뇌암은 현대 의학에서 가장 중대한 난제 중 하나로, 초기 단계 진단의 정확도가 환자의 생존과 치료 효과를 좌우하는 결정적 요인이다. 자기공명영상(MRI)은 신경 구조를 시각화하는 데 있어 확립된 표준이지만, 이러한 고차원 스캔을 해석하는 일은 의료진 간의 주관적 편차와 복잡한 의료 영상에 내재된 잡음으로 인해 흔히 복잡해진다. 최근의 접근법은 종종 매개변수가 많은 심층 학습 아키텍처에 의존하지만, 이러한 모델은 상당한 계산 비용을 수반하는 경우가 많고 효과적인 학습을 위해 방대한 데이터를 필요로 한다. 본 연구는 정밀한 특징 추출을 위해 Oriented FAST and Rotated BRIEF(ORB) 알고리즘을, 분류를 위해 서포트 벡터 머신(SVM)을 활용하는 하이브리드 프레임워크를 제안한다 [1], [2]. 제안한 접근법은 약 99.5%에 달하는 상당한 데이터 감소를 달성하며, 이를 통해 종양 식별에 필수적인 핵심 진단 패턴은 보존하면서 정보가 없는 배경 데이터의 영향을 효과적으로 최소화한다. 특징 희소성과 견고한 커널 기반 분류기 사이의 균형을 맞춤으로써, 이 방법론은 과대 매개변수화된 시스템의 한계를 해소하는 동시에 높은 진단 신뢰성을 유지한다. Br35H 데이터셋에서 수행한 실험 평가 결과, 이 프레임워크는 97.5%의 분류 정확도를 달성하였다. 이러한 결과는 국소적 특징 표현과 최적화된 분류의 통합이 의료 영상 분석을 위한 신뢰할 수 있고 자원 효율적인 대안을 제공하며, 과도한 계산 부담 없이도 성능을 유지하는 체계적인 해법이 될 수 있음을 시사한다.
Deep convolutional neural networks have demonstrated promising performance on image classification tasks, but the manual design process becomes more and more complex due to the fast depth growth and the increasingly complex topologies of convolutional neural networks. As a result, neural architecture search has emerged to automatically design convolutional neural networks that outperform handcrafted counterparts. However, the computational cost is immense, e.g. 22,400 GPU-days and 2,000 GPU-days for two outstanding neural architecture search works named NAS and NASNet, respectively, which motivates this work. A new effective and efficient surrogate-assisted particle swarm optimisation algorithm is proposed to automatically evolve convolutional neural networks. This is achieved by proposing a novel surrogate model, a new method of creating a surrogate dataset and a new encoding strategy to encode variable-length blocks of convolutional neural networks, all of which are integrated into a particle swarm optimisation algorithm to form the proposed method. The proposed method shows its effectiveness by achieving competitive error rates of 3.49% on the CIFAR-10 dataset, 18.49% on the CIFAR-100 dataset, and 1.82% on the SVHN dataset. The convolutional neural network blocks are efficiently learned by the proposed method from CIFAR-10 within 3 GPU-days due to the acceleration achieved by the surrogate model and the surrogate dataset to avoid the training of 80.1% of convolutional neural network blocks represented by the particles. Without any further search, the evolved blocks from CIFAR-10 can be successfully transferred to CIFAR-100 and SVHN, which exhibits the transferability of the block learned by the proposed method.
A method of a Convolutional Neural Networks (CNN) for image classification with image preprocessing and hyperparameters tuning was proposed. The method aims at increasing the predictive performance for COVID-19 diagnosis while more complex model architecture. Firstly, the CNN model includes four similar convolutional layers followed by a flattening and two dense layers. This work proposes a less complex solution based on simply classifying 2D-slices of Computed Tomography scans. Despite the simplicity in architecture, the proposed CNN model showed improved quantitative results exceeding state-of-the-art when predicting slice cases. The results were achieved on the annotated CT slices of the COV-19-CT-DB dataset. Secondly, the original dataset was processed via anatomy-relevant masking of slice, removing none-representative slices from the CT volume, and hyperparameters tuning. For slice processing, a fixed-sized rectangular area was used for cropping an anatomy-relevant region-of-interest in the images, and a threshold based on the number of white pixels in binarized slices was employed to remove none-representative slices from the 3D-CT scans. The CNN model with a learning rate schedule and an exponential decay and slice flipping techniques was deployed on the processed slices. The proposed method was used to make predictions on the 2D slices and for final diagnosis at patient level, majority voting was applied on the slices of each CT scan to take the diagnosis. The macro F1 score of the proposed method well-exceeded the baseline approach and other alternatives on the validation set as well as on a test partition of previously unseen images from COV-19CT-DB dataset.
MRI를 이용한 뇌종양 자동 분류(classification)는 의료 영상 분야에서 심층 학습(deep learning)이 활발히 적용되는 연구 주제로, 공개 벤치마크에서 보고되는 정확도는 일상적으로 98%를 웃돕니다. 그러나 정확도는 벤치마크 품질의 중요한 차원인 데이터셋(dataset) 무결성, 즉 영상, 환자, 획득 출처 수준에서 테스트 데이터가 학습(training) 데이터로부터 독립적인지 여부를 포착하지 못합니다. 본 연구에서는 관련 문헌의 기반이 되는 공개 코퍼스를 평가하기 위해 중복, 환자, 출처-라벨 누출로 구성된 3개 층(layer) 오염 프레임워크를 도입합니다. 가장 널리 사용되는 3개 코퍼스를 흉부 X선 음성 대조군과 비교 감사하고, 9개 아키텍처와 3개 평가 조건에 걸쳐 각 층이 측정된 성능에 미치는 영향을 정량화합니다. 모든 층에서 오염이 심각한 수준이었습니다. 가장 지배적인 코퍼스의 공식 테스트 분할 중 28.8%는 자체 학습 분할 내에 유사 복제본이 존재했고, 두 번째 코퍼스는 테스트 영상의 22.3%가 바이트 단위로 동일하게 누출되었으며, 추적 가능한 테스트 영상의 95.5%가 학습 데이터와 동일한 환자를 공유했고, 해부학적 정보를 포함하지 않는 파일 헤더 특징만으로도 파인튜닝(fine-tuning)된 ResNet 백본과 동등한 수준인 0.959의 균형 정확도로 종양과 비종양을 구분했습니다. 예상치 못한 결과는 확인된 모든 누출 테스트 영상을 제거해도 균형 정확도가 실질적으로 변하지 않았다는 점입니다. 즉, 중복 제거 후에도 성능이 안정적으로 유지된다고 해서 벤치마크의 무결성이 입증되는 것은 아닙니다. 본 연구의 결과는 데이터셋 무결성이 안정적인 리더보드만으로는 보증할 수 없는 벤치마크 품질의 명확하고 측정 가능한 축임을 규명합니다. 생물의학 연구에서 이러한 코퍼스만을 바탕으로 보고된 정확도는 모델(model)이 데이터셋 특화 단서를 악용하는 대신 종양을 인식하도록 학습되었음을 증명하지 못합니다. 연구진은 오염된 파일 목록, 복구된 환자 식별자, 중복이 제거된 분할 데이터를 공개합니다.
대규모 데이터셋으로 사전학습된 파운데이션 모델은 의료 영상 과제로의 강력한 전이 가능성을 보여준다. 그러나 이들의 잠재 표현이 임상적으로 관련 있는 정보를 어떻게 인코딩하는지 이해하는 것은 안전이 중요한(safety-critical) 영역에서 여전히 미해결 과제로 남아 있다. 본 연구는 사전학습된 파운데이션 모델의 내부 레이어가 생성하는 패치 수준 특징을 어떠한 미세조정 없이 해석하는 프로토타입 기반 퍼지 규칙 프레임워크를 제안한다. 클래스별 프로토타입은 특징 공간에서의 군집화(clustering)를 통해 학습되며, 이를 통해 압축된 시각적 패턴을 얻는다. 이후 패치 특징은 프로토타입과의 유사도로 표현되고, 사람이 읽을 수 있는 언어적 IF-THEN 조건을 가진 퍼지 규칙에 의해 분류된다. 이 프레임워크는 ImageNet-1K와 GastroNet-5M으로 사전학습된 ViT-S/16 백본의 마지막 두 블록에 걸쳐 적용되며, 동일한 고정(frozen) 특징 조건에서 k-최근접 이웃(k-nearest neighbours), 커널 SVM, 선형 프로빙(linear probing)과 비교하여 무선 캡슐 내시경 분류, 위장관 내시경 분류, 대장 용종 분할(segmentation) 과제에서 벤치마크된다. 실험 분석 결과, 제안된 방법은 백본 미세조정 없이도 이러한 블랙박스 분류기들과 비슷한 정확도에 도달하며, 도메인 특화 사전학습이 판별력이 있으면서도 기호적으로 압축 가능한 특징을 산출함을 보여준다. 도출된 규칙은 실제 데이터로부터 추출되어 해석 가능한 용어로 표현되기 때문에, 합성 의료 영상을 조사하는 도구로도 추가로 활용되어, 생성 모델이 어떤 실제 프로토타입과 규칙을 재현하거나 재현하지 못하는지를 사람이 읽을 수 있는 방식으로 설명하며, 단일 점수로 요약하는 대신 합성 영상이 실제 조직과 어디에서 달라지는지를 국소적으로 파악할 수 있게 한다. 따라서 이 프레임워크는 파운데이션 모델이 임상적으로 관련 있는 구조를 어떻게 조직화하는지에 대한 투명하고 깊이 수준에서 해석 가능한(depth-resolved) 시각을 제공하며, 추출된 규칙의 실용적인 후속 활용 방안도 함께 제시한다.
Following the recent progress in image classification and captioning using deep learning, we develop a novel natural language person retrieval system based on an attention mechanism. More specifically, given the description of a person, the goal is to localize the person in an image. To this end, we first construct a benchmark dataset for natural language person retrieval. To do so, we generate bounding boxes for persons in a public image dataset from the segmentation masks, which are then annotated with descriptions and attributes using the Amazon Mechanical Turk. We then adopt a region proposal network in Faster R-CNN as a candidate region generator. The cropped images based on the region proposals as well as the whole images with attention weights are fed into Convolutional Neural Networks for visual feature extraction, while the natural language expression and attributes are input to Bidirectional Long Short- Term Memory (BLSTM) models for text feature extraction. The visual and text features are integrated to score region proposals, and the one with the highest score is retrieved as the output of our system. The experimental results show significant improvement over the state-of-the-art method for generic object retrieval and this line of research promises to benefit search in surveillance video footage.
Humans are able to precisely communicate diverse concepts by employing sketches, a highly reduced and abstract shape based representation of visual content. We propose, for the first time, a fully convolutional end-to-end architecture that is able to synthesize human-like sketches of objects in natural images with potentially cluttered background. To enable an architecture to learn this highly abstract mapping, we employ the following key components: (1) a fully convolutional encoder-decoder structure, (2) a perceptual similarity loss function operating in an abstract feature space and (3) conditioning of the decoder on the label of the object that shall be sketched. Given the combination of these architectural concepts, we can train our structure in an end-to-end supervised fashion on a collection of sketch-image pairs. The generated sketches of our architecture can be classified with 85.6% Top-5 accuracy and we verify their visual quality via a user study. We find that deep features as a perceptual similarity metric enable image translation with large domain gaps and our findings further show that convolutional neural networks trained on image classification tasks implicitly learn to encode shape information. Code is available under https://github.com/kampelmuehler/synthesizing_human_like_sketches
Tracking monocular colonoscope in the Gastrointestinal tract (GI) is a challenging problem as the images suffer from deformation, blurred textures, significant changes in appearance. They greatly restrict the tracking ability of conventional geometry based methods. Even though Deep Learning (DL) can overcome these issues, limited labeling data is a roadblock to state-of-art DL method. Considering these, we propose a novel approach to combine DL method with traditional feature based approach to achieve better localization with small training data. Our method fully exploits the best of both worlds by introducing a Siamese network structure to perform few-shot classification to the closest zone in the segmented training image set. The classified label is further adopted to initialize the pose of scope. To fully use the training dataset, a pre-generated triangulated map points within the zone in the training set are registered with observation and contribute to estimating the optimal pose of the test image. The proposed hybrid method is extensively tested and compared with existing methods, and the result shows significant improvement over traditional geometric based or DL based localization. The accuracy is improved by 28.94% (Position) and 10.97% (Orientation) with respect to state-of-art method.
Developing secure machine learning models from adversarial examples is challenging as various methods are continually being developed to generate adversarial attacks. In this work, we propose an evolutionary approach to automatically determine Image Processing Techniques Sequence (IPTS) for detecting malicious inputs. Accordingly, we first used a diverse set of attack methods including adaptive attack methods (on our defense) to generate adversarial samples from the clean dataset. A detection framework based on a genetic algorithm (GA) is developed to find the optimal IPTS, where the optimality is estimated by different fitness measures such as Euclidean distance, entropy loss, average histogram, local binary pattern and loss functions. The "image difference" between the original and processed images is used to extract the features, which are then fed to a classification scheme in order to determine whether the input sample is adversarial or clean. This paper described our methodology and performed experiments using multiple data-sets tested with several adversarial attacks. For each attack-type and dataset, it generates unique IPTS. A set of IPTS selected dynamically in testing time which works as a filter for the adversarial attack. Our empirical experiments exhibited promising results indicating the approach can efficiently be used as processing for any AI model.
There is very little notable research on generating descriptions of the Bengali language. About 243 million people speak in Bengali, and it is the 7th most spoken language on the planet. The purpose of this research is to propose a CNN and Bidirectional GRU based architecture model that generates natural language captions in the Bengali language from an image. Bengali people can use this research to break the language barrier and better understand each other's perspectives. It will also help many blind people with their everyday lives. This paper used an encoder-decoder approach to generate captions. We used a pre-trained Deep convolutional neural network (DCNN) called InceptonV3image embedding model as the encoder for analysis, classification, and annotation of the dataset's images Bidirectional Gated Recurrent unit (BGRU) layer as the decoder to generate captions. Argmax and Beam search is used to produce the highest possible quality of the captions. A new dataset called BNATURE is used, which comprises 8000 images with five captions per image. It is used for training and testing the proposed model. We obtained BLEU-1, BLEU-2, BLEU-3, BLEU-4 and Meteor is 42.6, 27.95, 23, 66, 16.41, 28.7 respectively.
Recently, a common starting point for solving complex unsupervised image classification tasks is to use generic features, extracted with deep Convolutional Neural Networks (CNN) pretrained on a large and versatile dataset (ImageNet). However, in most research, the CNN architecture for feature extraction is chosen arbitrarily, without justification. This paper aims at providing insight on the use of pretrained CNN features for image clustering (IC). First, extensive experiments are conducted and show that, for a given dataset, the choice of the CNN architecture for feature extraction has a huge impact on the final clustering. These experiments also demonstrate that proper extractor selection for a given IC task is difficult. To solve this issue, we propose to rephrase the IC problem as a multi-view clustering (MVC) problem that considers features extracted from different architectures as different "views" of the same data. This approach is based on the assumption that information contained in the different CNN may be complementary, even when pretrained on the same data. We then propose a multi-input neural network architecture that is trained end-to-end to solve the MVC problem effectively. This approach is tested on nine natural image datasets, and produces state-of-the-art results for IC.
Automated scoring of free drawings or images as responses has yet to be utilized in large-scale assessments of student achievement. In this study, we propose artificial neural networks to classify these types of graphical responses from a computer based international mathematics and science assessment. We are comparing classification accuracy of convolutional and feedforward approaches. Our results show that convolutional neural networks (CNNs) outperform feedforward neural networks in both loss and accuracy. The CNN models classified up to 97.71% of the image responses into the appropriate scoring category, which is comparable to, if not more accurate, than typical human raters. These findings were further strengthened by the observation that the most accurate CNN models correctly classified some image responses that had been incorrectly scored by the human raters. As an additional innovation, we outline a method to select human rated responses for the training sample based on an application of the expected response function derived from item response theory. This paper argues that CNN-based automated scoring of image responses is a highly accurate procedure that could potentially replace the workload and cost of second human raters for large scale assessments, while improving the validity and comparability of scoring complex constructed-response items.
Artificial intelligence is poised to augment dermatological care by enabling scalable image-based diagnostics. Yet, the development of robust and equitable models remains hindered by datasets that fail to capture the clinical and demographic complexity of real-world practice. This complexity stems from region-specific disease distributions, wide variation in skin tones, and the underrepresentation of outpatient scenarios from non-Western populations. We introduce DermaCon-IN, a prospectively curated dermatology dataset comprising over 5,450 clinical images from approximately 3,000 patients across outpatient clinics in South India. Each image is annotated by board-certified dermatologists with over 240 distinct diagnoses, structured under a hierarchical, etiology-based taxonomy adapted from Rook's classification. The dataset captures a wide spectrum of dermatologic conditions and tonal variation commonly seen in Indian outpatient care. We benchmark a range of architectures including convolutional models (ResNet, DenseNet, EfficientNet), transformer-based models (ViT, MaxViT, Swin), and Concept Bottleneck Models to establish baseline performance and explore how anatomical and concept-level cues may be integrated. These results are intended to guide future efforts toward interpretable and clinically realistic models. DermaCon-IN provides a scalable and representative foundation for advancing dermatology AI in real-world settings.
Driven by the urgent demand for managing remote sensing big data, large-scale remote sensing image retrieval (RSIR) attracts increasing attention in the remote sensing field. In general, existing retrieval methods can be regarded as visual-based retrieval approaches which search and return a set of similar images from a database to a given query image. Although retrieval methods have achieved great success, there is still a question that needs to be responded to: Can we obtain the accurate semantic labels of the returned similar images to further help analyzing and processing imagery? Inspired by the above question, in this paper, we redefine the image retrieval problem as visual and semantic retrieval of images. Specifically, we propose a novel deep hashing convolutional neural network (DHCNN) to simultaneously retrieve the similar images and classify their semantic labels in a unified framework. In more detail, a convolutional neural network (CNN) is used to extract high-dimensional deep features. Then, a hash layer is perfectly inserted into the network to transfer the deep features into compact hash codes. In addition, a fully connected layer with a softmax function is performed on hash layer to generate class distribution. Finally, a loss function is elaborately designed to simultaneously consider the label loss of each image and similarity loss of pairs of images. Experimental results on two remote sensing datasets demonstrate that the proposed method achieves the state-of-art retrieval and classification performance.
Transformers have proven superior performance for a wide variety of tasks since they were introduced. In recent years, they have drawn attention from the vision community in tasks such as image classification and object detection. Despite this wave, an accurate and efficient multiple-object tracking (MOT) method based on transformers is yet to be designed. We argue that the direct application of a transformer architecture with quadratic complexity and insufficient noise-initialized sparse queries - is not optimal for MOT. We propose TransCenter, a transformer-based MOT architecture with dense representations for accurately tracking all the objects while keeping a reasonable runtime. Methodologically, we propose the use of image-related dense detection queries and efficient sparse tracking queries produced by our carefully designed query learning networks (QLN). On one hand, the dense image-related detection queries allow us to infer targets' locations globally and robustly through dense heatmap outputs. On the other hand, the set of sparse tracking queries efficiently interacts with image features in our TransCenter Decoder to associate object positions through time. As a result, TransCenter exhibits remarkable performance improvements and outperforms by a large margin the current state-of-the-art methods in two standard MOT benchmarks with two tracking settings (public/private). TransCenter is also proven efficient and accurate by an extensive ablation study and comparisons to more naive alternatives and concurrent works. For scientific interest, the code is made publicly available at https://github.com/yihongxu/transcenter.
Slide presentations are an effective and efficient tool used by the teaching community for classroom communication. However, this teaching model can be challenging for blind and visually impaired (VI) students. The VI student required personal human assistance for understand the presented slide. This shortcoming motivates us to design a Classroom Slide Narration System (CSNS) that generates audio descriptions corresponding to the slide content. This problem poses as an image-to-markup language generation task. The initial step is to extract logical regions such as title, text, equation, figure, and table from the slide image. In the classroom slide images, the logical regions are distributed based on the location of the image. To utilize the location of the logical regions for slide image segmentation, we propose the architecture, Classroom Slide Segmentation Network (CSSN). The unique attributes of this architecture differs from most other semantic segmentation networks. Publicly available benchmark datasets such as WiSe and SPaSe are used to validate the performance of our segmentation architecture. We obtained 9.54 segmentation accuracy improvement in WiSe dataset. We extract content (information) from the slide using four well-established modules such as optical character recognition (OCR), figure classification, equation description, and table structure recognizer. With this information, we build a Classroom Slide Narration System (CSNS) to help VI students understand the slide content. The users have given better feedback on the quality output of the proposed CSNS in comparison to existing systems like Facebooks Automatic Alt-Text (AAT) and Tesseract.
Background: Radiography (X-rays) is the dominant modality in orthopedics, and improving the interpretation of radiographs is clinically relevant. Machine learning (ML) has revolutionized data analysis and has been applied to medicine, with some success, in the form of natural language processing (NLP) and artificial neural networks (ANN). Latent Dirichlet allocation (LDA) is an NLP method that automatically categorizes documents into topics. Successfully applying ML to orthopedic radiography could enable the creation of computer-aided decision systems for use in the clinic. We studied how an automated ML pipeline could classify orthopedic trauma radiographs from radiologist reports. Methods: Wrist and ankle radiographs from Danderyd Hospital in Sweden taken between 2002 and 2015, with radiologist reports. LDA was used to create image labels for radiographs from the radiologist reports. Radiographs and labels were used to train an image recognition ANN. The ANN outcomes were manually reviewed to get an accurate estimate of the method's utility and accuracy. Results: Image Labels generated via LDA could successfully train the ANN. The ANN reached an accuracy between 91% and 60% compared to a gold standard, depending on the label. Conclusions: We found that LDA was unsuited to label orthopedic radiographs from reports with high accuracy. However, despite this, the ANN could learn to detect some features in radiographs with high accuracy. The study also illustrates how ML and ANN can be applied to medical research.
Few-shot classification (FSC) is one of the most concerned hot issues in recent years. The general setting consists of two phases: (1) Pre-train a feature extraction model (FEM) with base data (has large amounts of labeled samples). (2) Use the FEM to extract the features of novel data (with few labeled samples and totally different categories from base data), then classify them with the to-be-designed classifier. The adaptability of pre-trained FEM to novel data determines the accuracy of novel features, thereby affecting the final classification performances. To this end, how to appraise the pre-trained FEM is the most crucial focus in the FSC community. It sounds like traditional Class Activate Mapping (CAM) based methods can achieve this by overlaying weighted feature maps. However, due to the particularity of FSC (e.g., there is no backpropagation when using the pre-trained FEM to extract novel features), we cannot activate the feature map with the novel classes. To address this challenge, we propose a simple, flexible method, dubbed as Class-Irrelevant Mapping (CIM). Specifically, first, we introduce dictionary learning theory and view the channels of the feature map as the bases in a dictionary. Then we utilize the feature map to fit the feature vector of an image to achieve the corresponding channel weights. Finally, we overlap the weighted feature map for visualization to appraise the ability of pre-trained FEM on novel data. For fair use of CIM in evaluating different models, we propose a new measurement index, called Feature Localization Accuracy (FLA). In experiments, we first compare our CIM with CAM in regular tasks and achieve outstanding performances. Next, we use our CIM to appraise several classical FSC frameworks without considering the classification results and discuss them.
Recognizing arbitrary objects in the wild has been a challenging problem due to the limitations of existing classification models and datasets. In this paper, we propose a new task that aims at parsing scenes with a large and open vocabulary, and several evaluation metrics are explored for this problem. Our proposed approach to this problem is a joint image pixel and word concept embeddings framework, where word concepts are connected by semantic relations. We validate the open vocabulary prediction ability of our framework on ADE20K dataset which covers a wide variety of scenes and objects. We further explore the trained joint embedding space to show its interpretability.
We present a new probabilistic model of compact commutative Lie groups that produces invariant-equivariant and disentangled representations of data. To define the notion of disentangling, we borrow a fundamental principle from physics that is used to derive the elementary particles of a system from its symmetries. Our model employs a newfound Bayesian conjugacy relation that enables fully tractable probabilistic inference over compact commutative Lie groups -- a class that includes the groups that describe the rotation and cyclic translation of images. We train the model on pairs of transformed image patches, and show that the learned invariant representation is highly effective for classification.