With the maturing of deep learning systems, trustworthiness is becoming increasingly important for model assessment. We understand trustworthiness as the combination of explainability and robustness. Generative classifiers (GCs) are a promising class of models that are said to naturally accomplish these qualities. However, this has mostly been demonstrated on simple datasets such as MNIST and CIFAR in the past. In this work, we firstly develop an architecture and training scheme that allows GCs to operate on a more relevant level of complexity for practical computer vision, namely the ImageNet challenge. Secondly, we demonstrate the immense potential of GCs for trustworthy image classification. Explainability and some aspects of robustness are vastly improved compared to feed-forward models, even when the GCs are just applied naively. While not all trustworthiness problems are solved completely, we observe that GCs are a highly promising basis for further algorithms and modifications. We release our trained model for download in the hope that it serves as a starting point for other generative classification tasks, in much the same way as pretrained ResNet architectures do for discriminative classification.
The recent success of learning-based algorithms can be greatly attributed to the immense amount of annotated data used for training. Yet, many datasets lack annotations due to the high costs associated with labeling, resulting in degraded performances of deep learning methods. Self-supervised learning is frequently adopted to mitigate the reliance on massive labeled datasets since it exploits unlabeled data to learn relevant feature representations. In this work, we propose SS-StyleGAN, a self-supervised approach for image annotation and classification suitable for extremely small annotated datasets. This novel framework adds self-supervision to the StyleGAN architecture by integrating an encoder that learns the embedding to the StyleGAN latent space, which is well-known for its disentangled properties. The learned latent space enables the smart selection of representatives from the data to be labeled for improved classification performance. We show that the proposed method attains strong classification results using small labeled datasets of sizes 50 and even 10. We demonstrate the superiority of our approach for the tasks of COVID-19 and liver tumor pathology identification.
Explaining the prediction of deep neural networks (DNNs) and semantic image compression are two active research areas of deep learning with a numerous of applications in decision-critical systems, such as surveillance cameras, drones and self-driving cars, where interpretable decision is critical and storage/network bandwidth is limited. In this paper, we propose a novel end-to-end Neural Image Compression and Explanation (NICE) framework that learns to (1) explain the predictions of convolutional neural networks (CNNs), and (2) subsequently compress the input images for efficient storage or transmission. Specifically, NICE generates a sparse mask over an input image by attaching a stochastic binary gate to each pixel of the image, whose parameters are learned through the interaction with the CNN classifier to be explained. The generated mask is able to capture the saliency of each pixel measured by its influence to the final prediction of CNN; it can also be used to produce a mixed-resolution image, where important pixels maintain their original high resolution and insignificant background pixels are subsampled to a low resolution. The produced images achieve a high compression rate (e.g., about 0.6x of original image file size), while retaining a similar classification accuracy. Extensive experiments across multiple image classification benchmarks demonstrate the superior performance of NICE compared to the state-of-the-art methods in terms of explanation quality and semantic image compression rate. Our code is available at: https://github.com/lxuniverse/NICE.
Researchers often spend weeks sifting through decades of unlabeled satellite imagery(on NASA Worldview) in order to develop datasets on which they can start conducting research. We developed an interactive, scalable and fast image similarity search engine (which can take one or more images as the query image) that automatically sifts through the unlabeled dataset reducing dataset generation time from weeks to minutes. In this work, we describe key components of the end to end pipeline. Our similarity search system was created to be able to identify similar images from a potentially petabyte scale database that are similar to an input image, and for this we had to break down each query image into its features, which were generated by a classification layer stripped CNN trained in a supervised manner. To store and search these features efficiently, we had to make several scalability improvements. To improve the speed, reduce the storage, and shrink memory requirements for embedding search, we add a fully connected layer to our CNN make all images into a 128 length vector before entering the classification layers. This helped us compress the size of our image features from 2048 (for ResNet, which was initially tried as our featurizer) to 128 for our new custom model. Additionally, we utilize existing approximate nearest neighbor search libraries to significantly speed up embedding search. Our system currently searches over our entire database of images at 5 seconds per query on a single virtual machine in the cloud. In the future, we would like to incorporate a SimCLR based featurizing model which could be trained without any labelling by a human (since the classification aspect of the model is irrelevant to this use case).
Hyperspectral images of land-cover captured by airborne or satellite-mounted sensors provide a rich source of information about the chemical composition of the materials present in a given place. This makes hyperspectral imaging an important tool for earth sciences, land-cover studies, and military and strategic applications. However, the scarcity of labeled training examples and spatial variability of spectral signature are two of the biggest challenges faced by hyperspectral image classification. In order to address these issues, we aim to develop a framework for material-agnostic information retrieval in hyperspectral images based on Positive-Unlabelled (PU) classification. Given a hyperspectral scene, the user labels some positive samples of a material he/she is looking for and our goal is to retrieve all the remaining instances of the query material in the scene. Additionally, we require the system to work equally well for any material in any scene without the user having to disclose the identity of the query material. This material-agnostic nature of the framework provides it with superior generalization abilities. We explore two alternative approaches to solve the hyperspectral image classification problem within this framework. The first approach is an adaptation of non-negative risk estimation based PU learning for hyperspectral data. The second approach is based on one-versus-all positive-negative classification where the negative class is approximately sampled using a novel spectral-spatial retrieval model. We propose two annotator models - uniform and blob - that represent the labelling patterns of a human annotator. We compare the performances of the proposed algorithms for each annotator model on three benchmark hyperspectral image datasets - Indian Pines, Pavia University and Salinas.
This work presents a novel method of exploring human brain-visual representations, with a view towards replicating these processes in machines. The core idea is to learn plausible computational and biological representations by correlating human neural activity and natural images. Thus, we first propose a model, EEG-ChannelNet, to learn a brain manifold for EEG classification. After verifying that visual information can be extracted from EEG data, we introduce a multimodal approach that uses deep image and EEG encoders, trained in a siamese configuration, for learning a joint manifold that maximizes a compatibility measure between visual features and brain representations. We then carry out image classification and saliency detection on the learned manifold. Performance analyses show that our approach satisfactorily decodes visual information from neural signals. This, in turn, can be used to effectively supervise the training of deep learning models, as demonstrated by the high performance of image classification and saliency detection on out-of-training classes. The obtained results show that the learned brain-visual features lead to improved performance and simultaneously bring deep models more in line with cognitive neuroscience work related to visual perception and attention.
This paper investigates novel classifier ensemble techniques for uncertainty calibration applied to various deep neural networks for image classification. We evaluate both accuracy and calibration metrics, focusing on Expected Calibration Error (ECE) and Maximum Calibration Error (MCE). Our work compares different methods for building simple yet efficient classifier ensembles, including majority voting and several metamodel-based approaches. Our evaluation reveals that while state-of-the-art deep neural networks for image classification achieve high accuracy on standard datasets, they frequently suffer from significant calibration errors. Basic ensemble techniques like majority voting provide modest improvements, while metamodel-based ensembles consistently reduce ECE and MCE across all architectures. Notably, the largest of our compared metamodels demonstrate the most substantial calibration improvements, with minimal impact on accuracy. Moreover, classifier ensembles with metamodels outperform traditional model ensembles in calibration performance, while requiring significantly fewer parameters. In comparison to traditional post-hoc calibration methods, our approach removes the need for a separate calibration dataset. These findings underscore the potential of our proposed metamodel-based classifier ensembles as an efficient and effective approach to improving model calibration, thereby contributing to more reliable deep learning systems.
This paper adresses the problem of interactive multiclass segmentation. We propose a fast and efficient new interactive segmentation method called Superpixel Classification-based Interactive Segmentation (SCIS). From a few strokes drawn by a human user over an image, this method extracts relevant semantic objects. To get a fast calculation and an accurate segmentation, SCIS uses superpixel over-segmentation and support vector machine classification. In this paper, we demonstrate that SCIS significantly outperfoms competing algorithms by evaluating its performances on the reference benchmarks of McGuinness and Santner.
In this paper we propose the use of multiple local binary patterns(LBPs) to effectively classify land use images. We use the UC Merced 21 class land use image dataset. Task is challenging for classification as the dataset contains intra class variability and inter class similarities. Our proposed method of using multi-neighborhood LBPs combined with nearest neighbor classifier is able to achieve an accuracy of 77.76%. Further class wise analysis is conducted and suitable suggestion are made for further improvements to classification accuracy.
This paper aims to classify and locate objects accurately and efficiently, without using bounding box annotations. It is challenging as objects in the wild could appear at arbitrary locations and in different scales. In this paper, we propose a novel classification architecture ProNet based on convolutional neural networks. It uses computationally efficient neural networks to propose image regions that are likely to contain objects, and applies more powerful but slower networks on the proposed regions. The basic building block is a multi-scale fully-convolutional network which assigns object confidence scores to boxes at different locations and scales. We show that such networks can be trained effectively using image-level annotations, and can be connected into cascades or trees for efficient object classification. ProNet outperforms previous state-of-the-art significantly on PASCAL VOC 2012 and MS COCO datasets for object classification and point-based localization.
Sparse coding can learn good robust representation to noise and model more higher-order representation for image classification. However, the inference algorithm is computationally expensive even though the supervised signals are used to learn compact and discriminative dictionaries in sparse coding techniques. Luckily, a simplified neural network module (SNNM) has been proposed to directly learn the discriminative dictionaries for avoiding the expensive inference. But the SNNM module ignores the sparse representations. Therefore, we propose a sparse SNNM module by adding the mixed-norm regularization (l1/l2 norm). The sparse SNNM modules are further stacked to build a sparse deep stacking network (S-DSN). In the experiments, we evaluate S-DSN with four databases, including Extended YaleB, AR, 15 scene and Caltech101. Experimental results show that our model outperforms related classification methods with only a linear classifier. It is worth noting that we reach 98.8% recognition accuracy on 15 scene.
This paper analyzes and compares different deep learning loss functions in the framework of multi-label remote sensing (RS) image scene classification problems. We consider seven loss functions: 1) cross-entropy loss; 2) focal loss; 3) weighted cross-entropy loss; 4) Hamming loss; 5) Huber loss; 6) ranking loss; and 7) sparseMax loss. All the considered loss functions are analyzed for the first time in RS. After a theoretical analysis, an experimental analysis is carried out to compare the considered loss functions in terms of their: 1) overall accuracy; 2) class imbalance awareness (for which the number of samples associated to each class significantly varies); 3) convexibility and differentiability; and 4) learning efficiency (i.e., convergence speed). On the basis of our analysis, some guidelines are derived for a proper selection of a loss function in multi-label RS scene classification problems.
Histopathology remains the gold standard for diagnosis of various cancers. Recent advances in computer vision, specifically deep learning, have facilitated the analysis of histopathology images for various tasks, including immune cell detection and microsatellite instability classification. The state-of-the-art for each task often employs base architectures that have been pretrained for image classification on ImageNet. The standard approach to develop classifiers in histopathology tends to focus narrowly on optimizing models for a single task, not considering the aspects of modeling innovations that improve generalization across tasks. Here we present ChampKit (Comprehensive Histopathology Assessment of Model Predictions toolKit): an extensible, fully reproducible benchmarking toolkit that consists of a broad collection of patch-level image classification tasks across different cancers. ChampKit enables a way to systematically document the performance impact of proposed improvements in models and methodology. ChampKit source code and data are freely accessible at https://github.com/kaczmarj/champkit .
Convolutional neural networks (CNNs) have been pivotal in various 2D image analysis tasks, including computer vision, image indexing and retrieval or semantic classification. Extending CNNs to 3D data such as point clouds and 3D meshes raises significant challenges since the very basic convolution and pooling operators need to be completely re-visited and re-defined in an appropriate manner to tackle irregular connectivity issues. In this paper, we introduce MeshConv3D, a 3D mesh-dedicated methodology integrating specialized convolution and face collapse-based pooling operators. MeshConv3D operates directly on meshes of arbitrary topology, without any need of prior re-meshing/conversion techniques. In order to validate our approach, we have considered a semantic classification task. The experimental results obtained on three distinct benchmark datasets show that the proposed approach makes it possible to achieve equivalent or superior classification results, while minimizing the related memory footprint and computational load.
Images are an important data source for diagnosis and treatment of oral diseases. The manual classification of images may lead to misdiagnosis or mistreatment due to subjective errors. In this paper an image classification model based on Convolutional Neural Network is applied to Quantitative Light-induced Fluorescence images. The deep neural network outperforms other state of the art shallow classification models in predicting labels derived from three different dental plaque assessment scores. The model directly benefits from multi-channel representation of the images resulting in improved performance when, besides the Red colour channel, additional Green and Blue colour channels are used.
Solder joint inspection (SJI) is a critical process in the production of printed circuit boards (PCB). Detection of solder errors during SJI is quite challenging as the solder joints have very small sizes and can take various shapes. In this study, we first show that solders have low feature diversity, and that the SJI can be carried out as a fine-grained image classification task which focuses on hard-to-distinguish object classes. To improve the fine-grained classification accuracy, penalizing confident model predictions by maximizing entropy was found useful in the literature. Inline with this information, we propose using the {\alpha}-skew Jensen-Shannon divergence ({\alpha}-JS) for penalizing the confidence in model predictions. We compare the {\alpha}-JS regularization with both existing entropyregularization based methods and the methods based on attention mechanism, segmentation techniques, transformer models, and specific loss functions for fine-grained image classification tasks. We show that the proposed approach achieves the highest F1-score and competitive accuracy for different models in the finegrained solder joint classification task. Finally, we visualize the activation maps and show that with entropy-regularization, more precise class-discriminative regions are localized, which are also more resilient to noise. Code will be made available here upon acceptance.
Pre-trained vision-language models (VLMs) have enabled significant progress in open vocabulary computer vision tasks such as image classification, object detection and image segmentation. Some recent works have focused on extending VLMs to open vocabulary single label action classification in videos. However, previous methods fall short in holistic video understanding which requires the ability to simultaneously recognize multiple actions and entities e.g., objects in the video in an open vocabulary setting. We formulate this problem as open vocabulary multilabel video classification and propose a method to adapt a pre-trained VLM such as CLIP to solve this task. We leverage large language models (LLMs) to provide semantic guidance to the VLM about class labels to improve its open vocabulary performance with two key contributions. First, we propose an end-to-end trainable architecture that learns to prompt an LLM to generate soft attributes for the CLIP text-encoder to enable it to recognize novel classes. Second, we integrate a temporal modeling module into CLIP's vision encoder to effectively model the spatio-temporal dynamics of video concepts as well as propose a novel regularized finetuning technique to ensure strong open vocabulary classification performance in the video domain. Our extensive experimentation showcases the efficacy of our approach on multiple benchmark datasets.
Objective: Surgical data science is evolving into a research field that aims to observe everything occurring within and around the treatment process to provide situation-aware data-driven assistance. In the context of endoscopic video analysis, the accurate classification of organs in the field of view of the camera proffers a technical challenge. Herein, we propose a new approach to anatomical structure classification and image tagging that features an intrinsic measure of confidence to estimate its own performance with high reliability and which can be applied to both RGB and multispectral imaging (MI) data. Methods: Organ recognition is performed using a superpixel classification strategy based on textural and reflectance information. Classification confidence is estimated by analyzing the dispersion of class probabilities. Assessment of the proposed technology is performed through a comprehensive in vivo study with seven pigs. Results: When applied to image tagging, mean accuracy in our experiments increased from 65% (RGB) and 80% (MI) to 90% (RGB) and 96% (MI) with the confidence measure. Conclusion: Results showed that the confidence measure had a significant influence on the classification accuracy, and MI data are better suited for anatomical structure labeling than RGB data. Significance: This work significantly enhances the state of art in automatic labeling of endoscopic videos by introducing the use of the confidence metric, and by being the first study to use MI data for in vivo laparoscopic tissue classification. The data of our experiments will be released as the first in vivo MI dataset upon publication of this paper.
We introduce the Single Stage Headless (SSH) face detector. Unlike two stage proposal-classification detectors, SSH detects faces in a single stage directly from the early convolutional layers in a classification network. SSH is headless. That is, it is able to achieve state-of-the-art results while removing the "head" of its underlying classification network -- i.e. all fully connected layers in the VGG-16 which contains a large number of parameters. Additionally, instead of relying on an image pyramid to detect faces with various scales, SSH is scale-invariant by design. We simultaneously detect faces with different scales in a single forward pass of the network, but from different layers. These properties make SSH fast and light-weight. Surprisingly, with a headless VGG-16, SSH beats the ResNet-101-based state-of-the-art on the WIDER dataset. Even though, unlike the current state-of-the-art, SSH does not use an image pyramid and is 5X faster. Moreover, if an image pyramid is deployed, our light-weight network achieves state-of-the-art on all subsets of the WIDER dataset, improving the AP by 2.5%. SSH also reaches state-of-the-art results on the FDDB and Pascal-Faces datasets while using a small input size, leading to a runtime of 50 ms/image on a GPU. The code is available at https://github.com/mahyarnajibi/SSH.
Contrastive Vision-Language Pre-training(CLIP) demonstrates impressive zero-shot capability. The key to improve the adaptation of CLIP to downstream task with few exemplars lies in how to effectively model and transfer the useful knowledge embedded in CLIP. Previous work mines the knowledge typically based on the limited visual samples and close-set semantics (i.e., within target category set of downstream task). However, the aligned CLIP image/text encoders contain abundant relationships between visual features and almost infinite open semantics, which may benefit the few-shot learning but remains unexplored. In this paper, we propose to mine open semantics as anchors to perform a relation transition from image-anchor relationship to image-target relationship to make predictions. Specifically, we adopt a transformer module which takes the visual feature as "Query", the text features of the anchors as "Key" and the similarity matrix between the text features of anchor and target classes as "Value". In this way, the output of such a transformer module represents the relationship between the image and target categories, i.e., the classification predictions. To avoid manually selecting the open semantics, we make the [CLASS] token of input text embedding learnable. We conduct extensive experiments on eleven representative classification datasets. The results show that our method performs favorably against previous state-of-the-arts considering few-shot classification settings.