Related papers: CustomContrast: A Multilevel Contrastive Perspecti…
Recent advances in large-scale text-to-image generation models have led to a surge in subject-driven text-to-image generation, which aims to produce customized images that align with textual descriptions while preserving the identity of…
Multimodal contrastive learning is a methodology for linking different data modalities; the canonical example is linking image and text data. The methodology is typically framed as the identification of a set of encoders, one for each…
We present a novel unsupervised domain adaptation method for semantic segmentation that generalizes a model trained with source images and corresponding ground-truth labels to a target domain. A key to domain adaptive semantic segmentation…
We present a novel unsupervised learning approach to image landmark discovery by incorporating the inter-subject landmark consistencies on facial images. This is achieved via an inter-subject mapping module that transforms original subject…
Discriminative representation is crucial for the association step in multi-object tracking. Recent work mainly utilizes features in single or neighboring frames for constructing metric loss and empowering networks to extract representation…
Consistent text-to-image (T2I) generation seeks to produce identity-preserving images of the same subject across diverse scenes, yet it often fails due to a phenomenon called identity (ID) shift. Previous methods have tackled this issue,…
Unpaired image-to-image (I2I) translation often requires to maximize the mutual information between the source and the translated images across different domains, which is critical for the generator to keep the source content and prevent it…
Recently, contrastive learning (CL) plays an important role in exploring complementary information for multi-view clustering (MVC) and has attracted increasing attention. Nevertheless, real-world multi-view data suffer from data…
Self-supervised learning (SSL) has recently become the favorite among feature learning methodologies. It is therefore appealing for domain adaptation approaches to consider incorporating SSL. The intuition is to enforce instance-level…
Fine-tuning a pre-trained Text-to-Image (T2I) model on a tailored portrait dataset is the mainstream method for text-to-portrait customization. However, existing methods often severely impact the original model's behavior (e.g., changes in…
Quantifying and evaluating image complexity can be instrumental in enhancing the performance of various computer vision tasks. Supervised learning can effectively learn image complexity features from well-annotated datasets. However,…
Contrastive vision-language models such as CLIP have demonstrated strong performance across a wide range of multimodal tasks by learning from aligned image-text pairs. However, their ability to handle complex, real-world web documents…
Visual decoding from brain signals is a key challenge at the intersection of computer vision and neuroscience, requiring methods that bridge neural representations and computational models of vision. A field-wide goal is to achieve…
Given a query composed of a reference image and a relative caption, the Composed Image Retrieval goal is to retrieve images visually similar to the reference one that integrates the modifications expressed by the caption. Given that recent…
Text-to-image diffusion models allow seamless generation of personalized images from scant reference photos. Yet, these tools, in the wrong hands, can fabricate misleading or harmful content, endangering individuals. To address this…
Large-scale text-to-image models including Stable Diffusion are capable of generating high-fidelity photorealistic portrait images. There is an active research area dedicated to personalizing these models, aiming to synthesize specific…
Personalized text-to-image (T2I) generation has emerged as a key application for creating user-specific concepts from a few reference images. The core challenge is concept disentanglement: separating the target concept from irrelevant…
An effective framework for learning 3D representations for perception tasks is distilling rich self-supervised image features via contrastive learning. However, image-to point representation learning for autonomous driving datasets faces…
Multi-subject image generation aims to synthesize user-provided subjects in a single image while preserving subject fidelity, ensuring prompt consistency, and aligning with human aesthetic preferences. Existing In-Context-Learning based…
Whilst contrastive learning yields powerful representations by matching different augmented views of the same instance, it lacks the ability to capture the similarities between different instances. One popular way to address this limitation…