Automated recognition and classification of bacteria species from microscopic images have significant importance in clinical microbiology. Bacteria classification is usually carried out manually by biologists using different shapes and morphologic characteristics of bacteria species. The manual taxonomy of bacteria types from microscopy images is time-consuming and a challenging task for even experienced biologists. In this study, an automated deep learning based classification approach has been proposed to classify bacterial images into different categories. The ResNet-50 pre-trained CNN architecture has been used to classify digital bacteria images into 33 categories. The transfer learning technique was employed to accelerate the training process of the network and improve the classification performance of the network. The proposed method achieved an average classification accuracy of 99.2%. The experimental results demonstrate that the proposed technique surpasses state-of-the-art methods in the literature and can be used for any type of bacteria classification tasks.
In this paper, we present a methodology and the corresponding Python library 1 for the classification of webpages. Our method retrieves a fixed number of images from a given webpage, and based on them classifies the webpage into a set of established classes with a given probability. The library trains a random forest model build upon the features extracted from images by a pre-trained deep network. The implementation is tested by recognizing weapon class webpages in a curated list of 3859 websites. The results show that the best method of classifying a webpage into the studies classes is to assign the class according to the maximum probability of any image belonging to this (weapon) class being above the threshold, across all the retrieved images. Further research explores the possibilities for the developed methodology to also apply in image classification for healthcare applications.
Few-shot image classification requires the classifier to robustly cope with unseen classes even if there are only a few samples for each class. Recent advances benefit from the meta-learning process where episodic tasks are formed to train a model that can adapt to class change. However, these task sare independent to each other and existing works mainly rely on limited samples of individual support set in a single meta task. This strategy leads to severe meta shift issues across multiple tasks, meaning the learned prototypes or class descriptors are not stable as each task only involves their own support set. To avoid this problem, we propose a concise Semantic RegularizationNetwork to learn a common semantic space under the framework of meta-learning. In this space, all class descriptors can be regularized by the learned semantic basis, which can effectively solve the meta shift problem. The key is to train a class encoder and decoder structure that can encode the sample embedding features into the semantic domain with trained semantic basis, and generate a more stable and general class descriptor from the decoder. We evaluate our work by extensive comparisons with previous methods on three benchmark datasets (MiniImageNet, TieredImageNet, and CUB). The results show that the semantic regularization module improves performance by 4%-7% over the baseline method, and achieves competitive results over the current state-of-the-art models.
One of the well-known challenges in computer vision tasks is the visual diversity of images, which could result in an agreement or disagreement between the learned knowledge and the visual content exhibited by the current observation. In this work, we first define such an agreement in a concepts learning process as congruency. Formally, given a particular task and sufficiently large dataset, the congruency issue occurs in the learning process whereby the task-specific semantics in the training data are highly varying. We propose a Direction Concentration Learning (DCL) method to improve congruency in the learning process, where enhancing congruency influences the convergence path to be less circuitous. The experimental results show that the proposed DCL method generalizes to state-of-the-art models and optimizers, as well as improves the performances of saliency prediction task, continual learning task, and classification task. Moreover, it helps mitigate the catastrophic forgetting problem in the continual learning task. The code is publicly available at https://github.com/luoyan407/congruency.
Multi-label image and video classification are fundamental yet challenging tasks in computer vision. The main challenges lie in capturing spatial or temporal dependencies between labels and discovering the locations of discriminative features for each class. In order to overcome these challenges, we propose to use cross-modality attention with semantic graph embedding for multi label classification. Based on the constructed label graph, we propose an adjacency-based similarity graph embedding method to learn semantic label embeddings, which explicitly exploit label relationships. Then our novel cross-modality attention maps are generated with the guidance of learned label embeddings. Experiments on two multi-label image classification datasets (MS-COCO and NUS-WIDE) show our method outperforms other existing state-of-the-arts. In addition, we validate our method on a large multi-label video classification dataset (YouTube-8M Segments) and the evaluation results demonstrate the generalization capability of our method.
Polarimetric SAR data has the characteristics of all-weather, all-time and so on, which is widely used in many fields. However, the data of annotation is relatively small, which is not conducive to our research. In this paper, we have collected five open polarimetric SAR images, which are images of the San Francisco area. These five images come from different satellites at different times, which has great scientific research value. We annotate the collected images at the pixel level for image classification and segmentation. For the convenience of researchers, the annotated data is open source https://github.com/liuxuvip/PolSF.
Zero-shot learning, the task of learning to recognize new classes not seen during training, has received considerable attention in the case of 2D image classification. However despite the increasing ubiquity of 3D sensors, the corresponding 3D point cloud classification problem has not been meaningfully explored and introduces new challenges. This paper extends, for the first time, transductive Zero-Shot Learning (ZSL) and Generalized Zero-Shot Learning (GZSL) approaches to the domain of 3D point cloud classification. To this end, a novel triplet loss is developed that takes advantage of unlabeled test data. While designed for the task of 3D point cloud classification, the method is also shown to be applicable to the more common use-case of 2D image classification. An extensive set of experiments is carried out, establishing state-of-the-art for ZSL and GZSL in the 3D point cloud domain, as well as demonstrating the applicability of the approach to the image domain.
We propose Disentanglement based Active Learning (DAL), a new active learning technique based on self-supervision which leverages the concept of disentanglement. Instead of requesting labels from human oracle, our method automatically labels the majority of the datapoints, thus drastically reducing the human labeling budget in Generative Adversarial Net (GAN) based active learning approaches. The proposed method uses Information Maximizing Generative Adversarial Nets (InfoGAN) to learn disentangled class category representations. Disagreement between active learner predictions and InfoGAN labels decides if the datapoints need to be human-labeled. We also introduce a label correction mechanism that aims to filter out label noise that occurs due to automatic labeling. Results on three benchmark datasets for the image classification task demonstrate that our method achieves better performance compared to existing GAN-based active learning approaches.
Due to respectively limited training data, different entities addressing the same vision task based on certain sensitive images may not train a robust deep network. This paper introduces a new vision task where various entities share task-specific image data to enlarge each other's training data volume without visually disclosing sensitive contents (e.g. illegal images). Then, we present a new structure-based training regime to enable different entities learn task-specific and reconstruction-proof image representations for image data sharing. Specifically, each entity learns a private Deep Poisoning Module (DPM) and insert it to a pre-trained deep network, which is designed to perform the specific vision task. The DPM deliberately poisons convolutional image features to prevent image reconstructions, while ensuring that the altered image data is functionally equivalent to the non-poisoned data for the specific vision task. Given this equivalence, the poisoned features shared from one entity could be used by another entity for further model refinement. Experimental results on image classification prove the efficacy of the proposed method.
Deep neural networks such as GoogLeNet, ResNet, and BERT have achieved impressive performance in tasks such as image and text classification. To understand how such performance is achieved, we probe a trained deep neural network by studying neuron activations, i.e., combinations of neuron firings, at various layers of the network in response to a particular input. With a large number of inputs, we aim to obtain a global view of what neurons detect by studying their activations. In particular, we develop visualizations that show the shape of the activation space, the organizational principle behind neuron activations, and the relationships of these activations within a layer. Applying tools from topological data analysis, we present TopoAct, a visual exploration system to study topological summaries of activation vectors. We present exploration scenarios using TopoAct that provide valuable insights into learned representations of neural networks. We expect TopoAct to give a topological perspective that enriches the current toolbox of neural network analysis, and to provide a basis for network architecture diagnosis and data anomaly detection.
We extend first-order model agnostic meta-learning algorithms (including FOMAML and Reptile) to image segmentation, present a novel neural network architecture built for fast learning which we call EfficientLab, and leverage a formal definition of the test error of meta-learning algorithms to decrease error on out of distribution tasks. We show state of the art results on the FSS-1000 dataset by meta-training EfficientLab with FOMAML and using Bayesian optimization to infer the optimal test-time adaptation routine hyperparameters. We also construct a small benchmark dataset, FP-k, for the empirical study of how meta-learning systems perform in both few- and many-shot settings. On the FP-k dataset, we show that meta-learned initializations provide value for canonical few-shot image segmentation but their performance is quickly matched by conventional transfer learning with performance being equal beyond 10 labeled examples. Our code, meta-learned model, and the FP-k dataset are available at https://github.com/ml4ai/mliis .
Recurrent neural networks (RNNs) are challenging to train, let alone those with deep spatial structures. Architectures built upon highway connections such as Recurrent Highway Network (RHN) were developed to allow larger step-to-step transition depth, leading to more expressive models. However, problems that require capturing long-term dependencies still can not be well addressed by these models. Moreover, the ability to keep long-term memories tends to diminish when the spatial depth increases, since deeper structure may accelerate gradient vanishing. In this paper, we address these issues by proposing a novel RNN architecture based on RHN, namely the Recurrent Highway Network with Grouped Auxiliary Memory (GAM-RHN). The proposed architecture interconnects the RHN with a set of auxiliary memory units specifically for storing long-term information via reading and writing operations, which is analogous to Memory Augmented Neural Networks (MANNs). Experimental results on artificial long time lag tasks show that GAM-RHNs can be trained efficiently while being deep in both time and space. We also evaluate the proposed architecture on a variety of tasks, including language modeling, sequential image classification, and financial market forecasting. The potential of our approach is demonstrated by achieving state-of-the-art results on these tasks.
Generic object counting in natural scenes is a challenging computer vision problem. Existing approaches either rely on instance-level supervision or absolute count information to train a generic object counter. We introduce a partially supervised setting that significantly reduces the supervision level required for generic object counting. We propose two novel frameworks, named lower-count (LC) and reduced lower-count (RLC), to enable object counting under this setting. Our frameworks are built on a novel dual-branch architecture that has an image classification and a density branch. Our LC framework reduces the annotation cost due to multiple instances in an image by using only lower-count supervision for all object categories. Our RLC framework further reduces the annotation cost arising from large numbers of object categories in a dataset by only using lower-count supervision for a subset of categories and class-labels for the remaining ones. The RLC framework extends our dual-branch LC framework with a novel weight modulation layer and a category-independent density map prediction. Experiments are performed on COCO, Visual Genome and PASCAL 2007 datasets. Our frameworks perform on par with state-of-the-art approaches using higher levels of supervision. Additionally, we demonstrate the applicability of our LC supervised density map for image-level supervised instance segmentation.
Ground referencing is essential for supervised crop mapping. However, conventional ground truthing involves extensive field surveys and post processing, which is costly in terms of time and labor. In this study, we applied a convolutional neural network (CNN) model to explore the efficacy of automatic ground truthing via Google street view (GSV) images in two distinct farming regions: central Illinois and southern California. We demonstrated the feasibility and reliability of the new ground referencing technique further by performing pixel-based crop mapping with vegetation indices as the model input. The results were evaluated using the United States Department of Agriculture (USDA) crop data layer (CDL) products. From 8,514 GSV images, the CNN model screened out 2,645 target crop images. These images were well classified into crop types, including alfalfa, almond, corn, cotton, grape, soybean, and pistachio. The overall GSV image classification accuracy reached 93% in California and 97% in Illinois. We then shifted the image geographic coordinates using fixed empirical coefficients to produce 8,173 crop reference points including 1,764 in Illinois and 6,409 in California. Evaluation of these new reference points with CDL products showed satisfactory coherence, with 94 to 97% agreement. CNN-based mapping also captured the general pattern of crop type distributions. The overall differences between CDL products and our mapping results were 4% in California and 5% in Illinois. Thus, using these deep learning and GSV image techniques, we have provided an efficient and cost-effective alternative method for ground referencing and crop mapping.
There have been many efforts in attacking image classification models with adversarial perturbations, but the same topic on video classification has not yet been thoroughly studied. This paper presents a novel idea of video-based attack, which appends a few dummy frames (e.g., containing the texts of `thanks for watching') to a video clip and then adds adversarial perturbations only on these new frames. Our approach enjoys three major benefits, namely, a high success rate, a low perceptibility, and a strong ability in transferring across different networks. These benefits mostly come from the common dummy frame which pushes all samples towards the boundary of classification. On the other hand, such attacks are easily to be concealed since most people would not notice the abnormality behind the perturbed video clips. We perform experiments on two popular datasets with six state-of-the-art video classification models, and demonstrate the effectiveness of our approach in the scenario of universal video attacks.
The unprecedented performance achieved by deep convolutional neural networks for image classification is linked primarily to their ability of capturing rich structural features at various layers within networks. Here we design a series of experiments, inspired by children's learning of the arithmetic addition of two integers, to showcase that such deep networks can go beyond the structural features to learn deeper knowledge. In our experiments, a set of images is constructed, each image containing an arithmetic addition $n+m$ in its central area, and several classification networks are then trained over a subset of images, using the sum as the label. Tests on the excluded images show that, as the image set gets larger, the networks have well learnt the law of arithmetic additions so as to build up their autonomous reasoning ability strongly. For instance, networks trained over a small percentage of images can classify a big majority of the remaining images correctly, and many arithmetic additions involving some integers that have never been seen during the training can also be solved correctly by the trained networks.
Deep learning has made tremendous advances in computer vision tasks such as image classification. However, recent studies have shown that deep learning models are vulnerable to specifically crafted adversarial inputs that are quasi-imperceptible to humans. In this work, we propose a novel approach to defending adversarial attacks. We employ an input processing technique based on denoising autoencoders as a defense. It has been shown that the input perturbations grow and accumulate as noise in feature maps while propagating through a convolutional neural network (CNN). We exploit the noisy feature maps by using an additional subnetwork to extract image feature maps and train an auto-encoder on perceptual losses of these feature maps. This technique achieves close to state-of-the-art results on defending MNIST and CIFAR10 datasets, but more importantly, shows a new way of employing a defense that cannot be trivially trained end-to-end by the attacker. Empirical results demonstrate the effectiveness of this approach on the MNIST and CIFAR10 datasets on simple as well as iterative LP attacks. Our method can be applied as a preprocessing technique to any off the shelf CNN.
Image classification systems recently made a giant leap with the advancement of deep neural networks. However, these systems require an excessive amount of labeled data to be adequately trained. Gathering a correctly annotated dataset is not always feasible due to several factors, such as the expensiveness of the labeling process or difficulty of correctly classifying data, even for the experts. Because of these practical challenges, label noise is a common problem in real-world datasets, and numerous methods to train deep neural networks with label noise are proposed in the literature. Although deep neural networks are known to be relatively robust to label noise, their tendency to overfit data makes them vulnerable to memorizing even random noise. Therefore, it is crucial to consider the existence of label noise and develop counter algorithms to fade away its adverse effects to train deep neural networks efficiently. Even though an extensive survey of machine learning techniques under label noise exists, the literature lacks a comprehensive survey of methodologies centered explicitly around deep learning in the presence of noisy labels. This paper aims to present these algorithms while categorizing them into one of the two subgroups: noise model based and noise model free methods. Algorithms in the first group aim to estimate the noise structure and use this information to avoid the adverse effects of noisy labels. Differently, methods in the second group try to come up with inherently noise robust algorithms by using approaches like robust losses, regularizers or other learning paradigms.
Few-shot image classification aims at training a model from only a few examples for each of the "novel" classes. This paper proposes the idea of associative alignment for leveraging part of the base data by aligning the novel training instances to the closely related ones in the base training set. This expands the size of the effective novel training set by adding extra "related base" instances to the few novel ones, thereby allowing a constructive fine-tuning. We propose two associative alignment strategies: 1) a metric-learning loss for minimizing the distance between related base samples and the centroid of novel instances in the feature space, and 2) a conditional adversarial alignment loss based on the Wasserstein distance. Experiments on four standard datasets and three backbones demonstrate that combining our centroid-based alignment loss results in absolute accuracy improvements of 4.4%, 1.2%, and 6.2% in 5-shot learning over the state of the art for object recognition, fine-grained classification, and cross-domain adaptation, respectively.
Land cover mapping is essential to monitoring the environment and understanding the effects of human activities on it. The automatic approaches to land cover mapping (i.e., image segmentation) mostly used traditional machine learning that requires heuristic feature design. On natural images, deep learning has outperformed traditional machine learning approaches for image segmentation. On remote sensing images, recent studies demonstrate successful applications of specific deep learning models to small-scale land cover mapping tasks (e.g., to classify wetland complexes). However, it is not readily clear which of the existing models are the best candidates for which remote sensing task. In this study, we answer that question for mapping the fundamental land cover classes using satellite radar data. We took Sentinel-1 C-band SAR images available at no cost to users as representative data. CORINE land cover map was used as a reference, and the models were trained to distinguish between the 5 major CORINE classes. We selected seven among the state-of-the-art semantic segmentation models so that they cover a diverse set of approaches: U-Net, DeepLabV3+, PSPNet, BiSeNet, SegNet, FC-DenseNet, and FRRN-B. The models were pre-trained on the ImageNet dataset and further fine-tuned in this study. All the models demonstrated solid performance with overall accuracy between 87.9% and 93.1%, and with good to a very good agreement (kappa statistic between 0.75 and 0.86). The two best models were FC-DenseNet and SegNet, with the latter having a much smaller inference time. Overall, our results indicate that the semantic segmentation models are suitable for efficient wide-area mapping using satellite SAR imagery and also provide baseline accuracy against which the newly proposed models should be evaluated.