts in the distribution of the style variables. Empirically, we show that the CoRe penalty improves predictive accuracy substantially in settings where domain changes occur in terms of image quality, brightness and color while we also look at more complex changes such as changes in movement and posture.
In recent years, deep learning has successfully been applied to automate a wide variety of tasks in diagnostic histopathology. However, fast and reliable localization of small-scale regions-of-interest (ROI) has remained a key challenge, as discriminative morphologic features often occupy only a small fraction of a gigapixel-scale whole-slide image (WSI). In this paper, we propose a sparse WSI analysis method for the rapid identification of high-power ROI for WSI-level classification. We develop an evaluation framework inspired by the early classification literature, in order to quantify the tradeoff between diagnostic performance and inference time for sparse analytic approaches. We test our method on a common but time-consuming task in pathology - that of diagnosing gastric intestinal metaplasia (GIM) on hematoxylin and eosin (H&E)-stained slides from endoscopic biopsy specimens. GIM is a well-known precursor lesion along the pathway to development of gastric cancer. We performed a thorough evaluation of the performance and inference time of our approach on a test set of GIM-positive and GIM-negative WSI, finding that our method successfully detects GIM in all positive WSI, with a WSI-level classification area under the receiver operating characteristic curve (AUC) of 0.98 and an average precision (AP) of 0.95. Furthermore, we show that our method can attain these metrics in under one minute on a standard CPU. Our results are applicable toward the goal of developing neural networks that can easily be deployed in clinical settings to support pathologists in quickly localizing and diagnosing small-scale morphologic features in WSI.
Underwater image enhancement is such an important low-level vision task with many applications that numerous algorithms have been proposed in recent years. These algorithms developed upon various assumptions demonstrate successes from various aspects using different data sets and different metrics. In this work, we setup an undersea image capturing system, and construct a large-scale Real-world Underwater Image Enhancement (RUIE) data set divided into three subsets. The three subsets target at three challenging aspects for enhancement, i.e., image visibility quality, color casts, and higher-level detection/classification, respectively. We conduct extensive and systematic experiments on RUIE to evaluate the effectiveness and limitations of various algorithms to enhance visibility and correct color casts on images with hierarchical categories of degradation. Moreover, underwater image enhancement in practice usually serves as a preprocessing step for mid-level and high-level vision tasks. We thus exploit the object detection performance on enhanced images as a brand new task-specific evaluation criterion. The findings from these evaluations not only confirm what is commonly believed, but also suggest promising solutions and new directions for visibility enhancement, color correction, and object detection on real-world underwater images.
Vision-language pre-training (VLP) models have been demonstrated to be effective in many computer vision applications. In this paper, we consider developing a VLP model in the medical domain for making computer-aided diagnoses (CAD) based on image scans and text descriptions in electronic health records, as done in practice. To achieve our goal, we present a lightweight CAD system MedBLIP, a new paradigm for bootstrapping VLP from off-the-shelf frozen pre-trained image encoders and frozen large language models. We design a MedQFormer module to bridge the gap between 3D medical images and 2D pre-trained image encoders and language models as well. To evaluate the effectiveness of our MedBLIP, we collect more than 30,000 image volumes from five public Alzheimer's disease (AD) datasets, i.e., ADNI, NACC, OASIS, AIBL, and MIRIAD. On this largest AD dataset we know, our model achieves the SOTA performance on the zero-shot classification of healthy, mild cognitive impairment (MCI), and AD subjects, and shows its capability of making medical visual question answering (VQA). The code and pre-trained models is available online: https://github.com/Qybc/MedBLIP.
Image pyramids are commonly used in modern computer vision tasks to obtain multi-scale features for precise understanding of images. However, image pyramids process multiple resolutions of images using the same large-scale model, which requires significant computational cost. To overcome this issue, we propose a novel network architecture known as the Parameter-Inverted Image Pyramid Networks (PIIP). Our core idea is to use models with different parameter sizes to process different resolution levels of the image pyramid, thereby balancing computational efficiency and performance. Specifically, the input to PIIP is a set of multi-scale images, where higher resolution images are processed by smaller networks. We further propose a feature interaction mechanism to allow features of different resolutions to complement each other and effectively integrate information from different spatial scales. Extensive experiments demonstrate that the PIIP achieves superior performance in tasks such as object detection, segmentation, and image classification, compared to traditional image pyramid methods and single-branch networks, while reducing computational cost. Notably, when applying our method on a large-scale vision foundation model InternViT-6B, we improve its performance by 1%-2% on detection and segmentation with only 40%-60% of the original computation. These results validate the effectiveness of the PIIP approach and provide a new technical direction for future vision computing tasks. Our code and models are available at https://github.com/OpenGVLab/PIIP.
This study presents a comprehensive review of the potential of multimodal deep learning (DL) in medical diagnosis, using COVID-19 as a case example. Motivated by the success of artificial intelligence applications during the COVID-19 pandemic, this research aims to uncover the capabilities of DL in disease screening, prediction, and classification, and to derive insights that enhance the resilience, sustainability, and inclusiveness of science, technology, and innovation systems. Adopting a systematic approach, we investigate the fundamental methodologies, data sources, preprocessing steps, and challenges encountered in various studies and implementations. We explore the architecture of deep learning models, emphasising their data-specific structures and underlying algorithms. Subsequently, we compare different deep learning strategies utilised in COVID-19 analysis, evaluating them based on methodology, data, performance, and prerequisites for future research. By examining diverse data types and diagnostic modalities, this research contributes to scientific understanding and knowledge of the multimodal application of DL and its effectiveness in diagnosis. We have implemented and analysed 11 deep learning models using COVID-19 image, text, and speech (ie, cough) data. Our analysis revealed that the MobileNet model achieved the highest accuracy of 99.97% for COVID-19 image data and 93.73% for speech data (i.e., cough). However, the BiGRU model demonstrated superior performance in COVID-19 text classification with an accuracy of 99.89%. The broader implications of this research suggest potential benefits for other domains and disciplines that could leverage deep learning techniques for image, text, and speech analysis.
In a Content Based Image Retrieval (CBIR) System, the task is to retrieve similar images from a large database given a query image. The usual procedure is to extract some useful features from the query image, and retrieve images which have similar set of features. For this purpose, a suitable similarity measure is chosen, and images with high similarity scores are retrieved. Naturally the choice of these features play a very important role in the success of this system, and high level features are required to reduce the semantic gap. In this paper, we propose to use features derived from pre-trained network models from a deep-learning convolution network trained for a large image classification problem. This approach appears to produce vastly superior results for a variety of databases, and it outperforms many contemporary CBIR systems. We analyse the retrieval time of the method, and also propose a pre-clustering of the database based on the above-mentioned features which yields comparable results in a much shorter time in most of the cases.
Motivated by the lack of publicly available datasets of chest radiographs of positive patients with Coronavirus disease 2019 (COVID-19), we build the first-of-its-kind open dataset of synthetic COVID-19 chest X-ray images of high fidelity using an unsupervised domain adaptation approach by leveraging class conditioning and adversarial training. Our contributions are twofold. First, we show considerable performance improvements on COVID-19 detection using various deep learning architectures when employing synthetic images as additional training set. Second, we show how our image synthesis method can serve as a data anonymization tool by achieving comparable detection performance when trained only on synthetic data. In addition, the proposed data generation framework offers a viable solution to the COVID-19 detection in particular, and to medical image classification tasks in general. Our publicly available benchmark dataset consists of 21,295 synthetic COVID-19 chest X-ray images. The insights gleaned from this dataset can be used for preventive actions in the fight against the COVID-19 pandemic.
Detection Transformer (DETR) is a Transformer architecture based object detection model. In this paper, we demonstrate that it can also be used as a data augmenter. We term our approach as DETR assisted CutMix, or DeMix for short. DeMix builds on CutMix, a simple yet highly effective data augmentation technique that has gained popularity in recent years. CutMix improves model performance by cutting and pasting a patch from one image onto another, yielding a new image. The corresponding label for this new example is specified as the weighted average of the original labels, where the weight is proportional to the area of the patch. CutMix selects a random patch to be cut. In contrast, DeMix elaborately selects a semantically rich patch, located by a pre-trained DETR. The label of the new image is specified in the same way as in CutMix. Experimental results on benchmark datasets for image classification demonstrate that DeMix significantly outperforms prior art data augmentation methods including CutMix. Oue code is available at https://github.com/ZJLAB-AMMI/DeMix.