Score-based modeling through stochastic differential equations (SDEs) has provided a new perspective on diffusion models, and demonstrated superior performance on continuous data. However, the gradient of the log-likelihood function, i.e., the score function, is not properly defined for discrete spaces. This makes it non-trivial to adapt \textcolor{\cdiff}{the score-based modeling} to categorical data. In this paper, we extend diffusion models to discrete variables by introducing a stochastic jump process where the reverse process denoises via a continuous-time Markov chain. This formulation admits an analytical simulation during backward sampling. To learn the reverse process, we extend score matching to general categorical data and show that an unbiased estimator can be obtained via simple matching of the conditional marginal distributions. We demonstrate the effectiveness of the proposed method on a set of synthetic and real-world music and image benchmarks.
In this paper, we propose a combined use of transformed images and vision transformer (ViT) models transformed with a secret key. We show for the first time that models trained with plain images can be directly transformed to models trained with encrypted images on the basis of the ViT architecture, and the performance of the transformed models is the same as models trained with plain images when using test images encrypted with the key. In addition, the proposed scheme does not require any specially prepared data for training models or network modification, so it also allows us to easily update the secret key. In an experiment, the effectiveness of the proposed scheme is evaluated in terms of performance degradation and model protection performance in an image classification task on the CIFAR-10 dataset.
Image steganography is the art and science of using images as cover for covert communications. With the development of neural networks, traditional image steganography is more likely to be detected by deep learning-based steganalysis. To improve upon this, we propose image steganography network based on style transfer, and the embedding of secret messages can be disguised as image stylization. We embed secret information while transforming the content image style. In latent space, the secret information is integrated into the latent representation of the cover image to generate the stego images, which are indistinguishable from normal stylized images. It is an end-to-end unsupervised model without pre-training. Extensive experiments on the benchmark dataset demonstrate the reliability, quality and security of stego images generated by our steganographic network.
Hateful memes are a growing menace on social media. While the image and its corresponding text in a meme are related, they do not necessarily convey the same meaning when viewed individually. Hence, detecting hateful memes requires careful consideration of both visual and textual information. Multimodal pre-training can be beneficial for this task because it effectively captures the relationship between the image and the text by representing them in a similar feature space. Furthermore, it is essential to model the interactions between the image and text features through intermediate fusion. Most existing methods either employ multimodal pre-training or intermediate fusion, but not both. In this work, we propose the Hate-CLIPper architecture, which explicitly models the cross-modal interactions between the image and text representations obtained using Contrastive Language-Image Pre-training (CLIP) encoders via a feature interaction matrix (FIM). A simple classifier based on the FIM representation is able to achieve state-of-the-art performance on the Hateful Memes Challenge (HMC) dataset with an AUROC of 85.8, which even surpasses the human performance of 82.65. Experiments on other meme datasets such as Propaganda Memes and TamilMemes also demonstrate the generalizability of the proposed approach. Finally, we analyze the interpretability of the FIM representation and show that cross-modal interactions can indeed facilitate the learning of meaningful concepts. The code for this work is available at https://github.com/gokulkarthik/hateclipper.
Belief function theory, a formal framework for uncertainty analysis and multiple evidence fusion, has made significant contributions in the medical domain, especially since the development of deep learning. Medical image segmentation with belief function theory has shown significant benefits in clinical diagnosis and medical image research. In this paper, we provide a review of medical image segmentation methods using belief function theory. We classify the methods according to the fusion step and explain how information with uncertainty or imprecision is modeled and fused with belief function theory. In addition, we discuss the challenges and limitations of present belief function-based medical image segmentation and propose orientations for future research. Future research could investigate both belief function theory and deep learning to achieve more promising and reliable segmentation results.
Bangladeshi Sign Language (BdSL) - like other sign languages - is tough to learn for general people, especially when it comes to expressing letters. In this poster, we propose PerSign, a system that can reproduce a person's image by introducing sign gestures in it. We make this operation personalized, which means the generated image keeps the person's initial image profile - face, skin tone, attire, background - unchanged while altering the hand, palm, and finger positions appropriately. We use an image-to-image translation technique and build a corresponding unique dataset to accomplish the task. We believe the translated image can reduce the communication gap between signers (person who uses sign language) and non-signers without having prior knowledge of BdSL.
Image demosaicing is problem of interpolating full- resolution color images from raw sensor (color filter array) data. During last decade, deep neural networks have been widely used in image restoration, and in particular, in demosaicing, attaining significant performance improvement. In recent years, vision transformers have been designed and successfully used in various computer vision applications. One of the recent methods of image restoration based on a Swin Transformer (ST), SwinIR, demonstrates state-of-the-art performance with a smaller number of parameters than neural network-based methods. Inspired by the success of SwinIR, we propose in this paper a novel Swin Transformer-based network for image demosaicing, called RSTCANet. To extract image features, RSTCANet stacks several residual Swin Transformer Channel Attention blocks (RSTCAB), introducing the channel attention for each two successive ST blocks. Extensive experiments demonstrate that RSTCANet out- performs state-of-the-art image demosaicing methods, and has a smaller number of parameters.
Label noise is a significant obstacle in deep learning model training. It can have a considerable impact on the performance of image classification models, particularly deep neural networks, which are especially susceptible because they have a strong propensity to memorise noisy labels. In this paper, we have examined the fundamental concept underlying related label noise approaches. A transition matrix estimator has been created, and its effectiveness against the actual transition matrix has been demonstrated. In addition, we examined the label noise robustness of two convolutional neural network classifiers with LeNet and AlexNet designs. The two FashionMINIST datasets have revealed the robustness of both models. We are not efficiently able to demonstrate the influence of the transition matrix noise correction on robustness enhancements due to our inability to correctly tune the complex convolutional neural network model due to time and computing resource constraints. There is a need for additional effort to fine-tune the neural network model and explore the precision of the estimated transition model in future research.
The French National Institute of Geographical and Forest Information (IGN) has the mission to document and measure land-cover on French territory and provides referential geographical datasets, including high-resolution aerial images and topographic maps. The monitoring of land-cover plays a crucial role in land management and planning initiatives, which can have significant socio-economic and environmental impact. Together with remote sensing technologies, artificial intelligence (IA) promises to become a powerful tool in determining land-cover and its evolution. IGN is currently exploring the potential of IA in the production of high-resolution land cover maps. Notably, deep learning methods are employed to obtain a semantic segmentation of aerial images. However, territories as large as France imply heterogeneous contexts: variations in landscapes and image acquisition make it challenging to provide uniform, reliable and accurate results across all of France. The FLAIR-one dataset presented is part of the dataset currently used at IGN to establish the French national reference land cover map "Occupation du sol \`a grande \'echelle" (OCS- GE).
Passive radar has key advantages over its active counterpart in terms of cost and stealth. In this paper, we address passive radar imaging problem by interferometric inversion using a spectral estimation method with a priori information within a deep learning (DL) framework. Cross-correlating the received signals from different look directions mitigates the influence of shared transmitter related phase components despite lack of a cooperative transmitter, and permits tractable inference via interferometric inversion. We thereon leverage deep architectures for modeling a priori information and for improving sample efficiency of state-of-the-art methods. Our approach comprises of an iterative algorithm based on generalizing the power method, and applies denoisers using plug-and-play (PnP) and regularization by denoising (RED) techniques. We evaluate our approach using simulated data for passive synthetic aperture radar (SAR) by using convolutional neural networks (CNN) as denoisers. The numerical experiments show that our method can achieve faster reconstruction and superior image quality in sample starved regimes than the state-of-the-art passive interferometric imaging algorithms.