In this work we propose a novel joint training method for Visual Place Recognition (VPR), which simultaneously learns a global descriptor and a pair classifier for re-ranking. The pair classifier can predict whether a given pair of images are from the same place or not. The network only comprises Vision Transformer components for both the encoder and the pair classifier, and both components are trained using their respective class tokens. In existing VPR methods, typically the network is initialized using pre-trained weights from a generic image dataset such as ImageNet. In this work we propose an alternative pre-training strategy, by using Siamese Masked Image Modelling as a pre-training task. We propose a Place-aware image sampling procedure from a collection of large VPR datasets for pre-training our model, to learn visual features tuned specifically for VPR. By re-using the Mask Image Modelling encoder and decoder weights in the second stage of training, Pair-VPR can achieve state-of-the-art VPR performance across five benchmark datasets with a ViT-B encoder, along with further improvements in localization recall with larger encoders. The Pair-VPR website is: https://csiro-robotics.github.io/Pair-VPR.
eXplainable Artificial Intelligence (XAI) has emerged as an essential requirement when dealing with mission-critical applications, ensuring transparency and interpretability of the employed black box AI models. The significance of XAI spans various domains, from healthcare to finance, where understanding the decision-making process of deep learning algorithms is essential. Most AI-based computer vision models are often black boxes; hence, providing explainability of deep neural networks in image processing is crucial for their wide adoption and deployment in medical image analysis, autonomous driving, and remote sensing applications. Recently, several XAI methods for image classification tasks have been introduced. On the contrary, image segmentation has received comparatively less attention in the context of explainability, although it is a fundamental task in computer vision applications, especially in remote sensing. Only some research proposes gradient-based XAI algorithms for image segmentation. This paper adapts the recent gradient-free Sobol XAI method for semantic segmentation. To measure the performance of the Sobol method for segmentation, we propose a quantitative XAI evaluation method based on a learnable noise model. The main objective of this model is to induce noise on the explanation maps, where higher induced noise signifies low accuracy and vice versa. A benchmark analysis is conducted to evaluate and compare performance of three XAI methods, including Seg-Grad-CAM, Seg-Grad-CAM++ and Seg-Sobol using the proposed noise-based evaluation technique. This constitutes the first attempt to run and evaluate XAI methods using high-resolution satellite images.
The cryo-electron microscopy (Cryo-EM) becomes popular for macromolecular structure determination. However, the 2D images which Cryo-EM detects are of high noise and often mixed with multiple heterogeneous conformations or contamination, imposing a challenge for denoising. Traditional image denoising methods can not remove Cryo-EM image noise well when the signal-noise-ratio (SNR) of images is meager. Thus it is desired to develop new effective denoising techniques to facilitate further research such as 3D reconstruction, 2D conformation classification, and so on. In this paper, we approach the robust image denoising problem in Cryo-EM by a joint Autoencoder and Generative Adversarial Networks (GAN) method. Equipped with robust $\ell_1$ Autoencoder and some designs of robust $\beta$-GANs, one can stabilize the training of GANs and achieve the state-of-the-art performance of robust denoising with low SNR data and against possible information contamination. The method is evaluated by both a heterogeneous conformational dataset on the Thermus aquaticus RNA Polymerase (RNAP) and a homogenous dataset on the Plasmodium falciparum 80S ribosome dataset (EMPIRE-10028), in terms of Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), as well as heterogeneous conformation clustering. These results suggest that our proposed methodology provides an effective tool for Cryo-EM 2D image denoising. Our code is available in "https://github.com/ghl1995/denoise-gan-in-cryo-em".
Face alignment is a crucial step in preparing face images for feature extraction in facial analysis tasks. For applications such as face recognition, facial expression recognition, and facial attribute classification, alignment is widely utilized during both training and inference to standardize the positions of key landmarks in the face. It is well known that the application and method of face alignment significantly affect the performance of facial analysis models. However, the impact of alignment on face image quality has not been thoroughly investigated. Current FIQA studies often assume alignment as a prerequisite but do not explicitly evaluate how alignment affects quality metrics, especially with the advent of modern deep learning-based detectors that integrate detection and landmark localization. To address this need, our study examines the impact of face alignment on face image quality scores. We conducted experiments on the LFW, IJB-B, and SCFace datasets, employing MTCNN and RetinaFace models for face detection and alignment. To evaluate face image quality, we utilized several assessment methods, including SER-FIQ, FaceQAN, DifFIQA, and SDD-FIQA. Our analysis included examining quality score distributions for the LFW and IJB-B datasets and analyzing average quality scores at varying distances in the SCFace dataset. Our findings reveal that face image quality assessment methods are sensitive to alignment. Moreover, this sensitivity increases under challenging real-life conditions, highlighting the importance of evaluating alignment's role in quality assessment.
Convolutional Neural Networks (CNNs) have proven to be state-of-the-art models for supervised computer vision tasks, such as image classification. However, large labeled data sets are generally needed for the training and validation of such models. In many domains, unlabeled data is available but labeling is expensive, for instance when specific expert knowledge is required. Active Learning (AL) is one approach to mitigate the problem of limited labeled data. Through selecting the most informative and representative data instances for labeling, AL can contribute to more efficient learning of the model. Recent AL methods for CNNs propose different solutions for the selection of instances to be labeled. However, they do not perform consistently well and are often computationally expensive. In this paper, we propose a novel AL algorithm that efficiently learns from unlabeled data by capturing high prediction uncertainty. By replacing the softmax standard output of a CNN with the parameters of a Dirichlet density, the model learns to identify data instances that contribute efficiently to improving model performance during training. We demonstrate in several experiments with publicly available data that our method consistently outperforms other state-of-the-art AL approaches. It can be easily implemented and does not require extensive computational resources for training. Additionally, we are able to show the benefits of the approach on a real-world medical use case in the field of automated detection of visual signals for pneumonia on chest radiographs.
In recent years, hyperspectral image classification (HSIC) has achieved impressive progress with emerging studies on deep learning models. However, the classification performance downgrades due to the limited number of annotated samples, especially for minority classes. Notably, the imbalanced data dilemma is familiar in remote sensing hyperspectral image because the ground objects are commonly distributed without evenness. Therefore, this paper proposes a novel deep generative spectral-spatial classifier (DGSSC) for addressing the issues of imbalanced HSIC. Specifically, the DGSSC comprises three components, a two-stage encoder, a decoder, and a classifier, which are trained in an end-to-end manner. In particular, to exploit the abundant spectral-spatial features with relatively low computational complexity, the first stage of the encoder comprises successive three-dimensional (3D) and two-dimensional (2D) convolutions, exploring the spectral-spatial and deep spatial information. In addition, the second stage involves the deep latent variable model to achieve minority-class data augmentation. Furthermore, a patch distance-based reconstruction loss function is designed to facilitate the outputs of the decoder being more similar to the input 3D patch samples. The proposed DGSSC can outperform the state-of-the-art methods on three benchmark datasets, especially with its more robust prediction results. For instance, the DGSSC achieves a remarkable 97.85% mean overall accuracy with 0.24% standard deviation over ten independent runs with randomly selected imbalanced 1% training samples on the University of Pavia dataset.
Active learning - a class of algorithms that iteratively searches for the most informative samples to include in a training dataset - has been shown to be effective at annotating data for image classification. However, the use of active learning for object detection is still largely unexplored as determining informativeness of an object-location hypothesis is more difficult. In this paper, we address this issue and present two metrics for measuring the informativeness of an object hypothesis, which allow us to leverage active learning to reduce the amount of annotated data needed to achieve a target object detection performance. Our first metric measures 'localization tightness' of an object hypothesis, which is based on the overlapping ratio between the region proposal and the final prediction. Our second metric measures 'localization stability' of an object hypothesis, which is based on the variation of predicted object locations when input images are corrupted by noise. Our experimental results show that by augmenting a conventional active-learning algorithm designed for classification with the proposed metrics, the amount of labeled training data required can be reduced up to 25%. Moreover, on PASCAL 2007 and 2012 datasets our localization-stability method has an average relative improvement of 96.5% and 81.9% over the baseline method using classification only.
In this paper, we propose a novel approach for text classification based on clustering word embeddings, inspired by the bag of visual words model, which is widely used in computer vision. After each word in a collection of documents is represented as word vector using a pre-trained word embeddings model, a k-means algorithm is applied on the word vectors in order to obtain a fixed-size set of clusters. The centroid of each cluster is interpreted as a super word embedding that embodies all the semantically related word vectors in a certain region of the embedding space. Every embedded word in the collection of documents is then assigned to the nearest cluster centroid. In the end, each document is represented as a bag of super word embeddings by computing the frequency of each super word embedding in the respective document. We also diverge from the idea of building a single vocabulary for the entire collection of documents, and propose to build class-specific vocabularies for better performance. Using this kind of representation, we report results on two text mining tasks, namely text categorization by topic and polarity classification. On both tasks, our model yields better performance than the standard bag of words.
This paper investigates the application of the latest machine learning technique deep neural networks for classifying road surface conditions (RSC) based on images from smartphones. Traditional machine learning techniques such as support vector machine (SVM) and random forests (RF) have been attempted in literature; however, their classification performance has been less than desirable due to challenges associated with image noises caused by sunlight glare and residual salts. A deep learning model based on convolutional neural network (CNN) is proposed and evaluated for its potential to address these challenges for improved classification accuracy. In the proposed approach we introduce the idea of applying an existing CNN model that has been pre-trained using millions of images with proven high recognition accuracy. The model is extended with two additional fully-connected layers of neurons for learning the specific features of the RSC images. The whole model is then trained with a low learning rate for fine-tuning by using a small set of RSC images. Results show that the proposed model has the highest classification performance in comparison to the traditional machine learning techniques. The testing accuracy with different training dataset sizes is also analyzed, showing the potential of achieving much higher accuracy with a larger training dataset.
Semi-supervised image classification has shown substantial progress in learning from limited labeled data, but recent advances remain largely untested for clinical applications. Motivated by the urgent need to improve timely diagnosis of life-threatening heart conditions, especially aortic stenosis, we develop a benchmark dataset to assess semi-supervised approaches to two tasks relevant to cardiac ultrasound (echocardiogram) interpretation: view classification and disease severity classification. We find that a state-of-the-art method called MixMatch achieves promising gains in heldout accuracy on both tasks, learning from a large volume of truly unlabeled images as well as a labeled set collected at great expense to achieve better performance than is possible with the labeled set alone. We further pursue patient-level diagnosis prediction, which requires aggregating across hundreds of images of diverse view types, most of which are irrelevant, to make a coherent prediction. The best patient-level performance is achieved by new methods that prioritize diagnosis predictions from images that are predicted to be clinically-relevant views and transfer knowledge from the view task to the diagnosis task. We hope our released Tufts Medical Echocardiogram Dataset and evaluation framework inspire further improvements in multi-task semi-supervised learning for clinical applications.
Learning visual representation of high quality is essential for image classification. Recently, a series of contrastive representation learning methods have achieved preeminent success. Particularly, SupCon outperformed the dominant methods based on cross-entropy loss in representation learning. However, we notice that there could be potential ethical risks in supervised contrastive learning. In this paper, we for the first time analyze unfairness caused by supervised contrastive learning and propose a new Fair Supervised Contrastive Loss (FSCL) for fair visual representation learning. Inheriting the philosophy of supervised contrastive learning, it encourages representation of the same class to be closer to each other than that of different classes, while ensuring fairness by penalizing the inclusion of sensitive attribute information in representation. In addition, we introduce a group-wise normalization to diminish the disparities of intra-group compactness and inter-class separability between demographic groups that arouse unfair classification. Through extensive experiments on CelebA and UTK Face, we validate that the proposed method significantly outperforms SupCon and existing state-of-the-art methods in terms of the trade-off between top-1 accuracy and fairness. Moreover, our method is robust to the intensity of data bias and effectively works in incomplete supervised settings. Our code is available at https://github.com/sungho-CoolG/FSCL.
Contrastive Vision-Language Pre-training, known as CLIP, has provided a new paradigm for learning visual representations using large-scale image-text pairs. It shows impressive performance on downstream tasks by zero-shot knowledge transfer. To further enhance CLIP's adaption capability, existing methods proposed to fine-tune additional learnable modules, which significantly improves the few-shot performance but introduces extra training time and computational resources. In this paper, we propose a training-free adaption method for CLIP to conduct few-shot classification, termed as Tip-Adapter, which not only inherits the training-free advantage of zero-shot CLIP but also performs comparably to those training-required approaches. Tip-Adapter constructs the adapter via a key-value cache model from the few-shot training set, and updates the prior knowledge encoded in CLIP by feature retrieval. On top of that, the performance of Tip-Adapter can be further boosted to be state-of-the-art on ImageNet by fine-tuning the cache model for 10$\times$ fewer epochs than existing methods, which is both effective and efficient. We conduct extensive experiments of few-shot classification on 11 datasets to demonstrate the superiority of our proposed methods. Code is released at https://github.com/gaopengcuhk/Tip-Adapter.
State-of-the-art (SOTA) deep learning mammogram classifiers, trained with weakly-labelled images, often rely on global models that produce predictions with limited interpretability, which is a key barrier to their successful translation into clinical practice. On the other hand, prototype-based models improve interpretability by associating predictions with training image prototypes, but they are less accurate than global models and their prototypes tend to have poor diversity. We address these two issues with the proposal of BRAIxProtoPNet++, which adds interpretability to a global model by ensembling it with a prototype-based model. BRAIxProtoPNet++ distills the knowledge of the global model when training the prototype-based model with the goal of increasing the classification accuracy of the ensemble. Moreover, we propose an approach to increase prototype diversity by guaranteeing that all prototypes are associated with different training images. Experiments on weakly-labelled private and public datasets show that BRAIxProtoPNet++ has higher classification accuracy than SOTA global and prototype-based models. Using lesion localisation to assess model interpretability, we show BRAIxProtoPNet++ is more effective than other prototype-based models and post-hoc explanation of global models. Finally, we show that the diversity of the prototypes learned by BRAIxProtoPNet++ is superior to SOTA prototype-based approaches.
The success of Deep Neural Network (DNN) models significantly depends on the quality of provided annotations. In medical image segmentation, for example, having multiple expert annotations for each data point is common to minimize subjective annotation bias. Then, the goal of estimation is to filter out the label noise and recover the ground-truth masks, which are not explicitly given. This paper proposes a probabilistic model for noisy observations that allows us to build a confident classification and segmentation models. To accomplish it, we explicitly model label noise and introduce a new information-based regularization that pushes the network to recover the ground-truth labels. In addition, for segmentation task we adjust the loss function by prioritizing learning in high-confidence regions where all the annotators agree on labeling. We evaluate the proposed method on a series of classification tasks such as noisy versions of MNIST, CIFAR-10, Fashion-MNIST datasets as well as CIFAR-10N, which is real-world dataset with noisy human annotations. Additionally, for segmentation task, we consider several medical imaging datasets, such as, LIDC and RIGA that reflect real-world inter-variability among multiple annotators. Our experiments show that our algorithm outperforms state-of-the-art solutions for the considered classification and segmentation problems.
Endoscopic imaging is commonly used to diagnose Ulcerative Colitis (UC) and classify its severity. It has been shown that deep learning based methods are effective in automated analysis of these images and can potentially be used to aid medical doctors. Unleashing the full potential of these methods depends on the availability of large amount of labeled images; however, obtaining and labeling these images are quite challenging. In this paper, we propose a active learning based generative augmentation method. The method involves generating a large number of synthetic samples by training using a small dataset consisting of real endoscopic images. The resulting data pool is narrowed down by using active learning methods to select the most informative samples, which are then used to train a classifier. We demonstrate the effectiveness of our method through experiments on a publicly available endoscopic image dataset. The results show that using synthesized samples in conjunction with active learning leads to improved classification performance compared to using only the original labeled examples and the baseline classification performance of 68.1% increases to 74.5% in terms of Quadratic Weighted Kappa (QWK) Score. Another observation is that, attaining equivalent performance using only real data necessitated three times higher number of images.
The goal for classification is to correctly assign labels to unseen samples. However, most methods misclassify samples with unseen labels and assign them to one of the known classes. Open-Set Classification (OSC) algorithms aim to maximize both closed and open-set recognition capabilities. Recent studies showed the utility of such algorithms on small-scale data sets, but limited experimentation makes it difficult to assess their performances in real-world problems. Here, we provide a comprehensive comparison of various OSC algorithms, including training-based (SoftMax, Garbage, EOS) and post-processing methods (Maximum SoftMax Scores, Maximum Logit Scores, OpenMax, EVM, PROSER), the latter are applied on features from the former. We perform our evaluation on three large-scale protocols that mimic real-world challenges, where we train on known and negative open-set samples, and test on known and unknown instances. Our results show that EOS helps to improve performance of almost all post-processing algorithms. Particularly, OpenMax and PROSER are able to exploit better-trained networks, demonstrating the utility of hybrid models. However, while most algorithms work well on negative test samples -- samples of open-set classes seen during training -- they tend to perform poorly when tested on samples of previously unseen unknown classes, especially in challenging conditions.
Face anti-spoofing (FAS) is crucial for protecting facial recognition systems from presentation attacks. Previous methods approached this task as a classification problem, lacking interpretability and reasoning behind the predicted results. Recently, multimodal large language models (MLLMs) have shown strong capabilities in perception, reasoning, and decision-making in visual tasks. However, there is currently no universal and comprehensive MLLM and dataset specifically designed for FAS task. To address this gap, we propose FaceShield, a MLLM for FAS, along with the corresponding pre-training and supervised fine-tuning (SFT) datasets, FaceShield-pre10K and FaceShield-sft45K. FaceShield is capable of determining the authenticity of faces, identifying types of spoofing attacks, providing reasoning for its judgments, and detecting attack areas. Specifically, we employ spoof-aware vision perception (SAVP) that incorporates both the original image and auxiliary information based on prior knowledge. We then use an prompt-guided vision token masking (PVTM) strategy to random mask vision tokens, thereby improving the model's generalization ability. We conducted extensive experiments on three benchmark datasets, demonstrating that FaceShield significantly outperforms previous deep learning models and general MLLMs on four FAS tasks, i.e., coarse-grained classification, fine-grained classification, reasoning, and attack localization. Our instruction datasets, protocols, and codes will be released soon.
A Trustworthy Clinical Decision Support Framework for Brain Tumor MRI Classification: Integrating Attention-Guided Learning, Explainable AI, and Out-of-Distribution Validation
뇌종양 진단을 위한 딥러닝 모델은 높은 분류 정확도를 달성하는 것 이상을 해야 한다. 실제 사용을 위해서는 이해할 수 있는 예측을 제공하고, 부적합한 입력을 인식하며, 사용 가능한 임상 시스템 안에서 작동해야 한다. 본 논문은 뇌 MRI를 신경교종, 수막종, 뇌하수체 종양, 종양 없음의 네 범주로 분류하는 프레임워크를 제시한다. 이 모델은 합성곱 블록 어텐션 모듈(CBAM)을 결합한 InceptionResNetV2를 사용하며, Grad-CAM으로 예측에 대한 시각적 설명을 제공한다. 2단계 분포 외(OOD) 메커니즘은 먼저 그레이스케일 검사를 수행한 뒤 마할라노비스 거리, 소프트맥스 신뢰도, 예측 엔트로피를 이용해 부적합한 입력을 걸러낸다. 이러한 구성 요소는 실시간 웹 애플리케이션인 NeuroScan AI로 통합되었다. 12,064개 이미지로 구성된 Mendeley 뇌종양 MRI 데이터셋에서 평가한 결과, 이 프레임워크는 검증 정확도 98.70%, 테스트 정확도 96.73%, 매크로 평균 AUC 0.9965를 달성하였다. OOD 파이프라인은 예비적인 100개 이미지 벤치마크에서 99%의 검출 정확도를 보였다. Grad-CAM 시각화는 네 범주 모두에서 임상적으로 알려진 종양 위치와 정성적으로 부합하였다. 종합하면 본 연구는 분류, 설명 가능성, 입력 검증, 배포를 하나의 프레임워크로 통합하였으며, 더 폭넓은 임상 및 OOD 검증이 여전히 필요함을 인정한다.
Exposure to intense illumination light is an unavoidable consequence of fluorescence microscopy, and poses a risk to the health of the sample in every live-cell fluorescence microscopy experiment. Furthermore, the possible side-effects of phototoxicity on the scientific conclusions that are drawn from an imaging experiment are often unaccounted for. Previously, controlling for phototoxicity in imaging experiments required additional labels and experiments, limiting its widespread application. Here we provide a proof-of-principle demonstration that the phototoxic effects of an imaging experiment can be identified directly from a single phase-contrast image using deep convolutional neural networks (ConvNets). This lays the groundwork for an automated tool for assessing cell health in a wide range of imaging experiments. Interpretability of such a method is crucial for its adoption. We take steps towards interpreting the classification mechanism of the trained ConvNet by visualizing salient features of images that contribute to accurate classification.
In this paper we show that by carefully making good choices for various detailed but important factors in a visual recognition framework using deep learning features, one can achieve a simple, efficient, yet highly accurate image classification system. We first list 5 important factors, based on both existing researches and ideas proposed in this paper. These important detailed factors include: 1) $\ell_2$ matrix normalization is more effective than unnormalized or $\ell_2$ vector normalization, 2) the proposed natural deep spatial pyramid is very effective, and 3) a very small $K$ in Fisher Vectors surprisingly achieves higher accuracy than normally used large $K$ values. Along with other choices (convolutional activations and multiple scales), the proposed DSP framework is not only intuitive and efficient, but also achieves excellent classification accuracy on many benchmark datasets. For example, DSP's accuracy on SUN397 is 59.78%, significantly higher than previous state-of-the-art (53.86%).