Related papers: MixDiff: Mixing Natural and Synthetic Images for R…

Deep learning models have demonstrated remarkable performance across various computer vision tasks, yet their vulnerability to distribution shifts remains a critical challenge. Despite sophisticated neural network architectures, existing…

Faithful image super-resolution (SR) not only needs to recover images that appear realistic, similar to image generation tasks, but also requires that the restored images maintain fidelity and structural consistency with the input. To this…

Recently proposed consistency-based Semi-Supervised Learning (SSL) methods such as the $\Pi$-model, temporal ensembling, the mean teacher, or the virtual adversarial training, have advanced the state of the art in several SSL tasks. These…

We study the relative effects of data augmentations, pretraining algorithms, and model architectures in Self-Supervised Learning (SSL). While the recent literature in this space leaves the impression that the pretraining algorithm is of…

Data augmentation techniques, such as simple image transformations and combinations, are highly effective at improving the generalization of computer vision models, especially when training data is limited. However, such techniques are…

Self-supervised learning (SSL) has emerged as a powerful approach for learning visual representations without manual annotations. However, the robustness of standard SSL methods to domain shift -- systematic differences across data sources…

Medical image segmentation suffers from data scarcity, particularly in polyp detection where annotation requires specialized expertise. We present SynDiff, a framework combining text-guided synthetic data generation with efficient…

Contrastive self supervised learning(CSSL) usually makes use of the multi-view assumption which states that all relevant information must be shared between all views. The main objective of CSSL is to maximize the mutual information(MI)…

Semi-supervised learning (SSL) has seen great strides when labeled data is scarce but unlabeled data is abundant. Critically, most recent work assume that such unlabeled data is drawn from the same distribution as the labeled data. In this…

Conventional methods in semi-supervised learning (SSL) often face challenges related to limited data utilization, mainly due to their reliance on threshold-based techniques for selecting high-confidence unlabeled data during training.…

Self-supervised learning (SSL) has gained remarkable success, for which contrastive learning (CL) plays a key role. However, the recent development of new non-CL frameworks has achieved comparable or better performance with high improvement…

Training learning-based deblurring methods demands a tremendous amount of blurred and sharp image pairs. Unfortunately, existing synthetic datasets are not realistic enough, and deblurring models trained on them cannot handle real blurred…

Deep learning has demonstrated its power in image rectification by leveraging the representation capacity of deep neural networks via supervised training based on a large-scale synthetic dataset. However, the model may overfit the synthetic…

Deep architecture have proven capable of solving many tasks provided a sufficient amount of labeled data. In fact, the amount of available labeled data has become the principal bottleneck in low label settings such as Semi-Supervised…

Paired image-text data with subtle variations in-between (e.g., people holding surfboards vs. people holding shovels) hold the promise of producing Vision-Language Models with proper compositional understanding. Synthesizing such training…

Semi-supervised Learning (SSL) has witnessed great success owing to the impressive performances brought by various methods based on pseudo labeling and consistency regularization. However, we argue that existing methods might fail to…

The effectiveness of Contrastive Language-Image Pre-training (CLIP) models critically depends on the semantic diversity and quality of their training data. However, while existing synthetic data generation methods primarily focus on…

Mixup data augmentation approaches have been applied for various tasks of deep learning to improve the generalization ability of deep neural networks. Some existing approaches CutMix, SaliencyMix, etc. randomly replace a patch in one image…

Image fusion is famous as an alternative solution to generate one high-quality image from multiple images in addition to image restoration from a single degraded image. The essence of image fusion is to integrate complementary information…

Data mixing augmentation has proved effective in training deep models. Recent methods mix labels mainly based on the mixture proportion of image pixels. As the main discriminative information of a fine-grained image usually resides in…