Related papers: CustomContrast: A Multilevel Contrastive Perspecti…
The recent demand for customized image generation raises a need for techniques that effectively extract the common concept from small sets of images. Existing methods typically rely on additional guidance, such as text prompts or spatial…
Text-to-image (T2I) customization empowers users to adapt the T2I diffusion model to new concepts absent in the pre-training dataset. On this basis, capturing multiple new concepts from a single image has emerged as a new task, allowing the…
Predicting the neural response to natural images in the visual cortex requires extracting relevant features from the images and relating those feature to the observed responses. In this work, we optimize the feature extraction in order to…
Multi-modal contrastive learning (MMCL) has recently garnered considerable interest due to its superior performance in visual tasks, achieved by embedding multi-modal data, such as visual-language pairs. However, there still lack…
Multimodal representation learning, exemplified by multimodal contrastive learning (MMCL) using image-text pairs, aims to learn powerful representations by aligning cues across modalities. This approach relies on the core assumption that…
Image captioning, a popular topic in computer vision, has achieved substantial progress in recent years. However, the distinctiveness of natural descriptions is often overlooked in previous work. It is closely related to the quality of…
Unsupervised feature learning has made great strides with contrastive learning based on instance discrimination and invariant mapping, as benchmarked on curated class-balanced datasets. However, natural data could be highly correlated and…
Contrastive learning is a well-established paradigm in representation learning. The standard framework of contrastive learning minimizes the distance between "similar" instances and maximizes the distance between dissimilar ones in the…
Text-to-image diffusion models have shown remarkable success in generating personalized subjects based on a few reference images. However, current methods often fail when generating multiple subjects simultaneously, resulting in mixed…
With the advent of large pre-trained vision-language models such as CLIP, prompt learning methods aim to enhance the transferability of the CLIP model. They learn the prompt given few samples from the downstream task given the specific…
Recent advancements in personalizing text-to-image (T2I) diffusion models have shown the capability to generate images based on personalized visual concepts using a limited number of user-provided examples. However, these models often…
Text-to-image (T2I) customization aims to create images that embody specific visual concepts delineated in textual descriptions. However, existing works still face a main challenge, concept overfitting. To tackle this challenge, we first…
To overcome the domain gap between synthetic and real-world datasets, unsupervised domain adaptation methods have been proposed for semantic segmentation. Majority of the previous approaches have attempted to reduce the gap either at the…
The image-text retrieval task aims to retrieve relevant information from a given image or text. The main challenge is to unify multimodal representation and distinguish fine-grained differences across modalities, thereby finding similar…
Customized text-to-image generation, which synthesizes images based on user-specified concepts, has made significant progress in handling individual concepts. However, when extended to multiple concepts, existing methods often struggle with…
As a pioneering work, PointContrast conducts unsupervised 3D representation learning via leveraging contrastive learning over raw RGB-D frames and proves its effectiveness on various downstream tasks. However, the trend of large-scale…
In a surge of text-to-image (T2I) models and their customization methods that generate new images of a user-provided subject, current works focus on alleviating the costs incurred by a lengthy per-subject optimization. These zero-shot…
The evolution from Large Language Models (LLMs) to Multimodal Large Language Models (MLLMs) has spurred research into extending In-Context Learning (ICL) to its multimodal counterpart. Existing such studies have primarily concentrated on…
Most text-to-image customization techniques fine-tune models on a small set of \emph{personal concept} images captured in minimal contexts. This often results in the model becoming overfitted to these training images and unable to…
Multi-view clustering can explore common semantics from multiple views and has attracted increasing attention. However, existing works punish multiple objectives in the same feature space, where they ignore the conflict between learning…