Related papers: A Modular System for Enhanced Robustness of Multim…

Multimodal semantic communication has great potential to enhance downstream task performance by integrating complementary information across modalities. This paper introduces ProMSC-MIS, a novel Prompt-based Multimodal Semantic…

Current models for point cloud recognition demonstrate promising performance on synthetic datasets. However, real-world point cloud data inevitably contains noise, impacting model robustness. While recent efforts focus on enhancing…

Human parsing aims to segment each pixel of the human image with fine-grained semantic categories. However, current human parsers trained with clean data are easily confused by numerous image corruptions such as blur and noise. To improve…

Data augmentation has been proven effective for training high-accuracy convolutional neural network classifiers by preventing overfitting. However, building deep neural networks in real-world scenarios requires not only high accuracy on…

We focus on the challenging problem of learning an unbiased classifier from a large number of potentially relevant but noisily labeled web images given only a few clean labeled images. This problem is particularly practical because it…

Deep learning is a very promising technique for low-dose computed tomography (LDCT) image denoising. However, traditional deep learning methods require paired noisy and clean datasets, which are often difficult to obtain. This paper…

We describe a novel method for training high-quality image denoising models based on unorganized collections of corrupted images. The training does not need access to clean reference images, or explicit pairs of corrupted images, and can…

Deep neural networks have proven to be highly effective when large amounts of data with clean labels are available. However, their performance degrades when training data contains noisy labels, leading to poor generalization on the test…

Data denoising is a persistent challenge across scientific and engineering domains. Real-world data is frequently corrupted by complex, non-linear noise, rendering traditional rule-based denoising methods inadequate. To overcome these…

We introduce Corrupted Image Modeling (CIM) for self-supervised visual pre-training. CIM uses an auxiliary generator with a small trainable BEiT to corrupt the input image instead of using artificial [MASK] tokens, where some patches are…

The recently advanced unsupervised learning approaches use the siamese-like framework to compare two "views" from the same image for learning representations. Making the two views distinctive is a core to guarantee that unsupervised methods…

Image-based single-modality compression learning approaches have demonstrated exceptionally powerful encoding and decoding capabilities in the past few years , but suffer from blur and severe semantics loss at extremely low bitrates. To…

For safety-critical applications such as autonomous driving, CNNs have to be robust with respect to unavoidable image corruptions, such as image noise. While previous works addressed the task of robust prediction in the context of…

Introducing training-time augmentations is a key technique to enhance generalization and prepare deep neural networks against test-time corruptions. Inspired by the success of generative diffusion models, we propose a novel approach of…

Code datasets, often collected from diverse and uncontrolled sources such as GitHub, potentially suffer from quality issues, thereby affecting the performance and training efficiency of Large Language Models (LLMs) optimized for code…

Hyperspectral image (HSI) denoising is a crucial step in enhancing the quality of HSIs. Noise modeling methods can fit noise distributions to generate synthetic HSIs to train denoising networks. However, the noise in captured HSIs is…

Multi-Modal Self-Supervised Learning from videos has been shown to improve model's performance on various downstream tasks. However, such Self-Supervised pre-training requires large batch sizes and a large amount of computation resources…

While deep neural networks have achieved remarkable performance, they tend to lack transparency in prediction. The pursuit of greater interpretability in neural networks often results in a degradation of their original performance. Some…

Medical images usually suffer from image degradation in clinical practice, leading to decreased performance of deep learning-based models. To resolve this problem, most previous works have focused on filtering out degradation-causing…

Due to numerous hardware shortcomings, medical image acquisition devices are susceptible to producing low-quality (i.e., low contrast, inappropriate brightness, noisy, etc.) images. Regrettably, perceptually degraded images directly impact…