相关论文: Identifying and Mitigating Model Failures through …

With the growing interest in pretrained vision-language models like CLIP, recent research has focused on adapting these models to downstream tasks. Despite achieving promising results, most existing methods require labeled data for all…

Scene text detection techniques have garnered significant attention due to their wide-ranging applications. However, existing methods have a high demand for training data, and obtaining accurate human annotations is labor-intensive and…

We tackle the common challenge of inter-concept visual confusion in compositional concept generation using text-guided diffusion models (TGDMs). It becomes even more pronounced in the generation of customized concepts, due to the scarcity…

The application of zero-shot learning in computer vision has been revolutionized by the use of image-text matching models. The most notable example, CLIP, has been widely used for both zero-shot classification and guiding generative models…

Foundation models (FMs) such as CLIP have demonstrated impressive zero-shot performance across various tasks by leveraging large-scale, unsupervised pre-training. However, they often inherit harmful or unwanted knowledge from noisy…

Few-shot segmentation remains challenging due to the limitations of its labeling information for unseen classes. Most previous approaches rely on extracting high-level feature maps from the frozen visual encoder to compute the pixel-wise…

Developing effective visual inspection models remains challenging due to the scarcity of defect data. While image generation models have been used to synthesize defect images, producing highly realistic defects remains difficult. We propose…

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…

Deep graph generative modeling has gained enormous attraction in recent years due to its impressive ability to directly learn the underlying hidden graph distribution. Despite their initial success, these techniques, like much of the…

Diffusion models have demonstrated their capability to synthesize high-quality and diverse images from textual prompts. However, simultaneous control over both global contexts (e.g., object layouts and interactions) and local details (e.g.,…

Deep learning is providing a wealth of new approaches to the problem of novel view synthesis, from Neural Radiance Field (NeRF) based approaches to end-to-end style architectures. Each approach offers specific strengths but also comes with…

The astonishing growth of generative tools in recent years has empowered many exciting applications in text-to-image generation and text-to-video generation. The underlying principle behind these generative tools is the concept of…

Generative models, particularly diffusion models, have made significant success in data synthesis across various modalities, including images, videos, and 3D assets. However, current diffusion models are computationally intensive, often…

Given a query from one modality, few-shot cross-modal retrieval (CMR) retrieves semantically similar instances in another modality with the target domain including classes that are disjoint from the source domain. Compared with classical…

Diffusion models have been successfully adapted to text generation tasks by mapping the discrete text into the continuous space. However, there exist nonnegligible gaps between training and inference, owing to the absence of the forward…

Diffusion models, a family of generative models based on deep learning, have become increasingly prominent in cutting-edge machine learning research. With a distinguished performance in generating samples that resemble the observed data,…

Visual language models like Contrastive Language-Image Pretraining (CLIP) have shown impressive performance in analyzing natural images with language information. However, these models often encounter challenges when applied to specialized…

Deep generative models produce data according to a learned representation, e.g. diffusion models, through a process of approximation computing possible samples. Approximation can be understood as reconstruction and the large datasets used…

Deep learning models for visual recognition often exhibit systematic errors due to underrepresented semantic subpopulations. Although existing debugging frameworks can pinpoint these failures by identifying key failure attributes, repairing…

Infrared imagery enables temperature-based scene understanding using passive sensors, particularly under conditions of low visibility where traditional RGB imaging fails. Yet, developing downstream vision models for infrared applications is…