Related papers: D3G: Diverse Demographic Data Generation Increases…

AI in dermatology is evolving at a rapid pace but the major limitation to training trustworthy classifiers is the scarcity of data with ground-truth concept level labels, which are meta-labels semantically meaningful to humans. Foundation…

Personalized image generation aims to integrate user-provided concepts into text-to-image models, enabling the generation of customized content based on a given prompt. Recent zero-shot approaches, particularly those leveraging diffusion…

One challenge in text-to-image (T2I) generation is the inadvertent reflection of culture gaps present in the training data, which signifies the disparity in generated image quality when the cultural elements of the input text are rarely…

Deep Learning (DL) is undergoing a paradigm shift with the emergence of foundation models. In this work, we focus on Contrastive Language-Image Pre-training (CLIP), a Vision-Language foundation model that achieves high accuracy across…

Labeling large image datasets with attributes such as facial age or object type is tedious and sometimes infeasible. Supervised machine learning methods provide a highly accurate solution, but require manual labels which are often…

This study proposes a method for imbalanced data classification based on deep probabilistic graphical models (DPGMs) to solve the problem that traditional methods have insufficient learning ability for minority class samples. To address the…

Label estimation is an important component in an unsupervised person re-identification (re-ID) system. This paper focuses on cross-camera label estimation, which can be subsequently used in feature learning to learn robust re-ID models.…

Robust generalization to new concepts has long remained a distinctive feature of human intelligence. However, recent progress in deep generative models has now led to neural architectures capable of synthesizing novel instances of unknown…

Diffusion models (DMs) have become dominant in visual generation but suffer performance drop when tested on resolutions that differ from the training scale, whether lower or higher. In fact, the key challenge in generating variable-scale…

Contrastive language-image pre-training (CLIP) has demonstrated remarkable zero-shot classification ability, namely image classification using novel text labels. Existing works have attempted to enhance CLIP by fine-tuning on downstream…

Learning-based image matching critically depends on large-scale, diverse, and geometrically accurate training data. 3D Gaussian Splatting (3DGS) enables photorealistic novel-view synthesis and thus is attractive for data generation.…

A variety of real-world tasks involve the classification of images into pre-determined categories. Designing image classification algorithms that exhibit robustness to acquisition noise and image distortions, particularly when the available…

With the success of image generation, generative diffusion models are increasingly adopted for discriminative tasks, as pixel generation provides a unified perception interface. However, directly repurposing the generative denoising process…

Image classification serves as the cornerstone of computer vision, traditionally achieved through discriminative models based on deep neural networks. Recent advancements have introduced classification methods derived from generative…

Recent studies emphasize the crucial role of data augmentation in enhancing the performance of object detection models. However,existing methodologies often struggle to effectively harmonize dataset diversity with semantic coordination.To…

Pre-training backbone networks on a general annotated dataset (e.g., ImageNet) that comprises numerous manually collected images with category annotations has proven to be indispensable for enhancing the generalization capacity of…

Open-vocabulary 3D Scene Graph (3DSG) can enhance various downstream tasks in robotics by leveraging structured semantic representations, yet current 3DSG construction methods suffer from semantic inconsistencies caused by noisy cross-image…

Interstitial lung diseases (ILD) present diagnostic challenges due to their varied manifestations and overlapping imaging features. To address this, we propose a machine learning approach that utilizes CLIP, a multimodal (image and text)…

Generating accurate 3D models is a challenging problem that traditionally requires explicit learning from 3D datasets using supervised learning. Although recent advances have shown promise in learning 3D models from 2D images, these methods…

We propose a text-to-image generation algorithm based on deep neural networks when text captions for images are unavailable during training. In this work, instead of simply generating pseudo-ground-truth sentences of training images using…