Related papers: Corrupted Image Modeling for Self-Supervised Visua…

Pre-training general-purpose visual features with convolutional neural networks without relying on annotations is a challenging and important task. Most recent efforts in unsupervised feature learning have focused on either small or highly…

Medical image segmentation remains a formidable challenge due to the label scarcity. Pre-training Vision Transformer (ViT) through masked image modeling (MIM) on large-scale unlabeled medical datasets presents a promising solution,…

In this work, we dive deep into the impact of additive noise in pre-training deep networks. While various methods have attempted to use additive noise inspired by the success of latent denoising diffusion models, when used in combination…

In supervised learning, traditional image masking faces two key issues: (i) discarded pixels are underutilized, leading to a loss of valuable contextual information; (ii) masking may remove small or critical features, especially in…

The Vision Transformer (ViT) has demonstrated remarkable performance in Self-Supervised Learning (SSL) for 3D medical image analysis. Masked AutoEncoder (MAE) for feature pre-training can further unleash the potential of ViT on various…

In modern machine learning, the trend of harnessing self-supervised learning to derive high-quality representations without label dependency has garnered significant attention. However, the absence of label information, coupled with the…

Real-world low-light images captured by imaging devices suffer from poor visibility and require a domain-specific enhancement to produce artifact-free outputs that reveal details. In this paper, we propose an unpaired low-light image…

We study a new family of inverse problems for recovering representations of corrupted data. We assume access to a pre-trained representation learning network R(x) that operates on clean images, like CLIP. The problem is to recover the…

In the realm of self-supervised learning (SSL), masked image modeling (MIM) has gained popularity alongside contrastive learning methods. MIM involves reconstructing masked regions of input images using their unmasked portions. A notable…

Composed Image Retrieval (CIR) uses a reference image and a modification text as a query to retrieve a target image satisfying the requirement of ``modifying the reference image according to the text instructions''. However, existing CIR…

Deep networks are increasingly being applied to problems involving image synthesis, e.g., generating images from textual descriptions and reconstructing an input image from a compact representation. Supervised training of image-synthesis…

Composed Image Retrieval (CIR) is a challenging image retrieval paradigm. It aims to retrieve target images from large-scale image databases that are consistent with the modification semantics, based on a multimodal query composed of a…

Traditional model-based image reconstruction (MBIR) methods combine forward and noise models with simple object priors. Recent application of deep learning methods for image reconstruction provides a successful data-driven approach to…

In this work we investigate the use of deep learning for distortion-generic blind image quality assessment. We report on different design choices, ranging from the use of features extracted from pre-trained Convolutional Neural Networks…

Recently, zero-shot image captioning has gained increasing attention, where only text data is available for training. The remarkable progress in text-to-image diffusion model presents the potential to resolve this task by employing…

Intrinsic image decomposition (IID) is an under-constrained problem. Therefore, traditional approaches use hand crafted priors to constrain the problem. However, these constraints are limited when coping with complex scenes. Deep…

Masking strategies commonly employed in natural language processing are still underexplored in vision tasks such as concept learning, where conventional methods typically rely on full images. However, using masked images diversifies…

Remote sensing images are used for a variety of analyses, from agricultural monitoring, to disaster relief, to resource planning, among others. The images can be corrupted due to a number of reasons, including instrument errors and natural…

An important goal of self-supervised learning is to enable model pre-training to benefit from almost unlimited data. However, one method that has recently become popular, namely masked image modeling (MIM), is suspected to be unable to…

Blind Compressed Image Restoration (CIR) has garnered significant attention due to its practical applications. It aims to mitigate compression artifacts caused by unknown quality factors, particularly with JPEG codecs. Existing works on…