Related papers: DiffAug: Enhance Unsupervised Contrastive Learning…

Recent literature in self-supervised has demonstrated significant progress in closing the gap between supervised and unsupervised methods in the image and text domains. These methods rely on domain-specific augmentations that are not…

Conditional diffusion models have exhibited superior performance in high-fidelity text-guided visual generation and editing. Nevertheless, prevailing text-guided visual diffusion models primarily focus on incorporating text-visual…

Semi-supervised learning utilizes insights from unlabeled data to improve model generalization, thereby reducing reliance on large labeled datasets. Most existing studies focus on limited samples and fail to capture the overall data…

Self-supervised learning for time-series representation aims to reduce reliance on labeled data while maintaining strong downstream performance, yet many existing approaches incur high computational costs or rely on assumptions that do not…

Retrieval-based conversational systems learn to rank response candidates for a given dialogue context by computing the similarity between their vector representations. However, training on a single textual form of the multi-turn context…

Recently, conditional score-based diffusion models have gained significant attention in the field of supervised speech enhancement, yielding state-of-the-art performance. However, these methods may face challenges when generalising to…

Contrastive pretraining can substantially increase model generalisation and downstream performance. However, the quality of the learned representations is highly dependent on the data augmentation strategy applied to generate positive…

Disentangled representation learning strives to extract the intrinsic factors within observed data. Factorizing these representations in an unsupervised manner is notably challenging and usually requires tailored loss functions or specific…

Facial attribute classification relies on large-scale annotated datasets in which many traits, such as age and expression, are inherently ambiguous and continuous but are discretized into categorical labels. Annotation inconsistencies arise…

Unsupervised domain adaptation (UDA) refers to a domain adaptation framework in which a learning model is trained based on the labeled samples on the source domain and unlabeled ones in the target domain. The dominant existing methods in…

Expanding visual categorization into a novel domain without the need of extra annotation has been a long-term interest for multimedia intelligence. Previously, this challenge has been approached by unsupervised domain adaptation (UDA).…

Appearance-based gaze estimation has shown great promise in many applications by using a single general-purpose camera as the input device. However, its success is highly depending on the availability of large-scale well-annotated gaze…

Table Structure Recognition is an essential part of end-to-end tabular data extraction in document images. The recent success of deep learning model architectures in computer vision remains to be non-reflective in table structure…

Semantic segmentation requires extensive pixel-level annotation, motivating unsupervised domain adaptation (UDA) to transfer knowledge from labelled source domains to unlabelled or weakly labelled target domains. One of the most efficient…

Synthetic data generation has become an emerging tool to help improve the adversarial robustness in classification tasks since robust learning requires a significantly larger amount of training samples compared with standard classification…

We introduce Diffusion Augmented Agents (DAAG), a novel framework that leverages large language models, vision language models, and diffusion models to improve sample efficiency and transfer learning in reinforcement learning for embodied…

While diffusion models excel at generating high-quality samples, their latent variables typically lack semantic meaning and are not suitable for representation learning. Here, we propose InfoDiffusion, an algorithm that augments diffusion…

In general, an experimental environment for deep learning assumes that the training and the test dataset are sampled from the same distribution. However, in real-world situations, a difference in the distribution between two datasets,…

Unsupervised domain adaptation (UDA) aims to align the labelled source distribution with the unlabelled target distribution to obtain domain-invariant predictive models. Since cross-modality medical data exhibit significant intra and…

Semantic segmentation provides pixel-level scene understanding essential for autonomous driving and fine-grained perception tasks. However, training segmentation models requires costly, labor-intensive annotations on real-world datasets.…