Intuitively, one would expect accuracy of a trained neural network's prediction on test samples to correlate with how densely the samples are surrounded by seen training samples in representation space. We find that a bound on empirical training error smoothed across linear activation regions scales inversely with training sample density in representation space. Empirically, we verify this bound is a strong predictor of the inaccuracy of the network's prediction on test samples. For unseen test sets, including those with out-of-distribution samples, ranking test samples by their local region's error bound and discarding samples with the highest bounds raises prediction accuracy by up to 20% in absolute terms for image classification datasets, on average over thresholds.
We introduce a self-supervised vision representation model BEiT, which stands for Bidirectional Encoder representation from Image Transformers. Following BERT developed in the natural language processing area, we propose a masked image modeling task to pretrain vision Transformers. Specifically, each image has two views in our pre-training, i.e, image patches (such as 16x16 pixels), and visual tokens (i.e., discrete tokens). We first "tokenize" the original image into visual tokens. Then we randomly mask some image patches and fed them into the backbone Transformer. The pre-training objective is to recover the original visual tokens based on the corrupted image patches. After pre-training BEiT, we directly fine-tune the model parameters on downstream tasks by appending task layers upon the pretrained encoder. Experimental results on image classification and semantic segmentation show that our model achieves competitive results with previous pre-training methods. For example, base-size BEiT achieves 83.2% top-1 accuracy on ImageNet-1K, significantly outperforming from-scratch DeiT training (81.8%) with the same setup. Moreover, large-size BEiT obtains 86.3% only using ImageNet-1K, even outperforming ViT-L with supervised pre-training on ImageNet-22K (85.2%). The code and pretrained models are available at https://aka.ms/beit.
Meta-learning has emerged as an efficient approach for constructing target models based on support sets. For example, the meta-learned embeddings enable the construction of target nearest-neighbor classifiers for specific tasks by pulling instances closer to their same-class neighbors. However, a single instance can be annotated from various latent attributes, making visually similar instances inside or across support sets have different labels and diverse relationships with others. Consequently, a uniform meta-learned strategy for inferring the target model from the support set fails to capture the instance-wise ambiguous similarity. To this end, we propose Learning to Decompose Network (LeadNet) to contextualize the meta-learned ``support-to-target'' strategy, leveraging the context of instances with one or mixed latent attributes in a support set. In particular, the comparison relationship between instances is decomposed w.r.t. multiple embedding spaces. LeadNet learns to automatically select the strategy associated with the right attribute via incorporating the change of comparison across contexts} with polysemous embeddings. We demonstrate the superiority of LeadNet in various applications, including exploring multiple views of confusing data, out-of-distribution recognition, and few-shot image classification.
Plant species identification is time consuming, costly, and requires lots of efforts, and expertise knowledge. In recent, many researchers use deep learning methods to classify plants directly using plant images. While deep learning models have achieved a great success, the lack of interpretability limit their widespread application. To overcome this, we explore the use of interpretable, measurable and computer-aided features extracted from plant leaf images. Image processing is one of the most challenging, and crucial steps in feature-extraction. The purpose of image processing is to improve the leaf image by removing undesired distortion. The main image processing steps of our algorithm involves: i) Convert original image to RGB (Red-Green-Blue) image, ii) Gray scaling, iii) Gaussian smoothing, iv) Binary thresholding, v) Remove stalk, vi) Closing holes, and vii) Resize image. The next step after image processing is to extract features from plant leaf images. We introduced 52 computationally efficient features to classify plant species. These features are mainly classified into four groups as: i) shape-based features, ii) color-based features, iii) texture-based features, and iv) scagnostic features. Length, width, area, texture correlation, monotonicity and scagnostics are to name few of them. We explore the ability of features to discriminate the classes of interest under supervised learning and unsupervised learning settings. For that, supervised dimensionality reduction technique, Linear Discriminant Analysis (LDA), and unsupervised dimensionality reduction technique, Principal Component Analysis (PCA) are used to convert and visualize the images from digital-image space to feature space. The results show that the features are sufficient to discriminate the classes of interest under both supervised and unsupervised learning settings.
At present, the Synthetic Aperture Radar (SAR) image classification method based on convolution neural network (CNN) has faced some problems such as poor noise resistance and generalization ability. Spiking neural network (SNN) is one of the core components of brain-like intelligence and has good application prospects. This article constructs a complete SAR image classifier based on unsupervised and supervised learning of SNN by using spike sequences with complex spatio-temporal information. We firstly expound the spiking neuron model, the receptive field of SNN, and the construction of spike sequence. Then we put forward an unsupervised learning algorithm based on STDP and a supervised learning algorithm based on gradient descent. The average classification accuracy of single layer and bilayer unsupervised learning SNN in three categories images on MSTAR dataset is 80.8\% and 85.1\%, respectively. Furthermore, the convergent output spike sequences of unsupervised learning can be used as teaching signals. Based on the TensorFlow framework, a single layer supervised learning SNN is built from the bottom, and the classification accuracy reaches 90.05\%. By comparing noise resistance and model parameters between SNNs and CNNs, the effectiveness and outstanding advantages of SNN are verified. Code to reproduce our experiments is available at \url{https://github.com/Jiankun-chen/Supervised-SNN-with-GD}.
Accurate estimation of predictive uncertainty (model calibration) is essential for the safe application of neural networks. Many instances of miscalibration in modern neural networks have been reported, suggesting a trend that newer, more accurate models produce poorly calibrated predictions. Here, we revisit this question for recent state-of-the-art image classification models. We systematically relate model calibration and accuracy, and find that the most recent models, notably those not using convolutions, are among the best calibrated. Trends observed in prior model generations, such as decay of calibration with distribution shift or model size, are less pronounced in recent architectures. We also show that model size and amount of pretraining do not fully explain these differences, suggesting that architecture is a major determinant of calibration properties.
Defect detection and classification technology has changed from traditional artificial visual inspection to current intelligent automated inspection, but most of the current defect detection methods are training related detection models based on a data-driven approach, taking into account the difficulty of collecting some sample data in the industrial field. We apply zero-shot learning technology to the industrial field. Aiming at the problem of the existing "Latent Feature Guide Attribute Attention" (LFGAA) zero-shot image classification network, the output latent attributes and artificially defined attributes are different in the semantic space, which leads to the problem of model performance degradation, proposed an LGFAA network based on semantic feedback, and improved model performance by constructing semantic embedded modules and feedback mechanisms. At the same time, for the common domain shift problem in zero-shot learning, based on the idea of co-training algorithm using the difference information between different views of data to learn from each other, we propose an Ensemble Co-training algorithm, which adaptively reduces the prediction error in image tag embedding from multiple angles. Various experiments conducted on the zero-shot dataset and the cylinder liner dataset in the industrial field provide competitive results.
In this paper, we propose a transfer-learning based model construction technique for the aerial scene classification problem. The core of our technique is a layer selection strategy, named ReLU-Based Feature Fusion (RBFF), that extracts feature maps from a pretrained CNN-based single-object image classification model, namely MobileNetV2, and constructs a model for the aerial scene classification task. RBFF stacks features extracted from the batch normalization layer of a few selected blocks of MobileNetV2, where the candidate blocks are selected based on the characteristics of the ReLU activation layers present in those blocks. The feature vector is then compressed into a low-dimensional feature space using dimension reduction algorithms on which we train a low-cost SVM classifier for the classification of the aerial images. We validate our choice of selected features based on the significance of the extracted features with respect to our classification pipeline. RBFF remarkably does not involve any training of the base CNN model except for a few parameters for the classifier, which makes the technique very cost-effective for practical deployments. The constructed model despite being lightweight outperforms several recently proposed models in terms of accuracy for a number of aerial scene datasets.
Advancements in ultra-low-power tiny machine learning (TinyML) systems promise to unlock an entirely new class of smart applications. However, continued progress is limited by the lack of a widely accepted and easily reproducible benchmark for these systems. To meet this need, we present MLPerf Tiny, the first industry-standard benchmark suite for ultra-low-power tiny machine learning systems. The benchmark suite is the collaborative effort of more than 50 organizations from industry and academia and reflects the needs of the community. MLPerf Tiny measures the accuracy, latency, and energy of machine learning inference to properly evaluate the tradeoffs between systems. Additionally, MLPerf Tiny implements a modular design that enables benchmark submitters to show the benefits of their product, regardless of where it falls on the ML deployment stack, in a fair and reproducible manner. The suite features four benchmarks: keyword spotting, visual wake words, image classification, and anomaly detection.
When data is publicly released for human consumption, it is unclear how to prevent its unauthorized usage for machine learning purposes. Successful model training may be preventable with carefully designed dataset modifications, and we present a proof-of-concept approach for the image classification setting. We propose methods based on the notion of adversarial shortcuts, which encourage models to rely on non-robust signals rather than semantic features, and our experiments demonstrate that these measures successfully prevent deep learning models from achieving high accuracy on real, unmodified data examples.
High-resolution representations (HR) are essential for dense prediction tasks such as segmentation, detection, and pose estimation. Learning HR representations is typically ignored in previous Neural Architecture Search (NAS) methods that focus on image classification. This work proposes a novel NAS method, called HR-NAS, which is able to find efficient and accurate networks for different tasks, by effectively encoding multiscale contextual information while maintaining high-resolution representations. In HR-NAS, we renovate the NAS search space as well as its searching strategy. To better encode multiscale image contexts in the search space of HR-NAS, we first carefully design a lightweight transformer, whose computational complexity can be dynamically changed with respect to different objective functions and computation budgets. To maintain high-resolution representations of the learned networks, HR-NAS adopts a multi-branch architecture that provides convolutional encoding of multiple feature resolutions, inspired by HRNet. Last, we proposed an efficient fine-grained search strategy to train HR-NAS, which effectively explores the search space, and finds optimal architectures given various tasks and computation resources. HR-NAS is capable of achieving state-of-the-art trade-offs between performance and FLOPs for three dense prediction tasks and an image classification task, given only small computational budgets. For example, HR-NAS surpasses SqueezeNAS that is specially designed for semantic segmentation while improving efficiency by 45.9%. Code is available at https://github.com/dingmyu/HR-NAS
Image classification is an important task in various machine learning applications. In recent years, a number of classification methods based on quantum machine learning and different quantum image encoding techniques have been proposed. In this paper, we study the effect of three different quantum image encoding approaches on the performance of a convolution-inspired hybrid quantum-classical image classification algorithm called quanvolutional neural network (QNN). We furthermore examine the effect of variational - i.e. trainable - quantum circuits on the classification results. Our experiments indicate that some image encodings are better suited for variational circuits. However, our experiments show as well that there is not one best image encoding, but that the choice of the encoding depends on the specific constraints of the application.
Neural networks are prone to overfitting and memorizing data patterns. To avoid over-fitting and enhance their generalization and performance, various methods have been suggested in the literature, including dropout, regularization, label smoothing, etc. One such method is augmentation which introduces different types of corruption in the data to prevent the model from overfitting and to memorize patterns present in the data. A sub-area of data augmentation is image mixing and deleting. This specific type of augmentation either deletes image regions or mixes two images to hide or make particular characteristics of images confusing for the network, forcing it to emphasize the overall structure of the object in an image. Models trained with this approach have proven to perform and generalize well compared to those trained without image mixing or deleting. An added benefit that comes with this method of training is robustness against image corruption. Due to its low computational cost and recent success, researchers have proposed many image mixing and deleting techniques. We furnish an in-depth survey of image mixing and deleting techniques and provide categorization via their most distinguishing features. We initiate our discussion with some fundamental relevant concepts. Next, we present essentials, such as each category's strengths and limitations, describing their working mechanism, basic formulations, and applications. We also discuss the general challenges and recommend possible future research directions for image mixing and deleting data augmentation techniques. Datasets and codes for evaluation are publicly available here.
Metric-based few-shot fine-grained image classification (FSFGIC) aims to learn a transferable feature embedding network by estimating the similarities between query images and support classes from very few examples. In this work, we propose, for the first time, to introduce the non-linear data projection concept into the design of FSFGIC architecture in order to address the limited sample problem in few-shot learning and at the same time to increase the discriminability of the model for fine-grained image classification. Specifically, we first design a feature re-abstraction embedding network that has the ability to not only obtain the required semantic features for effective metric learning but also re-enhance such features with finer details from input images. Then the descriptors of the query images and the support classes are projected into different non-linear spaces in our proposed similarity metric learning network to learn discriminative projection factors. This design can effectively operate in the challenging and restricted condition of a FSFGIC task for making the distance between the samples within the same class smaller and the distance between samples from different classes larger and for reducing the coupling relationship between samples from different categories. Furthermore, a novel similarity measure based on the proposed non-linear data project is presented for evaluating the relationships of feature information between a query image and a support set. It is worth to note that our proposed architecture can be easily embedded into any episodic training mechanisms for end-to-end training from scratch. Extensive experiments on FSFGIC tasks demonstrate the superiority of the proposed methods over the state-of-the-art benchmarks.
The field of Explainable Artificial Intelligence (XAI) aims to build explainable and interpretable machine learning (or deep learning) methods without sacrificing prediction performance. Convolutional Neural Networks (CNNs) have been successful in making predictions, especially in image classification. However, these famous deep learning models use tens of millions of parameters based on a large number of pre-trained filters which have been repurposed from previous data sets. We propose a novel Interaction-based Convolutional Neural Network (ICNN) that does not make assumptions about the relevance of local information. Instead, we use a model-free Influence Score (I-score) to directly extract the influential information from images to form important variable modules. We demonstrate that the proposed method produces state-of-the-art prediction performance of 99.8% on a real-world data set classifying COVID-19 Chest X-ray images without sacrificing the explanatory power of the model. This proposed design can efficiently screen COVID-19 patients before human diagnosis, and will be the benchmark for addressing future XAI problems in large-scale data sets.
Explainable artificial intelligence has rapidly emerged since lawmakers have started requiring interpretable models for safety-critical domains. Concept-based neural networks have arisen as explainable-by-design methods as they leverage human-understandable symbols (i.e. concepts) to predict class memberships. However, most of these approaches focus on the identification of the most relevant concepts but do not provide concise, formal explanations of how such concepts are leveraged by the classifier to make predictions. In this paper, we propose a novel end-to-end differentiable approach enabling the extraction of logic explanations from neural networks using the formalism of First-Order Logic. The method relies on an entropy-based criterion which automatically identifies the most relevant concepts. We consider four different case studies to demonstrate that: (i) this entropy-based criterion enables the distillation of concise logic explanations in safety-critical domains from clinical data to computer vision; (ii) the proposed approach outperforms state-of-the-art white-box models in terms of classification accuracy and matches black box performances.
Humans have the ability to seamlessly combine low-level visual input with high-level symbolic reasoning often in the form of recognising objects, learning relations between them and applying rules. Neuro-symbolic systems aim to bring a unifying approach to connectionist and logic-based principles for visual processing and abstract reasoning respectively. This paper presents a complete neuro-symbolic method for processing images into objects, learning relations and logical rules in an end-to-end fashion. The main contribution is a differentiable layer in a deep learning architecture from which symbolic relations and rules can be extracted by pruning and thresholding. We evaluate our model using two datasets: subgraph isomorphism task for symbolic rule learning and an image classification domain with compound relations for learning objects, relations and rules. We demonstrate that our model scales beyond state-of-the-art symbolic learners and outperforms deep relational neural network architectures.
In this paper, a novel second-order method called NG+ is proposed. By following the rule ``the shape of the gradient equals the shape of the parameter", we define a generalized fisher information matrix (GFIM) using the products of gradients in the matrix form rather than the traditional vectorization. Then, our generalized natural gradient direction is simply the inverse of the GFIM multiplies the gradient in the matrix form. Moreover, the GFIM and its inverse keeps the same for multiple steps so that the computational cost can be controlled and is comparable with the first-order methods. A global convergence is established under some mild conditions and a regret bound is also given for the online learning setting. Numerical results on image classification with ResNet50, quantum chemistry modeling with Schnet, neural machine translation with Transformer and recommendation system with DLRM illustrate that GN+ is competitive with the state-of-the-art methods.
A few years ago, the first CNN surpassed human performance on ImageNet. However, it soon became clear that machines lack robustness on more challenging test cases, a major obstacle towards deploying machines "in the wild" and towards obtaining better computational models of human visual perception. Here we ask: Are we making progress in closing the gap between human and machine vision? To answer this question, we tested human observers on a broad range of out-of-distribution (OOD) datasets, recording 85,120 psychophysical trials across 90 participants. We then investigated a range of promising machine learning developments that crucially deviate from standard supervised CNNs along three axes: objective function (self-supervised, adversarially trained, CLIP language-image training), architecture (e.g. vision transformers), and dataset size (ranging from 1M to 1B). Our findings are threefold. (1.) The longstanding distortion robustness gap between humans and CNNs is closing, with the best models now exceeding human feedforward performance on most of the investigated OOD datasets. (2.) There is still a substantial image-level consistency gap, meaning that humans make different errors than models. In contrast, most models systematically agree in their categorisation errors, even substantially different ones like contrastive self-supervised vs. standard supervised models. (3.) In many cases, human-to-model consistency improves when training dataset size is increased by one to three orders of magnitude. Our results give reason for cautious optimism: While there is still much room for improvement, the behavioural difference between human and machine vision is narrowing. In order to measure future progress, 17 OOD datasets with image-level human behavioural data and evaluation code are provided as a toolbox and benchmark at: https://github.com/bethgelab/model-vs-human/
Robustness to variations in lighting conditions is a key objective for any deep vision system. To this end, our paper extends the receptive field of convolutional neural networks with two residual components, ubiquitous in the visual processing system of vertebrates: On-center and off-center pathways, with excitatory center and inhibitory surround; OOCS for short. The on-center pathway is excited by the presence of a light stimulus in its center but not in its surround, whereas the off-center one is excited by the absence of a light stimulus in its center but not in its surround. We design OOCS pathways via a difference of Gaussians, with their variance computed analytically from the size of the receptive fields. OOCS pathways complement each other in their response to light stimuli, ensuring this way a strong edge-detection capability, and as a result, an accurate and robust inference under challenging lighting conditions. We provide extensive empirical evidence showing that networks supplied with the OOCS edge representation gain accuracy and illumination-robustness compared to standard deep models.