相关论文: Each Attribute Matters: Contrastive Attention for …

This paper proposes a novel self-supervised based Cut-and-Paste GAN to perform foreground object segmentation and generate realistic composite images without manual annotations. We accomplish this goal by a simple yet effective…

This paper presents a whitening-based contrastive learning method for sentence embedding learning (WhitenedCSE), which combines contrastive learning with a novel shuffled group whitening. Generally, contrastive learning pulls distortions of…

Few-shot image generation aims to generate data of an unseen category based on only a few samples. Apart from basic content generation, a bunch of downstream applications hopefully benefit from this task, such as low-data detection and…

In this paper, we propose a self-supervised visual representation learning approach which involves both generative and discriminative proxies, where we focus on the former part by requiring the target network to recover the original image…

Deep neural models (e.g. Transformer) naturally learn spurious features, which create a ``shortcut'' between the labels and inputs, thus impairing the generalization and robustness. This paper advances the self-attention mechanism to its…

We present UNSEE: Unsupervised Non-Contrastive Sentence Embeddings, a novel approach that outperforms SimCSE in the Massive Text Embedding benchmark. Our exploration begins by addressing the challenge of representation collapse, a…

Generative Adversarial Networks (GANs) have been shown to produce realistically looking synthetic images with remarkable success, yet their performance seems less impressive when the training set is highly diverse. In order to provide a…

Text-to-image (T2I) diffusion models have revolutionized generative modeling by producing high-fidelity, diverse, and visually realistic images from textual prompts. Despite these advances, existing models struggle with complex prompts…

Unsupervised domain adaptation seeks to mitigate the distribution discrepancy between source and target domains, given labeled samples of the source domain and unlabeled samples of the target domain. Generative adversarial networks (GANs)…

This paper presents a new adversarial training framework for image inpainting with segmentation confusion adversarial training (SCAT) and contrastive learning. SCAT plays an adversarial game between an inpainting generator and a…

Recent works in Generative Adversarial Networks (GANs) are actively revisiting various data augmentation techniques as an effective way to prevent discriminator overfitting. It is still unclear, however, that which augmentations could…

Current text-to-image editing models often encounter challenges with smoothly manipulating multiple attributes using a single instruction. Taking inspiration from the Chain-of-Thought prompting technique utilized in language models, we…

Face frontalization provides an effective and efficient way for face data augmentation and further improves the face recognition performance in extreme pose scenario. Despite recent advances in deep learning-based face synthesis approaches,…

In this paper, we investigate the use of generative adversarial networks in the task of image generation according to subjective measures of semantic attributes. Unlike the standard (CGAN) that generates images from discrete categorical…

In the past few years, Generative Adversarial Network (GAN) became a prevalent research topic. By defining two convolutional neural networks (G-Network and D-Network) and introducing an adversarial procedure between them during the training…

This paper studies the task of matching image and sentence, where learning appropriate representations across the multi-modal data appears to be the main challenge. Unlike previous approaches that predominantly deploy symmetrical…

Contrastive Analysis VAE (CA-VAEs) is a family of Variational auto-encoders (VAEs) that aims at separating the common factors of variation between a background dataset (BG) (i.e., healthy subjects) and a target dataset (TG) (i.e., patients)…

Machine learning models are prone to adversarial attacks, where inputs can be manipulated in order to cause misclassifications. While previous research has focused on techniques like Generative Adversarial Networks (GANs), there's limited…

Deep Neural Networks have recently demonstrated promising performance in binary change detection (CD) problems in remote sensing (RS), requiring a large amount of labeled multitemporal training samples. Since collecting such data is…

One of the biggest issues facing the use of machine learning in medical imaging is the lack of availability of large, labelled datasets. The annotation of medical images is not only expensive and time consuming but also highly dependent on…