This paper addresses the task of learning an image clas-sifier when some categories are defined by semantic descriptions only (e.g. visual attributes) while the others are defined by exemplar images as well. This task is often referred to as the Zero-Shot classification task (ZSC). Most of the previous methods rely on learning a common embedding space allowing to compare visual features of unknown categories with semantic descriptions. This paper argues that these approaches are limited as i) efficient discrimi-native classifiers can't be used ii) classification tasks with seen and unseen categories (Generalized Zero-Shot Classification or GZSC) can't be addressed efficiently. In contrast , this paper suggests to address ZSC and GZSC by i) learning a conditional generator using seen classes ii) generate artificial training examples for the categories without exemplars. ZSC is then turned into a standard supervised learning problem. Experiments with 4 generative models and 5 datasets experimentally validate the approach, giving state-of-the-art results on both ZSC and GZSC.
We present a selective sampling method designed to accelerate the training of deep neural networks. To this end, we introduce a novel measurement, the minimal margin score (MMS), which measures the minimal amount of displacement an input should take until its predicted classification is switched. For multi-class linear classification, the MMS measure is a natural generalization of the margin-based selection criterion, which was thoroughly studied in the binary classification setting. In addition, the MMS measure provides an interesting insight into the progress of the training process and can be useful for designing and monitoring new training regimes. Empirically we demonstrate a substantial acceleration when training commonly used deep neural network architectures for popular image classification tasks. The efficiency of our method is compared against the standard training procedures, and against commonly used selective sampling alternatives: Hard negative mining selection, and Entropy-based selection. Finally, we demonstrate an additional speedup when we adopt a more aggressive learning drop regime while using the MMS selective sampling method.
Deep neural networks (DNNs) are vulnerable to backdoor attacks. Previous works have shown it extremely challenging to unlearn the undesired backdoor behavior from the network, since the entire network can be affected by the backdoor samples. In this paper, we propose a brand-new backdoor defense strategy, which makes it much easier to remove the harmful influence of backdoor samples from the model. Our defense strategy, \emph{Trap and Replace}, consists of two stages. In the first stage, we bait and trap the backdoors in a small and easy-to-replace subnetwork. Specifically, we add an auxiliary image reconstruction head on top of the stem network shared with a light-weighted classification head. The intuition is that the auxiliary image reconstruction task encourages the stem network to keep sufficient low-level visual features that are hard to learn but semantically correct, instead of overfitting to the easy-to-learn but semantically incorrect backdoor correlations. As a result, when trained on backdoored datasets, the backdoors are easily baited towards the unprotected classification head, since it is much more vulnerable than the shared stem, leaving the stem network hardly poisoned. In the second stage, we replace the poisoned light-weighted classification head with an untainted one, by re-training it from scratch only on a small holdout dataset with clean samples, while fixing the stem network. As a result, both the stem and the classification head in the final network are hardly affected by backdoor training samples. We evaluate our method against ten different backdoor attacks. Our method outperforms previous state-of-the-art methods by up to $20.57\%$, $9.80\%$, and $13.72\%$ attack success rate and on-average $3.14\%$, $1.80\%$, and $1.21\%$ clean classification accuracy on CIFAR10, GTSRB, and ImageNet-12, respectively. Code is available online.
This paper introduces the novel concept of few-shot weakly supervised learning for pathology Whole Slide Image (WSI) classification, denoted as FSWC. A solution is proposed based on prompt learning and the utilization of a large language model, GPT-4. Since a WSI is too large and needs to be divided into patches for processing, WSI classification is commonly approached as a Multiple Instance Learning (MIL) problem. In this context, each WSI is considered a bag, and the obtained patches are treated as instances. The objective of FSWC is to classify both bags and instances with only a limited number of labeled bags. Unlike conventional few-shot learning problems, FSWC poses additional challenges due to its weak bag labels within the MIL framework. Drawing inspiration from the recent achievements of vision-language models (V-L models) in downstream few-shot classification tasks, we propose a two-level prompt learning MIL framework tailored for pathology, incorporating language prior knowledge. Specifically, we leverage CLIP to extract instance features for each patch, and introduce a prompt-guided pooling strategy to aggregate these instance features into a bag feature. Subsequently, we employ a small number of labeled bags to facilitate few-shot prompt learning based on the bag features. Our approach incorporates the utilization of GPT-4 in a question-and-answer mode to obtain language prior knowledge at both the instance and bag levels, which are then integrated into the instance and bag level language prompts. Additionally, a learnable component of the language prompts is trained using the available few-shot labeled data. We conduct extensive experiments on three real WSI datasets encompassing breast cancer, lung cancer, and cervical cancer, demonstrating the notable performance of the proposed method in bag and instance classification. All codes will be available.
In recent years, deep convolutional neural networks (CNNs) have shown impressive ability to represent hyperspectral images (HSIs) and achieved encouraging results in HSI classification. However, the existing CNN-based models operate at the patch-level, in which pixel is separately classified into classes using a patch of images around it. This patch-level classification will lead to a large number of repeated calculations, and it is difficult to determine the appropriate patch size that is beneficial to classification accuracy. In addition, the conventional CNN models operate convolutions with local receptive fields, which cause failures in modeling contextual spatial information. To overcome the aforementioned limitations, we propose a novel end-to-end, pixels-to-pixels fully convolutional spatial propagation network (FCSPN) for HSI classification. Our FCSPN consists of a 3D fully convolution network (3D-FCN) and a convolutional spatial propagation network (CSPN). Specifically, the 3D-FCN is firstly introduced for reliable preliminary classification, in which a novel dual separable residual (DSR) unit is proposed to effectively capture spectral and spatial information simultaneously with fewer parameters. Moreover, the channel-wise attention mechanism is adapted in the 3D-FCN to grasp the most informative channels from redundant channel information. Finally, the CSPN is introduced to capture the spatial correlations of HSI via learning a local linear spatial propagation, which allows maintaining the HSI spatial consistency and further refining the classification results. Experimental results on three HSI benchmark datasets demonstrate that the proposed FCSPN achieves state-of-the-art performance on HSI classification.
In recent years, convolutional neural network has shown good performance in many image processing and computer vision tasks. However, a standard CNN model is not invariant to image rotations. In fact, even slight rotation of an input image will seriously degrade its performance. This shortcoming precludes the use of CNN in some practical scenarios. Thus, in this paper, we focus on designing convolutional layer with good rotation invariance. Specifically, based on a simple rotation-invariant coordinate system, we propose a new convolutional operation, called Rotation-Invariant Coordinate Convolution (RIC-C). Without additional trainable parameters and data augmentation, RIC-C is naturally invariant to arbitrary rotations around the input center. Furthermore, we find the connection between RIC-C and deformable convolution, and propose a simple but efficient approach to implement RIC-C using Pytorch. By replacing all standard convolutional layers in a CNN with the corresponding RIC-C, a RIC-CNN can be derived. Using MNIST dataset, we first evaluate the rotation invariance of RIC-CNN and compare its performance with most of existing rotation-invariant CNN models. It can be observed that RIC-CNN achieves the state-of-the-art classification on the rotated test dataset of MNIST. Then, we deploy RIC-C to VGG, ResNet and DenseNet, and conduct the classification experiments on two real image datasets. Also, a shallow CNN and the corresponding RIC-CNN are trained to extract image patch descriptors, and we compare their performance in patch verification. These experimental results again show that RIC-C can be easily used as drop in replacement for standard convolutions, and greatly enhances the rotation invariance of CNN models designed for different applications.
To learn models or features that generalize across tasks and domains is one of the grand goals of machine learning. In this paper, we propose to use cross-domain, cross-task data as validation objective for hyper-parameter optimization (HPO) to improve on this goal. Given a rich enough search space, optimization of hyper-parameters learn features that maximize validation performance and, due to the objective, generalize across tasks and domains. We demonstrate the effectiveness of this strategy on few-shot image classification within and across domains. The learned features outperform all previous few-shot and meta-learning approaches.
We demonstrate the emergence of scaling laws in the benchmark top versus QCD jet classification problem in collider physics. Six distinct physically-motivated classifiers exhibit power-law scaling of the binary cross-entropy test loss as a function of training set size, with distinct power law indices. This result highlights the importance of comparing classifiers as a function of dataset size rather than for a fixed training set, as the optimal classifier may change considerably as the dataset is scaled up. We speculate on the interpretation of our results in terms of previous models of scaling laws observed in natural language and image datasets.
Developing deep learning techniques for geometric data is an active and fruitful research area. This paper tackles the problem of sphere-type surface learning by developing a novel surface-to-image representation. Using this representation we are able to quickly adapt successful CNN models to the surface setting. The surface-image representation is based on a covering map from the image domain to the surface. Namely, the map wraps around the surface several times, making sure that every part of the surface is well represented in the image. Differently from previous surface-to-image representations, we provide a low distortion coverage of all surface parts in a single image. Specifically, for the use case of learning spherical signals, our representation provides a low distortion alternative to several popular spherical parameterizations used in deep learning. We have used the surface-to-image representation to apply standard CNN architectures to 3D models as well as spherical signals. We show that our method achieves state of the art or comparable results on the tasks of shape retrieval, shape classification and semantic shape segmentation.
In this paper, we introduce FairFaceGAN, a fairness-aware facial Image-to-Image translation model, mitigating the problem of unwanted translation in protected attributes (e.g., gender, age, race) during facial attributes editing. Unlike existing models, FairFaceGAN learns fair representations with two separate latents - one related to the target attributes to translate, and the other unrelated to them. This strategy enables FairFaceGAN to separate the information about protected attributes and that of target attributes. It also prevents unwanted translation in protected attributes while target attributes editing. To evaluate the degree of fairness, we perform two types of experiments on CelebA dataset. First, we compare the fairness-aware classification performances when augmenting data by existing image translation methods and FairFaceGAN respectively. Moreover, we propose a new fairness metric, namely Frechet Protected Attribute Distance (FPAD), which measures how well protected attributes are preserved. Experimental results demonstrate that FairFaceGAN shows consistent improvements in terms of fairness over the existing image translation models. Further, we also evaluate image translation performances, where FairFaceGAN shows competitive results, compared to those of existing methods.
Images encode both the state of the world and its content. The former is useful for tasks such as planning and control, and the latter for classification. The automatic extraction of this information is challenging because of the high-dimensionality and entangled encoding inherent to the image representation. This article introduces two theoretical approaches aimed at the resolution of these challenges. The approaches allow for the interpolation and extrapolation of images from an image sequence by joint estimation of the image representation and the generators of the sequence dynamics. In the first approach, the image representations are learned using probabilistic PCA \cite{tipping1999probabilistic}. The linear-Gaussian conditional distributions allow for a closed form analytical description of the latent distributions but assumes the underlying image manifold is a linear subspace. In the second approach, the image representations are learned using probabilistic nonlinear PCA which relieves the linear manifold assumption at the cost of requiring a variational approximation of the latent distributions. In both approaches, the underlying dynamics of the image sequence are modelled explicitly to disentangle them from the image representations. The dynamics themselves are modelled with Lie group structure which enforces the desirable properties of smoothness and composability of inter-image transformations.
Video classification has advanced tremendously over the recent years. A large part of the improvements in video classification had to do with the work done by the image classification community and the use of deep convolutional networks (CNNs) which produce competitive results with hand- crafted motion features. These networks were adapted to use video frames in various ways and have yielded state of the art classification results. We present two methods that build on this work, and scale it up to work with millions of videos and hundreds of thousands of classes while maintaining a low computational cost. In the context of large scale video processing, training CNNs on video frames is extremely time consuming, due to the large number of frames involved. We propose to avoid this problem by training CNNs on either YouTube thumbnails or Flickr images, and then using these networks' outputs as features for other higher level classifiers. We discuss the challenges of achieving this and propose two models for frame-level and video-level classification. The first is a highly efficient mixture of experts while the latter is based on long short term memory neural networks. We present results on the Sports-1M video dataset (1 million videos, 487 classes) and on a new dataset which has 12 million videos and 150,000 labels.
In vision-based object classification systems imaging sensors perceive the environment and machine learning is then used to detect and classify objects for decision-making purposes; e.g., to maneuver an automated vehicle around an obstacle or to raise an alarm to indicate the presence of an intruder in surveillance settings. In this work we demonstrate how the perception domain can be remotely and unobtrusively exploited to enable an attacker to create spurious objects or alter an existing object. An automated system relying on a detection/classification framework subject to our attack could be made to undertake actions with catastrophic results due to attacker-induced misperception. We focus on camera-based systems and show that it is possible to remotely project adversarial patterns into camera systems by exploiting two common effects in optical imaging systems, viz., lens flare/ghost effects and auto-exposure control. To improve the robustness of the attack to channel effects, we generate optimal patterns by integrating adversarial machine learning techniques with a trained end-to-end channel model. We experimentally demonstrate our attacks using a low-cost projector, on three different image datasets, in indoor and outdoor environments, and with three different cameras. Experimental results show that, depending on the projector-camera distance, attack success rates can reach as high as 100% and under targeted conditions.
The outbreak of novel coronavirus disease (COVID- 19) has claimed millions of lives and has affected all aspects of human life. This paper focuses on the application of deep learning (DL) models to medical imaging and drug discovery for managing COVID-19 disease. In this article, we detail various medical imaging-based studies such as X-rays and computed tomography (CT) images along with DL methods for classifying COVID-19 affected versus pneumonia. The applications of DL techniques to medical images are further described in terms of image localization, segmentation, registration, and classification leading to COVID-19 detection. The reviews of recent papers indicate that the highest classification accuracy of 99.80% is obtained when InstaCovNet-19 DL method is applied to an X-ray dataset of 361 COVID-19 patients, 362 pneumonia patients and 365 normal people. Furthermore, it can be seen that the best classification accuracy of 99.054% can be achieved when EDL_COVID DL method is applied to a CT image dataset of 7500 samples where COVID-19 patients, lung tumor patients and normal people are equal in number. Moreover, we illustrate the potential DL techniques in drug or vaccine discovery in combating the coronavirus. Finally, we address a number of problems, concerns and future research directions relevant to DL applications for COVID-19.
Click-based interactive segmentation (IS) aims to extract the target objects under user interaction. For this task, most of the current deep learning (DL)-based methods mainly follow the general pipelines of semantic segmentation. Albeit achieving promising performance, they do not fully and explicitly utilize and propagate the click information, inevitably leading to unsatisfactory segmentation results, even at clicked points. Against this issue, in this paper, we propose to formulate the IS task as a Gaussian process (GP)-based pixel-wise binary classification model on each image. To solve this model, we utilize amortized variational inference to approximate the intractable GP posterior in a data-driven manner and then decouple the approximated GP posterior into double space forms for efficient sampling with linear complexity. Then, we correspondingly construct a GP classification framework, named GPCIS, which is integrated with the deep kernel learning mechanism for more flexibility. The main specificities of the proposed GPCIS lie in: 1) Under the explicit guidance of the derived GP posterior, the information contained in clicks can be finely propagated to the entire image and then boost the segmentation; 2) The accuracy of predictions at clicks has good theoretical support. These merits of GPCIS as well as its good generality and high efficiency are substantiated by comprehensive experiments on several benchmarks, as compared with representative methods both quantitatively and qualitatively.
Biophilia is an innate love for living things and nature itself that has been associated with a positive impact on mental health and well-being. This study explores the application of deep learning methods for the classification of Biophilic artwork, in order to learn and explain the different Biophilic characteristics present in a visual representation of a painting. Using the concept of Biophilia that postulates the deep connection of human beings with nature, we use an artificially intelligent algorithm to recognise the different patterns underlying the Biophilic features in an artwork. Our proposed method uses a lower-dimensional representation of an image and a decoder model to extract salient features of the image of each Biophilic trait, such as plants, water bodies, seasons, animals, etc., based on learnt factors such as shape, texture, and illumination. The proposed classification model is capable of extracting Biophilic artwork that not only helps artists, collectors, and researchers studying to interpret and exploit the effects of mental well-being on exposure to nature-inspired visual aesthetics but also enables a methodical exploration of the study of Biophilia and Biophilic artwork for aesthetic preferences. Using the proposed algorithms, we have also created a gallery of Biophilic collections comprising famous artworks from different European and American art galleries, which will soon be published on the Vieunite@ online community.
Objective: Radiotherapy uses precise doses of radiation to treat cancer, requiring accurate verification, e.g. using the Electronic Portal Imaging Device (EPID), to guide treatment. To develop an effective artificial intelligence (AI) model for error detection and treatment verification, a large and well-annotated dataset of EPID images is needed, however, acquiring such high quality real data is difficult. While synthetic EPID data could be a viable alternative, it is critical to ensure that this data is as realistic as possible to effectively train an accurate and reliable AI model. The measurement uncertainty that is not modeled in EPID predictions but is present on real measured EPID images can hinder downstream tasks such as error detection and classification. Our research aims to improve synthetic EPID data through image-to-image (I2I) translation based on deep generative modeling. Approach: A dataset of 989 predicted EPID images and corresponding measured EPID images was used. We evaluate both paired and unpaired generative modeling approaches for this task. For the former, we introduce a novel modification of Variational Autoencoder (VAE) to I2I, a method that, to the best of our knowledge, has not been previously explored for this task. For the latter, we use UNsupervised Image-to-Image Translation Networks (UNIT). Results: Our results show that both models achieved some degree of I2I translation, with our novel modification of the VAE model outperforming the UNIT model in improving key metrics (mean absolute error: 4.1 cGy vs 6.4 cGy; relative dose difference in-field: 2.5% vs 5.5%; absolute dose difference in-field: 5.3 cGy vs 10.8 cGy). Significance: This enhanced synthetic data is expected to improve downstream tasks such as training neural networks for automated error detection and error classification in radiotherapy.
Noise is an important factor which when get added to an image reduces its quality and appearance. So in order to enhance the image qualities, it has to be removed with preserving the textural information and structural features of image. There are different types of noises exist who corrupt the images. Selection of the denoising algorithm is application dependent. Hence, it is necessary to have knowledge about the noise present in the image so as to select the appropriate denoising algorithm. Objective of this paper is to present brief account on types of noises, its types and different noise removal algorithms. In the first section types of noises on the basis of their additive and multiplicative nature are being discussed. In second section a precise classification and analysis of the different potential image denoising algorithm is presented. At the end of paper, a comparative study of all these algorithms in context of performance evaluation is done and concluded with several promising directions for future research work.
Utilization of classification latent space information for downstream reconstruction and generation is an intriguing and a relatively unexplored area. In general, discriminative representations are rich in class-specific features but are too sparse for reconstruction, whereas, in autoencoders the representations are dense but have limited indistinguishable class-specific features, making them less suitable for classification. In this work, we propose a discriminative modeling framework that employs manipulated supervised latent representations to reconstruct and generate new samples belonging to a given class. Unlike generative modeling approaches such as GANs and VAEs that aim to model the data manifold distribution, Representation based Generations (ReGene) directly represent the given data manifold in the classification space. Such supervised representations, under certain constraints, allow for reconstructions and controlled generations using an appropriate decoder without enforcing any prior distribution. Theoretically, given a class, we show that these representations when smartly manipulated using convex combinations retain the same class label. Furthermore, they also lead to the novel generation of visually realistic images. Extensive experiments on datasets of varying resolutions demonstrate that ReGene has higher classification accuracy than existing conditional generative models while being competitive in terms of FID.
Although large language models (LLMs) have demonstrated remarkable capabilities in recent years, the potential of information theory (IT) to enhance LLM development remains underexplored. This paper introduces the information theoretic principle of Conditional Mutual Information (CMI) to LLM fine-tuning for classification tasks, exploring its promise in two main ways: minimizing CMI to improve a model's standalone performance and maximizing CMI to enhance knowledge distillation (KD) for more capable student models. To apply CMI in LLM fine-tuning, we adapt the recently proposed CMI-constrained deep learning framework, which was initially developed for image classification, with some modification. By minimizing CMI during LLM fine-tuning, we achieve superior performance gains on 6 of 8 GLUE classification tasks compared to BERT. Additionally, maximizing CMI during the KD process results in significant performance improvements in 6 of 8 GLUE classification tasks compared to DistilBERT. These findings demonstrate CMI's adaptability for optimizing both standalone LLMs and student models, showcasing its potential as a robust framework for advancing LLM fine-tuning. Our work bridges the gap between information theory and LLM development, offering new insights for building high-performing language models.