Automatic classification of trees using remotely sensed data has been a dream of many scientists and land use managers. Recently, Unmanned aerial vehicles (UAV) has been expected to be an easy-to-use, cost-effective tool for remote sensing of forests, and deep learning has attracted attention for its ability concerning machine vision. In this study, using a commercially available UAV and a publicly available package for deep learning, we constructed a machine vision system for the automatic classification of trees. In our method, we segmented a UAV photography image of forest into individual tree crowns and carried out object-based deep learning. As a result, the system was able to classify 7 tree types at 89.0% accuracy. This performance is notable because we only used basic RGB images from a standard UAV. In contrast, most of previous studies used expensive hardware such as multispectral imagers to improve the performance. This result means that our method has the potential to classify individual trees in a cost-effective manner. This can be a usable tool for many forest researchers and managements.
This work describes algorithms for performing discrete object detection, specifically in the case of buildings, where usually only low quality RGB-only geospatial reflective imagery is available. We utilize new candidate search and feature extraction techniques to reduce the problem to a machine learning (ML) classification task. Here we can harness the complex patterns of contrast features contained in training data to establish a model of buildings. We avoid costly sliding windows to generate candidates; instead we innovatively stitch together well known image processing techniques to produce candidates for building detection that cover 80-85% of buildings. Reducing the number of possible candidates is important due to the scale of the problem. Each candidate is subjected to classification which, although linear, costs time and prohibits large scale evaluation. We propose a candidate alignment algorithm to boost classification performance to 80-90% precision with a linear time algorithm and show it has negligible cost. Also, we propose a new concept called a Permutable Haar Mesh (PHM) which we use to form and traverse a search space to recover candidate buildings which were lost in the initial preprocessing phase.
Typically, binary classification lens-finding schemes are used to discriminate between lens candidates and non-lenses. However, these models often suffer from substantial false-positive classifications. Such false positives frequently occur due to images containing objects such as crowded sources, galaxies with arms, and also images with a central source and smaller surrounding sources. Therefore, a model might confuse the stated circumstances with an Einstein ring. It has been proposed that by allowing such commonly misclassified image types to constitute their own classes, machine learning models will more easily be able to learn the difference between images that contain real lenses, and images that contain lens imposters. Using Hubble Space Telescope (HST) images, in the F814W filter, we compare the usage of binary and multi-class classification models applied to the lens finding task. From our findings, we conclude there is not a significant benefit to using the multi-class model over a binary model. We will also present the results of a simple lens search using a multi-class machine learning model, and potential new lens candidates.
Few-shot image classification consists of two consecutive learning processes: 1) In the meta-learning stage, the model acquires a knowledge base from a set of training classes. 2) During meta-testing, the acquired knowledge is used to recognize unseen classes from very few examples. Inspired by the compositional representation of objects in humans, we train a neural network architecture that explicitly represents objects as a dictionary of shared components and their spatial composition. In particular, during meta-learning, we train a knowledge base that consists of a dictionary of component representations and a dictionary of component activation maps that encode common spatial activation patterns of components. The elements of both dictionaries are shared among the training classes. During meta-testing, the representation of unseen classes is learned using the component representations and the component activation maps from the knowledge base. Finally, an attention mechanism is used to strengthen those components that are most important for each category. We demonstrate the value of our interpretable compositional learning framework for a few-shot classification using miniImageNet, tieredImageNet, CIFAR-FS, and FC100, where we achieve comparable performance.
Out-of-distribution (OOD) detection has attracted a large amount of attention from the machine learning research community in recent years due to its importance in deployed systems. Most of the previous studies focused on the detection of OOD samples in the multi-class classification task. However, OOD detection in the multi-label classification task, a more common real-world use case, remains an underexplored domain. In this research, we propose YolOOD - a method that utilizes concepts from the object detection domain to perform OOD detection in the multi-label classification task. Object detection models have an inherent ability to distinguish between objects of interest (in-distribution) and irrelevant objects (e.g., OOD objects) in images that contain multiple objects belonging to different class categories. These abilities allow us to convert a regular object detection model into an image classifier with inherent OOD detection capabilities with just minor changes. We compare our approach to state-of-the-art OOD detection methods and demonstrate YolOOD's ability to outperform these methods on a comprehensive suite of in-distribution and OOD benchmark datasets.
Computer Vision for Analyzing and Classifying cells and tissues often require rigorous lab procedures and so automated Computer Vision solutions have been sought. Most work in such field usually requires Feature Extractions before the analysis of such features via Machine Learning and Machine Vision algorithms. We developed a Convolutional Neural Network that classifies 5 types of epithelial breast cell lines comprised of two human cancer lines, 2 normal immortalized lines, and 1 immortalized mouse line (MDA-MB-468, MCF7, 10A, 12A and HC11) without requiring feature extraction. The Multiclass Cell Line Classification Convolutional Neural Network extends our earlier work on a Binary Breast Cancer Cell Line Classification model. CellLineNet is 31-layer Convolutional Neural Network trained, validated and tested on a 3,252 image dataset of 5 types of Epithelial Breast cell Lines (MDA-MB-468, MCF7, 10A, 12A and HC11) in an end-to-end fashion. End-to-End Learning enables CellLineNet to identify and learn on its own, visual features and regularities most important to Breast Cancer Cell Line Classification from the dataset of images. Using Transfer Learning, the 28-layer MobileNet Convolutional Neural Network architecture with pre-trained ImageNet weights is extended and fine tuned to the Multiclass Epithelial Breast cell Line Classification problem. CellLineNet simply requires an imaged Cell Line as input and it outputs the type of breast epithelial cell line (MDA-MB-468, MCF7, 10A, 12A or HC11) as predicted probabilities for the 5 classes. CellLineNet scored a 96.67% Accuracy.
Dropout and similar stochastic neural network regularization methods are often interpreted as implicitly averaging over a large ensemble of models. We propose STE (stochastically trained ensemble) layers, which enhance the averaging properties of such methods by training an ensemble of weight matrices with stochastic regularization while explicitly averaging outputs. This provides stronger regularization with no additional computational cost at test time. We show consistent improvement on various image classification tasks using standard network topologies.
In Bitcoin entity classification, results are strongly conditioned by the ground-truth dataset, especially when applying supervised machine learning approaches. However, these ground-truth datasets are frequently affected by significant class imbalance as generally they contain much more information regarding legal services (Exchange, Gambling), than regarding services that may be related to illicit activities (Mixer, Service). Class imbalance increases the complexity of applying machine learning techniques and reduces the quality of classification results, especially for underrepresented, but critical classes. In this paper, we propose to address this problem by using Generative Adversarial Networks (GANs) for Bitcoin data augmentation as GANs recently have shown promising results in the domain of image classification. However, there is no "one-fits-all" GAN solution that works for every scenario. In fact, setting GAN training parameters is non-trivial and heavily affects the quality of the generated synthetic data. We therefore evaluate how GAN parameters such as the optimization function, the size of the dataset and the chosen batch size affect GAN implementation for one underrepresented entity class (Mining Pool) and demonstrate how a "good" GAN configuration can be obtained that achieves high similarity between synthetically generated and real Bitcoin address data. To the best of our knowledge, this is the first study presenting GANs as a valid tool for generating synthetic address data for data augmentation in Bitcoin entity classification.
In the advent of wearable body-cameras, human activity classification from First-Person Videos (FPV) has become a topic of increasing importance for various applications, including in life-logging, law-enforcement, sports, workplace, and healthcare. One of the challenging aspects of FPV is its exposure to potentially sensitive objects within the user's field of view. In this work, we developed a privacy-aware activity classification system focusing on office videos. We utilized a Mask-RCNN with an Inception-ResNet hybrid as a feature extractor for detecting, and then blurring out sensitive objects (e.g., digital screens, human face, paper) from the videos. For activity classification, we incorporate an ensemble of Recurrent Neural Networks (RNNs) with ResNet, ResNext, and DenseNet based feature extractors. The proposed system was trained and evaluated on the FPV office video dataset that includes 18-classes made available through the IEEE Video and Image Processing (VIP) Cup 2019 competition. On the original unprotected FPVs, the proposed activity classifier ensemble reached an accuracy of 85.078% with precision, recall, and F1 scores of 0.88, 0.85 & 0.86, respectively. On privacy protected videos, the performances were slightly degraded, with accuracy, precision, recall, and F1 scores at 73.68%, 0.79, 0.75, and 0.74, respectively. The presented system won the 3rd prize in the IEEE VIP Cup 2019 competition.
Recently the vision transformer (ViT) architecture, where the backbone purely consists of self-attention mechanism, has achieved very promising performance in visual classification. However, the high performance of the original ViT heavily depends on pretraining using ultra large-scale datasets, and it significantly underperforms on ImageNet-1K if trained from scratch. This paper makes the efforts toward addressing this problem, by carefully considering the role of visual tokens. First, for classification head, existing ViT only exploits class token while entirely neglecting rich semantic information inherent in high-level visual tokens. Therefore, we propose a new classification paradigm, where the second-order, cross-covariance pooling of visual tokens is combined with class token for final classification. Meanwhile, a fast singular value power normalization is proposed for improving the second-order pooling. Second, the original ViT employs the naive embedding of fixed-size image patches, lacking the ability to model translation equivariance and locality. To alleviate this problem, we develop a light-weight, hierarchical module based on off-the-shelf convolutions for visual token embedding. The proposed architecture, which we call So-ViT, is thoroughly evaluated on ImageNet-1K. The results show our models, when trained from scratch, outperform the competing ViT variants, while being on par with or better than state-of-the-art CNN models. Code is available at https://github.com/jiangtaoxie/So-ViT
Cardiac Magnetic Resonance Imaging (MRI) plays an important role in the analysis of cardiac function. However, the acquisition is often accompanied by motion artefacts because of the difficulty of breath-hold, especially for acute symptoms patients. Therefore, it is essential to assess the quality of cardiac MRI for further analysis. Time-consuming manual-based classification is not conducive to the construction of an end-to-end computer aided diagnostic system. To overcome this problem, an automatic cardiac MRI quality estimation framework using ensemble and transfer learning is proposed in this work. Multiple pre-trained models were initialised and fine-tuned on 2-dimensional image patches sampled from the training data. In the model inference process, decisions from these models are aggregated to make a final prediction. The framework has been evaluated on CMRxMotion grand challenge (MICCAI 2022) dataset which is small, multi-class, and imbalanced. It achieved a classification accuracy of 78.8% and 70.0% on the training set (5-fold cross-validation) and a validation set, respectively. The final trained model was also evaluated on an independent test set by the CMRxMotion organisers, which achieved the classification accuracy of 72.5% and Cohen's Kappa of 0.6309 (ranked top 1 in this grand challenge). Our code is available on Github: https://github.com/ruizhe-l/CMRxMotion.
Whole-slide image (WSI) analysis plays a crucial role in cancer diagnosis and treatment. In addressing the demands of this critical task, self-supervised learning (SSL) methods have emerged as a valuable resource, leveraging their efficiency in circumventing the need for a large number of annotations, which can be both costly and time-consuming to deploy supervised methods. Nevertheless, patch-wise representation may exhibit instability in performance, primarily due to class imbalances stemming from patch selection within WSIs. In this paper, we introduce Nearby Patch Contrastive Learning (NearbyPatchCL), a novel self-supervised learning method that leverages nearby patches as positive samples and a decoupled contrastive loss for robust representation learning. Our method demonstrates a tangible enhancement in performance for downstream tasks involving patch-level multi-class classification. Additionally, we curate a new dataset derived from WSIs sourced from the Canine Cutaneous Cancer Histology, thus establishing a benchmark for the rigorous evaluation of patch-level multi-class classification methodologies. Intensive experiments show that our method significantly outperforms the supervised baseline and state-of-the-art SSL methods with top-1 classification accuracy of 87.56%. Our method also achieves comparable results while utilizing a mere 1% of labeled data, a stark contrast to the 100% labeled data requirement of other approaches. Source code: https://github.com/nvtien457/NearbyPatchCL
This survey aims at reviewing recent computer vision techniques used in the assessment of image aesthetic quality. Image aesthetic assessment aims at computationally distinguishing high-quality photos from low-quality ones based on photographic rules, typically in the form of binary classification or quality scoring. A variety of approaches has been proposed in the literature trying to solve this challenging problem. In this survey, we present a systematic listing of the reviewed approaches based on visual feature types (hand-crafted features and deep features) and evaluation criteria (dataset characteristics and evaluation metrics). Main contributions and novelties of the reviewed approaches are highlighted and discussed. In addition, following the emergence of deep learning techniques, we systematically evaluate recent deep learning settings that are useful for developing a robust deep model for aesthetic scoring. Experiments are conducted using simple yet solid baselines that are competitive with the current state-of-the-arts. Moreover, we discuss the possibility of manipulating the aesthetics of images through computational approaches. We hope that our survey could serve as a comprehensive reference source for future research on the study of image aesthetic assessment.
Model generalizability to unseen datasets, concerned with in-the-wild robustness, is less studied for indoor single-image depth prediction. We leverage gradient-based meta-learning for higher generalizability on zero-shot cross-dataset inference. Unlike the most-studied image classification in meta-learning, depth is pixel-level continuous range values, and mappings from each image to depth vary widely across environments. Thus no explicit task boundaries exist. We instead propose fine-grained task that treats each RGB-D pair as a task in our meta-optimization. We first show meta-learning on limited data induces much better prior (max +29.4\%). Using meta-learned weights as initialization for following supervised learning, without involving extra data or information, it consistently outperforms baselines without the method. Compared to most indoor-depth methods that only train/ test on a single dataset, we propose zero-shot cross-dataset protocols, closely evaluate robustness, and show consistently higher generalizability and accuracy by our meta-initialization. The work at the intersection of depth and meta-learning potentially drives both research streams to step closer to practical use.
As deep learning-based systems have become an integral part of everyday life, limitations in their generalization ability have begun to emerge. Machine learning algorithms typically rely on the i.i.d. assumption, meaning that their training and validation data are expected to follow the same distribution, which does not necessarily hold in practice. In the case of image classification, one frequent reason that algorithms fail to generalize is that they rely on spurious correlations present in training data, such as associating image styles with target classes. These associations may not be present in the unseen test data, leading to significant degradation of their effectiveness. In this work, we attempt to mitigate this Domain Generalization (DG) problem by training a robust feature extractor which disregards features attributed to image-style but infers based on style-invariant image representations. To achieve this, we train CycleGAN models to learn the different styles present in the training data and randomly mix them together to create samples with novel style attributes to improve generalization. Experimental results on the PACS DG benchmark validate the proposed method.
The key of zero-shot learning (ZSL) is how to find the information transfer model for bridging the gap between images and semantic information (texts or attributes). Existing ZSL methods usually construct the compatibility function between images and class labels with the consideration of the relevance on the semantic classes (the manifold structure of semantic classes). However, the relationship of image classes (the manifold structure of image classes) is also very important for the compatibility model construction. It is difficult to capture the relationship among image classes due to unseen classes, so that the manifold structure of image classes often is ignored in ZSL. To complement each other between the manifold structure of image classes and that of semantic classes information, we propose structure propagation (SP) for improving the performance of ZSL for classification. SP can jointly consider the manifold structure of image classes and that of semantic classes for approximating to the intrinsic structure of object classes. Moreover, the SP can describe the constrain condition between the compatibility function and these manifold structures for balancing the influence of the structure propagation iteration. The SP solution provides not only unseen class labels but also the relationship of two manifold structures that encode the positive transfer in structure propagation. Experimental results demonstrate that SP can attain the promising results on the AwA, CUB, Dogs and SUN databases.
In the recent years, convolutional neural networks have transformed the field of medical image analysis due to their capacity to learn discriminative image features for a variety of classification and regression tasks. However, successfully learning these features requires a large amount of manually annotated data, which is expensive to acquire and limited by the available resources of expert image analysts. Therefore, unsupervised, weakly-supervised and self-supervised feature learning techniques receive a lot of attention, which aim to utilise the vast amount of available data, while at the same time avoid or substantially reduce the effort of manual annotation. In this paper, we propose a novel way for training a cardiac MR image segmentation network, in which features are learnt in a self-supervised manner by predicting anatomical positions. The anatomical positions serve as a supervisory signal and do not require extra manual annotation. We demonstrate that this seemingly simple task provides a strong signal for feature learning and with self-supervised learning, we achieve a high segmentation accuracy that is better than or comparable to a U-net trained from scratch, especially at a small data setting. When only five annotated subjects are available, the proposed method improves the mean Dice metric from 0.811 to 0.852 for short-axis image segmentation, compared to the baseline U-net.
테이블형(tabular) 데이터를 시각적 표현으로 변환하는 테이블-이미지(tabular-to-image) 기법은 심층 학습(deep learning) 모델의 높은 성능을 활용하기 위한 새로운 패러다임으로 부상했습니다. 이러한 장점에도 불구하고, 분포 변화(distribution shift) 상황에서 이들 방법의 강건성(robustness)은 여전히 충분히 연구되지 않았습니다. 테스트 시점 증강(TTA, Test-Time Augmentation)은 각 입력에 대해 다양하게 변환된 뷰(view)들의 예측값을 종합하여 모델의 일반화 및 강건성을 개선하는 이미지 분류(image classification)의 효과적인 접근 방식입니다. 본 연구는 테이블-이미지 기법으로 생성된 표현에 대해 TTA 기술이 분포 외(OOD, Out-Of-Distribution) 환경에서의 예측 성능에 미치는 영향을 평가합니다. TINTO, IGTD, DeepInsight, BIE, DistanceMatrix, Fotomics의 6가지 테이블-이미지 인코딩 방법을 고려했습니다. 또한 기하학적(Geometric), 측광적(Photometric), 구조적(Structural), 주파수/인코딩(Frequency/Encoding), 믹스업(Mixup), 복합(Composite)의 6가지 유형으로 구성된 25가지 TTA 기법을 사용했습니다. 테이블 데이터에 대한 분포 변화의 영향을 평가하도록 설계된 분포 내(in-distribution) 및 OOD 테스트 서브셋을 제공하는 TableShift 벤치마크의 두 가지 데이터셋(HELOC 및 Voting)을 활용했습니다. 연구 결과는 TTA가 OOD 성능을 향상시키며, 복합 및 측광적 전략이 강건성과 분산 사이에서 최적의 절충안을 제공함을 보여줍니다. 반면 인코더의 특징-강도(feature-to-intensity) 매핑을 변경하는 주파수 영역 변환은 지속적으로 성능을 저하시킵니다. 이러한 발견은 특히 분포 변화 환경에서 테이블 데이터로부터 유도된 이미지 표현으로 학습된 분류기의 강건성과 일반화를 향상시키는 유망한 접근법으로서 TTA의 가능성을 강조합니다.
Pre-trained vision-language models like CLIP have recently shown superior performances on various downstream tasks, including image classification and segmentation. However, in fine-grained image re-identification (ReID), the labels are indexes, lacking concrete text descriptions. Therefore, it remains to be determined how such models could be applied to these tasks. This paper first finds out that simply fine-tuning the visual model initialized by the image encoder in CLIP, has already obtained competitive performances in various ReID tasks. Then we propose a two-stage strategy to facilitate a better visual representation. The key idea is to fully exploit the cross-modal description ability in CLIP through a set of learnable text tokens for each ID and give them to the text encoder to form ambiguous descriptions. In the first training stage, image and text encoders from CLIP keep fixed, and only the text tokens are optimized from scratch by the contrastive loss computed within a batch. In the second stage, the ID-specific text tokens and their encoder become static, providing constraints for fine-tuning the image encoder. With the help of the designed loss in the downstream task, the image encoder is able to represent data as vectors in the feature embedding accurately. The effectiveness of the proposed strategy is validated on several datasets for the person or vehicle ReID tasks. Code is available at https://github.com/Syliz517/CLIP-ReID.
Data augmentation is an effective way to improve the performance of deep networks. Unfortunately, current methods are mostly developed for high-level vision tasks (e.g., classification) and few are studied for low-level vision tasks (e.g., image restoration). In this paper, we provide a comprehensive analysis of the existing augmentation methods applied to the super-resolution task. We find that the methods discarding or manipulating the pixels or features too much hamper the image restoration, where the spatial relationship is very important. Based on our analyses, we propose CutBlur that cuts a low-resolution patch and pastes it to the corresponding high-resolution image region and vice versa. The key intuition of CutBlur is to enable a model to learn not only "how" but also "where" to super-resolve an image. By doing so, the model can understand "how much", instead of blindly learning to apply super-resolution to every given pixel. Our method consistently and significantly improves the performance across various scenarios, especially when the model size is big and the data is collected under real-world environments. We also show that our method improves other low-level vision tasks, such as denoising and compression artifact removal.