We propose an application-tailored data-driven fully automated method for functional approximation of combinational circuits. We demonstrate how an application-level error metric such as the classification accuracy can be translated to a component-level error metric needed for an efficient and fast search in the space of approximate low-level components that are used in the application. This is possible by employing a weighted mean error distance (WMED) metric for steering the circuit approximation process which is conducted by means of genetic programming. WMED introduces a set of weights (calculated from the data distribution measured on a selected signal in a given application) determining the importance of each input vector for the approximation process. The method is evaluated using synthetic benchmarks and application-specific approximate MAC (multiply-and-accumulate) units that are designed to provide the best trade-offs between the classification accuracy and power consumption of two image classifiers based on neural networks.
We propose Predict then Interpolate (PI), a simple algorithm for learning correlations that are stable across environments. The algorithm follows from the intuition that when using a classifier trained on one environment to make predictions on examples from another environment, its mistakes are informative as to which correlations are unstable. In this work, we prove that by interpolating the distributions of the correct predictions and the wrong predictions, we can uncover an oracle distribution where the unstable correlation vanishes. Since the oracle interpolation coefficients are not accessible, we use group distributionally robust optimization to minimize the worst-case risk across all such interpolations. We evaluate our method on both text classification and image classification. Empirical results demonstrate that our algorithm is able to learn robust classifiers (outperforms IRM by 23.85% on synthetic environments and 12.41% on natural environments). Our code and data are available at https://github.com/YujiaBao/Predict-then-Interpolate.
There has been an extensive use of Unmanned Aerial Vehicles in search and rescue missions to distribute first aid kits and food packets. It is important that these UAVs are able to identify and distinguish the markers from one another for effective distribution. One of the common ways to mark the locations is via the use of characters superimposed on shapes of various colors which gives rise to wide variety of markers based on combination of different shapes, characters, and their respective colors. In this paper, we propose an object detection and classification pipeline which prevents false positives and minimizes misclassification of alphanumeric characters and shapes in aerial images. Our method makes use of traditional computer vision techniques and unsupervised machine learning methods for identifying region proposals, segmenting the image targets and removing false positives. We make use of a computationally light model for classification, making it easy to be deployed on any aerial vehicle.
Customer feedback can be an important signal for improving commercial machine translation systems. One solution for fixing specific translation errors is to remove the related erroneous training instances followed by re-training of the machine translation system, which we refer to as instance-specific data filtering. Influence functions (IF) have been shown to be effective in finding such relevant training examples for classification tasks such as image classification, toxic speech detection and entailment task. Given a probing instance, IF find influential training examples by measuring the similarity of the probing instance with a set of training examples in gradient space. In this work, we examine the use of influence functions for Neural Machine Translation (NMT). We propose two effective extensions to a state of the art influence function and demonstrate on the sub-problem of copied training examples that IF can be applied more generally than handcrafted regular expressions.
The COVID-19 pandemic presented numerous challenges to healthcare systems worldwide. Given that lung infections are prevalent among COVID-19 patients, chest Computer Tomography (CT) scans have frequently been utilized as an alternative method for identifying COVID-19 conditions and various other types of pulmonary diseases. Deep learning architectures have emerged to automate the identification of pulmonary disease types by leveraging CT scan slices as inputs for classification models. This paper introduces COVID-VR, a novel approach for classifying pulmonary diseases based on volume rendering images of the lungs captured from multiple angles, thereby providing a comprehensive view of the entire lung in each image. To assess the effectiveness of our proposal, we compared it against competing strategies utilizing both private data obtained from partner hospitals and a publicly available dataset. The results demonstrate that our approach effectively identifies pulmonary lesions and performs competitively when compared to slice-based methods.
Labeling errors in datasets are common, if not systematic, in practice. They naturally arise in a variety of contexts-human labeling, noisy labeling, and weak labeling (i.e., image classification), for example. This presents a persistent and pervasive stress on machine learning practice. In particular, neural network (NN) architectures can withstand minor amounts of dataset imperfection with traditional countermeasures such as regularization, data augmentation, and batch normalization. However, major dataset imperfections often prove insurmountable. We propose and study the implementation of Rockafellian Relaxation (RR), a new loss reweighting, architecture-independent methodology, for neural network training. Experiments indicate RR can enhance standard neural network methods to achieve robust performance across classification tasks in computer vision and natural language processing (sentiment analysis). We find that RR can mitigate the effects of dataset corruption due to both (heavy) labeling error and/or adversarial perturbation, demonstrating effectiveness across a variety of data domains and machine learning tasks.
학습 데이터 기여도(TDA) 방법은 개별 학습 샘플이 모델의 예측에 미치는 영향을 추정하여 신경망을 해석하기 위한 원칙적인 관점을 제공한다. 방법론이 빠르게 발전했음에도 불구하고 TDA 평가는 여러 논문에 흩어져 있고 재현이 거의 이루어지지 않아 방법 간 공정한 비교가 어렵다. 우리는 TDA 평가를 표준화하는 Python 툴킷인 quanda를 소개한다. quanda는 이미지 분류, 텍스트 분류, 언어 모델링을 아우르는 포괄적인 평가 지표 모음과 바로 사용할 수 있는 벤치마크, 그리고 다양한 TDA 구현을 통합하기 위한 균일한 인터페이스를 제공한다. 기존 TDA 방법에 대한 비교 연구를 통해 quanda를 시연하며, 모든 지표에서 일관되게 우수한 접근법은 없고 실제 정답에 대한 충실도와 하위 과제 성능 사이에 뚜렷한 상충 관계가 있음을 확인한다. quanda는 TDA 관련 도구를 통합함으로써 커뮤니티가 기여도 방법을 엄밀하고 재현 가능하게 평가할 수 있도록 한다. 이 툴킷은 철저히 테스트되고 문서화되어 있으며 PyPI와 https://github.com/dilyabareeva/quanda 에서 오픈소스 라이브러리로 제공된다.
We present TaxaBind, a unified embedding space for characterizing any species of interest. TaxaBind is a multimodal embedding space across six modalities: ground-level images of species, geographic location, satellite image, text, audio, and environmental features, useful for solving ecological problems. To learn this joint embedding space, we leverage ground-level images of species as a binding modality. We propose multimodal patching, a technique for effectively distilling the knowledge from various modalities into the binding modality. We construct two large datasets for pretraining: iSatNat with species images and satellite images, and iSoundNat with species images and audio. Additionally, we introduce TaxaBench-8k, a diverse multimodal dataset with six paired modalities for evaluating deep learning models on ecological tasks. Experiments with TaxaBind demonstrate its strong zero-shot and emergent capabilities on a range of tasks including species classification, cross-model retrieval, and audio classification. The datasets and models are made available at https://github.com/mvrl/TaxaBind.
The process of digitising histology slides involves multiple factors that can affect a whole slide image's (WSI) final appearance, including the staining protocol, scanner, and tissue type. This variability constitutes a domain shift and results in significant problems when training and testing deep learning (DL) algorithms in multi-cohort settings. As such, developing robust and generalisable DL models in computational pathology (CPath) remains an open challenge. In this regard, we propose a framework that generates stain-augmented versions of the training images using stain matrix perturbation. Thereafter, we employed a stain regularisation loss to enforce consistency between the feature representations of the source and augmented images. Doing so encourages the model to learn stain-invariant and, consequently, domain-invariant feature representations. We evaluate the performance of the proposed model on cross-domain multi-class tissue type classification of colorectal cancer images and have achieved improved performance compared to other state-of-the-art methods.
이진 신경망(BNN)은 가중치와 활성화 함수를 1비트로 압축하여 모델 크기와 추론(inference) 비용을 대폭 줄임으로써 자원 제약이 있는 기기에서 효율적인 심층 학습(deep learning) 배포를 가능하게 합니다. 이벤트 카메라는 조밀한 이미지 프레임 대신 비동기 이벤트 스트림을 캡처하여 짧은 지연 시간, 높은 동적 범위(HDR), 저전력 소비 등 상호보완적인 이점을 제공합니다. 두 기술 모두 효율성을 강조함에도 불구하고, 이들을 결합하는 연구는 여전히 거의 탐구되지 않은 상태입니다. 본 연구는 최신 심층 BNN 아키텍처를 이벤트 데이터에 맞게 적응시키고 평가하는 것을 목표로 합니다. 또한 RGB 데이터로부터의 교차 모달 사전학습(cross-modal pretraining)이 뉴로모픽 데이터셋에서 BNN의 분류(classification) 정확도를 향상시킬 수 있음을 보입니다. 우리는 이벤트 카메라 데이터를 BNN에서 직접 처리할 수 있게 하며 완전 이진화된 이벤트 기반 비전 시스템을 향한 발걸음을 나타내는 이진 표현인 극성별 이진 이벤트 볼륨(PBEV)을 소개합니다. N-Caltech101 분류 벤치마크에서 평가된 최고 성능의 BNN은 전정밀도(full-precision) 모델 대비 7.5배 적은 연산량으로 90.58%의 정확도를 달성했습니다.
The detection of emotions using an Electroencephalogram (EEG) is a crucial area in brain-computer interfaces and has valuable applications in fields such as rehabilitation and medicine. In this study, we employed transfer learning to overcome the challenge of limited data availability in EEG-based emotion detection. The base model used in this study was Resnet50. Additionally, we employed a novel feature combination in EEG-based emotion detection. The input to the model was in the form of an image matrix, which comprised Mean Phase Coherence (MPC) and Magnitude Squared Coherence (MSC) in the upper-triangular and lower-triangular matrices, respectively. We further improved the technique by incorporating features obtained from the Differential Entropy (DE) into the diagonal, which previously held little to no useful information for classifying emotions. The dataset used in this study, SEED EEG (62 channel EEG), comprises three classes (Positive, Neutral, and Negative). We calculated both subject-independent and subject-dependent accuracy. The subject-dependent accuracy was obtained using a 10-fold cross-validation method and was 93.1%, while the subject-independent classification was performed by employing the leave-one-subject-out (LOSO) strategy. The accuracy obtained in subject-independent classification was 71.6%. Both of these accuracies are at least twice better than the chance accuracy of classifying 3 classes. The study found the use of MSC and MPC in EEG-based emotion detection promising for emotion classification. The future scope of this work includes the use of data augmentation techniques, enhanced classifiers, and better features for emotion classification.
Band selection refers to the process of choosing the most relevant bands in a hyperspectral image. By selecting a limited number of optimal bands, we aim at speeding up model training, improving accuracy, or both. It reduces redundancy among spectral bands while trying to preserve the original information of the image. By now many efforts have been made to develop unsupervised band selection approaches, of which the majority are heuristic algorithms devised by trial and error. In this paper, we are interested in training an intelligent agent that, given a hyperspectral image, is capable of automatically learning policy to select an optimal band subset without any hand-engineered reasoning. To this end, we frame the problem of unsupervised band selection as a Markov decision process, propose an effective method to parameterize it, and finally solve the problem by deep reinforcement learning. Once the agent is trained, it learns a band-selection policy that guides the agent to sequentially select bands by fully exploiting the hyperspectral image and previously picked bands. Furthermore, we propose two different reward schemes for the environment simulation of deep reinforcement learning and compare them in experiments. This, to the best of our knowledge, is the first study that explores a deep reinforcement learning model for hyperspectral image analysis, thus opening a new door for future research and showcasing the great potential of deep reinforcement learning in remote sensing applications. Extensive experiments are carried out on four hyperspectral data sets, and experimental results demonstrate the effectiveness of the proposed method.
We consider a family of structural descriptors for visual data, namely covariance descriptors (CovDs) that lie on a non-linear symmetric positive definite (SPD) manifold, a special type of Riemannian manifolds. We propose an improved version of CovDs for image set coding by extending the traditional CovDs from Euclidean space to the SPD manifold. Specifically, the manifold of SPD matrices is a complete inner product space with the operations of logarithmic multiplication and scalar logarithmic multiplication defined in the Log-Euclidean framework. In this framework, we characterise covariance structure in terms of the arc-cosine kernel which satisfies Mercer's condition and propose the operation of mean centralization on SPD matrices. Furthermore, we combine arc-cosine kernels of different orders using mixing parameters learnt by kernel alignment in a supervised manner. Our proposed framework provides a lower-dimensional and more discriminative data representation for the task of image set classification. The experimental results demonstrate its superior performance, measured in terms of recognition accuracy, as compared with the state-of-the-art methods.
Smart cameras are increasingly used in surveillance solutions in public spaces. Contemporary computer vision applications can be used to recognize events that require intervention by emergency services. Smart cameras can be mounted in locations where citizens feel particularly unsafe, e.g., pathways and underpasses with a history of incidents. One promising approach for smart cameras is edge AI, i.e., deploying AI technology on IoT devices. However, implementing resource-demanding technology such as image recognition using deep neural networks (DNN) on constrained devices is a substantial challenge. In this paper, we explore two approaches to reduce the need for compute in contemporary image recognition in an underpass. First, we showcase successful neural network pruning, i.e., we retain comparable classification accuracy with only 1.1\% of the neurons remaining from the state-of-the-art DNN architecture. Second, we demonstrate how a CycleGAN can be used to transform out-of-distribution images to the operational design domain. We posit that both pruning and CycleGANs are promising enablers for efficient edge AI in smart cameras.
The generalization performance of deep learning models for medical image analysis often decreases on images collected with different devices for data acquisition, device settings, or patient population. A better understanding of the generalization capacity on new images is crucial for clinicians' trustworthiness in deep learning. Although significant research efforts have been recently directed toward establishing generalization bounds and complexity measures, still, there is often a significant discrepancy between the predicted and actual generalization performance. As well, related large empirical studies have been primarily based on validation with general-purpose image datasets. This paper presents an empirical study that investigates the correlation between 25 complexity measures and the generalization abilities of supervised deep learning classifiers for breast ultrasound images. The results indicate that PAC-Bayes flatness-based and path norm-based measures produce the most consistent explanation for the combination of models and data. We also investigate the use of multi-task classification and segmentation approach for breast images, and report that such learning approach acts as an implicit regularizer and is conducive toward improved generalization.
Cellular composition prediction, i.e., predicting the presence and counts of different types of cells in the tumor microenvironment from a digitized image of a Hematoxylin and Eosin (H&E) stained tissue section can be used for various tasks in computational pathology such as the analysis of cellular topology and interactions, subtype prediction, survival analysis, etc. In this work, we propose an image-based cellular composition predictor (ALBRT) which can accurately predict the presence and counts of different types of cells in a given image patch. ALBRT, by its contrastive-learning inspired design, learns a compact and rotation-invariant feature representation that is then used for cellular composition prediction of different cell types. It offers significant improvement over existing state-of-the-art approaches for cell classification and counting. The patch-level feature representation learned by ALBRT is transferrable for cellular composition analysis over novel datasets and can also be utilized for downstream prediction tasks in CPath as well. The code and the inference webserver for the proposed method are available at the URL: https://github.com/engrodawood/ALBRT.
Explaining artificial intelligence (AI) predictions is increasingly important and even imperative in many high-stakes applications where humans are the ultimate decision-makers. In this work, we propose two novel architectures of self-interpretable image classifiers that first explain, and then predict (as opposed to post-hoc explanations) by harnessing the visual correspondences between a query image and exemplars. Our models consistently improve (by 1 to 4 points) on out-of-distribution (OOD) datasets while performing marginally worse (by 1 to 2 points) on in-distribution tests than ResNet-50 and a $k$-nearest neighbor classifier (kNN). Via a large-scale, human study on ImageNet and CUB, our correspondence-based explanations are found to be more useful to users than kNN explanations. Our explanations help users more accurately reject AI's wrong decisions than all other tested methods. Interestingly, for the first time, we show that it is possible to achieve complementary human-AI team accuracy (i.e., that is higher than either AI-alone or human-alone), in ImageNet and CUB image classification tasks.
Multi-head-self-attention (MHSA)-equipped models have achieved notable performance in computer vision. Their computational complexity is proportional to quadratic numbers of pixels in input feature maps, resulting in slow processing, especially when dealing with high-resolution images. New types of token-mixer are proposed as an alternative to MHSA to circumvent this problem: an FFT-based token-mixer involves global operations similar to MHSA but with lower computational complexity. However, despite its attractive properties, the FFT-based token-mixer has not been carefully examined in terms of its compatibility with the rapidly evolving MetaFormer architecture. Here, we propose a novel token-mixer called Dynamic Filter and novel image recognition models, DFFormer and CDFFormer, to close the gaps above. The results of image classification and downstream tasks, analysis, and visualization show that our models are helpful. Notably, their throughput and memory efficiency when dealing with high-resolution image recognition is remarkable. Our results indicate that Dynamic Filter is one of the token-mixer options that should be seriously considered. The code is available at https://github.com/okojoalg/dfformer
Predicting masked from visible parts of an image is a powerful self-supervised approach for visual representation learning. However, the common practice of masking random patches of pixels exhibits certain failure modes, which can prevent learning meaningful high-level features, as required for downstream tasks. We propose an alternative masking strategy that operates on a suitable transformation of the data rather than on the raw pixels. Specifically, we perform principal component analysis and then randomly mask a subset of components, which accounts for a fixed ratio of the data variance. The learning task then amounts to reconstructing the masked components from the visible ones. Compared to local patches of pixels, the principal components of images carry more global information. We thus posit that predicting masked from visible components involves more high-level features, allowing our masking strategy to extract more useful representations. This is corroborated by our empirical findings which demonstrate improved image classification performance for component over pixel masking. Our method thus constitutes a simple and robust data-driven alternative to traditional masked image modeling approaches.
This paper considers security risks buried in the data processing pipeline in common deep learning applications. Deep learning models usually assume a fixed scale for their training and input data. To allow deep learning applications to handle a wide range of input data, popular frameworks, such as Caffe, TensorFlow, and Torch, all provide data scaling functions to resize input to the dimensions used by deep learning models. Image scaling algorithms are intended to preserve the visual features of an image after scaling. However, common image scaling algorithms are not designed to handle human crafted images. Attackers can make the scaling outputs look dramatically different from the corresponding input images. This paper presents a downscaling attack that targets the data scaling process in deep learning applications. By carefully crafting input data that mismatches with the dimension used by deep learning models, attackers can create deceiving effects. A deep learning application effectively consumes data that are not the same as those presented to users. The visual inconsistency enables practical evasion and data poisoning attacks to deep learning applications. This paper presents proof-of-concept attack samples to popular deep-learning-based image classification applications. To address the downscaling attacks, the paper also suggests multiple potential mitigation strategies.