arXiv subjects

Computer vision

Explore arXiv computer-vision papers and cs.CV metadata. Search within the index for image segmentation, object detection and visual representation learning.

Follow this topic with RSS

At least 55 records · Page 3Linked to original sources

arXiv2018

KonIQ-10k: Towards an ecologically valid and large-scale IQA database

The main challenge in applying state-of-the-art deep learning methods to predict image quality in-the-wild is the relatively small size of existing quality scored datasets. The reason for the lack of larger datasets is the massive resources required in generating diverse and publishable content. We present a new systematic and scalable approach to create large-scale, authentic and diverse image datasets for Image Quality Assessment (IQA). We show how we built an IQA database, KonIQ-10k, consisting of 10,073 images, on which we performed very large scale crowdsourcing experiments in order to obtain reliable quality ratings from 1,467 crowd workers (1.2 million ratings). We argue for its ecological validity by analyzing the diversity of the dataset, by comparing it to state-of-the-art IQA databases, and by checking the reliability of our user studies.

cs.CV↗

arXiv2024

Tracking Passengers and Baggage Items Using Multiple Overhead Cameras at Security Checkpoints

We introduce a novel framework to track multiple objects in overhead camera videos for airport checkpoint security scenarios where targets correspond to passengers and their baggage items. We propose a self-supervised learning (SSL) technique to provide the model information about instance segmentation uncertainty from overhead images. Our SSL approach improves object detection by employing a test-time data augmentation and a regression-based, rotation-invariant pseudo-label refinement technique. Our pseudo-label generation method provides multiple geometrically transformed images as inputs to a convolutional neural network (CNN), regresses the augmented detections generated by the network to reduce localization errors, and then clusters them using the mean-shift algorithm. The self-supervised detector model is used in a single-camera tracking algorithm to generate temporal identifiers for the targets. Our method also incorporates a multiview trajectory association mechanism to maintain consistent temporal identifiers as passengers travel across camera views. An evaluation of detection, tracking, and association performances on videos obtained from multiple overhead cameras in a realistic airport checkpoint environment demonstrates the effectiveness of the proposed approach. Our results show that self-supervision improves object detection accuracy by up to 42% without increasing the inference time of the model. Our multicamera association method achieves up to 89% multiobject tracking accuracy with an average computation time of less than 15 ms.

cs.CV↗

arXiv2019

Texture Synthesis Guided Deep Hashing for Texture Image Retrieval

With the large-scale explosion of images and videos over the internet, efficient hashing methods have been developed to facilitate memory and time efficient retrieval of similar images. However, none of the existing works uses hashing to address texture image retrieval mostly because of the lack of sufficiently large texture image databases. Our work addresses this problem by developing a novel deep learning architecture that generates binary hash codes for input texture images. For this, we first pre-train a Texture Synthesis Network (TSN) which takes a texture patch as input and outputs an enlarged view of the texture by injecting newer texture content. Thus it signifies that the TSN encodes the learnt texture specific information in its intermediate layers. In the next stage, a second network gathers the multi-scale feature representations from the TSN's intermediate layers using channel-wise attention, combines them in a progressive manner to a dense continuous representation which is finally converted into a binary hash code with the help of individual and pairwise label information. The new enlarged texture patches also help in data augmentation to alleviate the problem of insufficient texture data and are used to train the second stage of the network. Experiments on three public texture image retrieval datasets indicate the superiority of our texture synthesis guided hashing approach over current state-of-the-art methods.

cs.CV↗

arXiv2021

Disparities in Dermatology AI: Assessments Using Diverse Clinical Images

More than 3 billion people lack access to care for skin disease. AI diagnostic tools may aid in early skin cancer detection; however most models have not been assessed on images of diverse skin tones or uncommon diseases. To address this, we curated the Diverse Dermatology Images (DDI) dataset - the first publicly available, pathologically confirmed images featuring diverse skin tones. We show that state-of-the-art dermatology AI models perform substantially worse on DDI, with ROC-AUC dropping 29-40 percent compared to the models' original results. We find that dark skin tones and uncommon diseases, which are well represented in the DDI dataset, lead to performance drop-offs. Additionally, we show that state-of-the-art robust training methods cannot correct for these biases without diverse training data. Our findings identify important weaknesses and biases in dermatology AI that need to be addressed to ensure reliable application to diverse patients and across all disease.

eess.IV↗

arXiv2025

LapisGS: Layered Progressive 3D Gaussian Splatting for Adaptive Streaming

The rise of Extended Reality (XR) requires efficient streaming of 3D online worlds, challenging current 3DGS representations to adapt to bandwidth-constrained environments. This paper proposes LapisGS, a layered 3DGS that supports adaptive streaming and progressive rendering. Our method constructs a layered structure for cumulative representation, incorporates dynamic opacity optimization to maintain visual fidelity, and utilizes occupancy maps to efficiently manage Gaussian splats. This proposed model offers a progressive representation supporting a continuous rendering quality adapted for bandwidth-aware streaming. Extensive experiments validate the effectiveness of our approach in balancing visual fidelity with the compactness of the model, with up to 50.71% improvement in SSIM, 286.53% improvement in LPIPS with 23% of the original model size, and shows its potential for bandwidth-adapted 3D streaming and rendering applications.

cs.CV↗

arXiv2020

Deep learning approach to description and classification of fungi microscopic images

Diagnosis of fungal infections can rely on microscopic examination, however, in many cases, it does not allow unambiguous identification of the species due to their visual similarity. Therefore, it is usually necessary to use additional biochemical tests. That involves additional costs and extends the identification process up to 10 days. Such a delay in the implementation of targeted treatment is grave in consequences as the mortality rate for immunosuppressed patients is high. In this paper, we apply machine learning approach based on deep learning and bag-of-words to classify microscopic images of various fungi species. Our approach makes the last stage of biochemical identification redundant, shortening the identification process by 2-3 days and reducing the cost of the diagnostic examination.

cs.CV↗

arXiv2021

Consensual Collaborative Training And Knowledge Distillation Based Facial Expression Recognition Under Noisy Annotations

Presence of noise in the labels of large scale facial expression datasets has been a key challenge towards Facial Expression Recognition (FER) in the wild. During early learning stage, deep networks fit on clean data. Then, eventually, they start overfitting on noisy labels due to their memorization ability, which limits FER performance. This work proposes an effective training strategy in the presence of noisy labels, called as Consensual Collaborative Training (CCT) framework. CCT co-trains three networks jointly using a convex combination of supervision loss and consistency loss, without making any assumption about the noise distribution. A dynamic transition mechanism is used to move from supervision loss in early learning to consistency loss for consensus of predictions among networks in the later stage. Inference is done using a single network based on a simple knowledge distillation scheme. Effectiveness of the proposed framework is demonstrated on synthetic as well as real noisy FER datasets. In addition, a large test subset of around 5K images is annotated from the FEC dataset using crowd wisdom of 16 different annotators and reliable labels are inferred. CCT is also validated on it. State-of-the-art performance is reported on the benchmark FER datasets RAFDB (90.84%) FERPlus (89.99%) and AffectNet (66%). Our codes are available at https://github.com/1980x/CCT.

cs.CV↗

arXiv2024

Mitigating Open-Vocabulary Caption Hallucinations

While recent years have seen rapid progress in image-conditioned text generation, image captioning still suffers from the fundamental issue of hallucinations, namely, the generation of spurious details that cannot be inferred from the given image. Existing methods largely use closed-vocabulary object lists to mitigate or evaluate hallucinations in image captioning, ignoring the long-tailed nature of hallucinations that occur in practice. To this end, we propose a framework for addressing hallucinations in image captioning in the open-vocabulary setting. Our framework includes a new benchmark, OpenCHAIR, that leverages generative foundation models to evaluate open-vocabulary object hallucinations for image captioning, surpassing the popular and similarly-sized CHAIR benchmark in both diversity and accuracy. Furthermore, to mitigate open-vocabulary hallucinations without using a closed object list, we propose MOCHa, an approach harnessing advancements in reinforcement learning. Our multi-objective reward function explicitly targets the trade-off between fidelity and adequacy in generations without requiring any strong supervision. MOCHa improves a large variety of image captioning models, as captured by our OpenCHAIR benchmark and other existing metrics. Code and models can be found at: https://github.com/assafbk/mocha_code

cs.CV↗

arXiv2020

Beyond Product Quantization: Deep Progressive Quantization for Image Retrieval

Product Quantization (PQ) has long been a mainstream for generating an exponentially large codebook at very low memory/time cost. Despite its success, PQ is still tricky for the decomposition of high-dimensional vector space, and the retraining of model is usually unavoidable when the code length changes. In this work, we propose a deep progressive quantization (DPQ) model, as an alternative to PQ, for large scale image retrieval. DPQ learns the quantization codes sequentially and approximates the original feature space progressively. Therefore, we can train the quantization codes with different code lengths simultaneously. Specifically, we first utilize the label information for guiding the learning of visual features, and then apply several quantization blocks to progressively approach the visual features. Each quantization block is designed to be a layer of a convolutional neural network, and the whole framework can be trained in an end-to-end manner. Experimental results on the benchmark datasets show that our model significantly outperforms the state-of-the-art for image retrieval. Our model is trained once for different code lengths and therefore requires less computation time. Additional ablation study demonstrates the effect of each component of our proposed model. Our code is released at https://github.com/cfm-uestc/DPQ.

cs.CV↗

arXiv2021

A Novel Interaction-based Methodology Towards Explainable AI with Better Understanding of Pneumonia Chest X-ray Images

In the field of eXplainable AI (XAI), robust "blackbox" algorithms such as Convolutional Neural Networks (CNNs) are known for making high prediction performance. However, the ability to explain and interpret these algorithms still require innovation in the understanding of influential and, more importantly, explainable features that directly or indirectly impact the performance of predictivity. A number of methods existing in literature focus on visualization techniques but the concepts of explainability and interpretability still require rigorous definition. In view of the above needs, this paper proposes an interaction-based methodology -- Influence Score (I-score) -- to screen out the noisy and non-informative variables in the images hence it nourishes an environment with explainable and interpretable features that are directly associated to feature predictivity. We apply the proposed method on a real world application in Pneumonia Chest X-ray Image data set and produced state-of-the-art results. We demonstrate how to apply the proposed approach for more general big data problems by improving the explainability and interpretability without sacrificing the prediction performance. The contribution of this paper opens a novel angle that moves the community closer to the future pipelines of XAI problems.

cs.LG↗

arXiv2021

Beyond Cats and Dogs: Semi-supervised Classification of fuzzy labels with overclustering

A long-standing issue with deep learning is the need for large and consistently labeled datasets. Although the current research in semi-supervised learning can decrease the required amount of annotated data by a factor of 10 or even more, this line of research still uses distinct classes like cats and dogs. However, in the real-world we often encounter problems where different experts have different opinions, thus producing fuzzy labels. We propose a novel framework for handling semi-supervised classifications of such fuzzy labels. Our framework is based on the idea of overclustering to detect substructures in these fuzzy labels. We propose a novel loss to improve the overclustering capability of our framework and show on the common image classification dataset STL-10 that it is faster and has better overclustering performance than previous work. On a real-world plankton dataset, we illustrate the benefit of overclustering for fuzzy labels and show that we beat previous state-of-the-art semisupervised methods. Moreover, we acquire 5 to 10% more consistent predictions of substructures.

cs.CV↗

arXiv2022

A Review of Deep Transfer Learning and Recent Advancements

Deep learning has been the answer to many machine learning problems during the past two decades. However, it comes with two major constraints: dependency on extensive labeled data and training costs. Transfer learning in deep learning, known as Deep Transfer Learning (DTL), attempts to reduce such dependency and costs by reusing an obtained knowledge from a source data/task in training on a target data/task. Most applied DTL techniques are network/model-based approaches. These methods reduce the dependency of deep learning models on extensive training data and drastically decrease training costs. As a result, researchers detected Covid-19 infection on chest X-Rays with high accuracy at the beginning of the pandemic with minimal data using DTL techniques. Also, the training cost reduction makes DTL viable on edge devices with limited resources. Like any new advancement, DTL methods have their own limitations, and a successful transfer depends on some adjustments for different scenarios. In this paper, we review the definition and taxonomy of deep transfer learning and well-known methods. Then we investigate the DTL approaches by reviewing recent applied DTL techniques in the past five years. Further, we review some experimental analyses of DTLs to learn the best practice for applying DTL in different scenarios. Moreover, the limitations of DTLs (catastrophic forgetting dilemma and overly biased pre-trained models) are discussed, along with possible solutions and research trends.

cs.LG↗

arXiv2010

Biometric Authentication using Nonparametric Methods

The physiological and behavioral trait is employed to develop biometric authentication systems. The proposed work deals with the authentication of iris and signature based on minimum variance criteria. The iris patterns are preprocessed based on area of the connected components. The segmented image used for authentication consists of the region with large variations in the gray level values. The image region is split into quadtree components. The components with minimum variance are determined from the training samples. Hu moments are applied on the components. The summation of moment values corresponding to minimum variance components are provided as input vector to k-means and fuzzy kmeans classifiers. The best performance was obtained for MMU database consisting of 45 subjects. The number of subjects with zero False Rejection Rate [FRR] was 44 and number of subjects with zero False Acceptance Rate [FAR] was 45. This paper addresses the computational load reduction in off-line signature verification based on minimal features using k-means, fuzzy k-means, k-nn, fuzzy k-nn and novel average-max approaches. FRR of 8.13% and FAR of 10% was achieved using k-nn classifier. The signature is a biometric, where variations in a genuine case, is a natural expectation. In the genuine signature, certain parts of signature vary from one instance to another. The system aims to provide simple, fast and robust system using less number of features when compared to state of art works.

cs.CV↗

arXiv2013

Robust Hyperspectral Unmixing with Correntropy based Metric

Hyperspectral unmixing is one of the crucial steps for many hyperspectral applications. The problem of hyperspectral unmixing has proven to be a difficult task in unsupervised work settings where the endmembers and abundances are both unknown. What is more, this task becomes more challenging in the case that the spectral bands are degraded with noise. This paper presents a robust model for unsupervised hyperspectral unmixing. Specifically, our model is developed with the correntropy based metric where the non-negative constraints on both endmembers and abundances are imposed to keep physical significance. In addition, a sparsity prior is explicitly formulated to constrain the distribution of the abundances of each endmember. To solve our model, a half-quadratic optimization technique is developed to convert the original complex optimization problem into an iteratively re-weighted NMF with sparsity constraints. As a result, the optimization of our model can adaptively assign small weights to noisy bands and give more emphasis on noise-free bands. In addition, with sparsity constraints, our model can naturally generate sparse abundances. Experiments on synthetic and real data demonstrate the effectiveness of our model in comparison to the related state-of-the-art unmixing models.

cs.CV↗

arXiv2013

Image Inpainting by Kriging Interpolation Technique

Image inpainting is the art of predicting damaged regions of an image. The manual way of image inpainting is a time consuming. Therefore, there must be an automatic digital method for image inpainting that recovers the image from the damaged regions. In this paper, a novel statistical image inpainting algorithm based on Kriging interpolation technique was proposed. Kriging technique automatically fills the damaged region in an image using the information available from its surrounding regions in such away that it uses the spatial correlation structure of points inside the k-by-k block. Kriging has the ability to face the challenge of keeping the structure and texture information as the size of damaged region heighten. Experimental results showed that, Kriging has a high PSNR value when recovering a variety of test images from scratches and text as damaged regions.

cs.CV↗

arXiv2013

An Analysis of the Connections Between Layers of Deep Neural Networks

We present an analysis of different techniques for selecting the connection be- tween layers of deep neural networks. Traditional deep neural networks use ran- dom connection tables between layers to keep the number of connections small and tune to different image features. This kind of connection performs adequately in supervised deep networks because their values are refined during the training. On the other hand, in unsupervised learning, one cannot rely on back-propagation techniques to learn the connections between layers. In this work, we tested four different techniques for connecting the first layer of the network to the second layer on the CIFAR and SVHN datasets and showed that the accuracy can be im- proved up to 3% depending on the technique used. We also showed that learning the connections based on the co-occurrences of the features does not confer an advantage over a random connection table in small networks. This work is helpful to improve the efficiency of connections between the layers of unsupervised deep neural networks.

cs.CV↗

arXiv2013

Using a bag of Words for Automatic Medical Image Annotation with a Latent Semantic

We present in this paper a new approach for the automatic annotation of medical images, using the approach of "bag-of-words" to represent the visual content of the medical image combined with text descriptors based approach tf.idf and reduced by latent semantic to extract the co-occurrence between terms and visual terms. A medical report is composed of a text describing a medical image. First, we are interested to index the text and extract all relevant terms using a thesaurus containing MeSH medical concepts. In a second phase, the medical image is indexed while recovering areas of interest which are invariant to change in scale, light and tilt. To annotate a new medical image, we use the approach of "bagof-words" to recover the feature vector. Indeed, we use the vector space model to retrieve similar medical image from the database training. The calculation of the relevance value of an image to the query image is based on the cosine function. We conclude with an experiment carried out on five types of radiological imaging to evaluate the performance of our system of medical annotation. The results showed that our approach works better with more images from the radiology of the skull.

cs.IR↗

arXiv2013

Distributed Bayesian inference for consistent labeling of tracked objects in non-overlapping camera networks

One of the fundamental requirements for visual surveillance using non-overlapping camera networks is the correct labeling of tracked objects on each camera in a consistent way,in the sense that the captured tracklets, or observations in this paper, of the same object at different cameras should be assigned with the same label. In this paper, we formulate this task as a Bayesian inference problem and propose a distributed inference framework in which the posterior distribution of labeling variable corresponding to each observation, conditioned on all history appearance and spatio-temporal evidence made in the whole networks, is calculated based solely on local information processing on each camera and mutual information exchanging between neighboring cameras. In our framework, the number of objects presenting in the monitored region, i.e. the sampling space of labeling variables, does not need to be specified beforehand. Instead, it can be determined automatically on the fly. In addition, we make no assumption about the appearance distribution of a single object, but use similarity scores between appearance pairs, given by advanced object re-identification algorithm, as appearance likelihood for inference. This feature makes our method very flexible and competitive when observing condition undergoes large changes across camera views. To cope with the problem of missing detection, which is critical for distributed inference, we consider an enlarged neighborhood of each camera during inference and use a mixture model to describe the higher order spatio-temporal constraints. The robustness of the algorithm against missing detection is improved at the cost of slightly increased computation and communication burden at each camera node. Finally, we demonstrate the effectiveness of our method through experiments on an indoor Office Building dataset and an outdoor Campus Garden dataset.

cs.CV↗