Related papers: MindAdapter: Few-Shot Parameter-Efficient Residual…

Vision-language models such as CLIP are pretrained on large volumes of internet sourced image and text pairs, and have been shown to sometimes exhibit impressive zero- and low-shot image classification performance. However, due to their…

Zero-shot anomaly detection (ZSAD) enables anomaly detection without normal samples from target categories, addressing scenarios where task-specific training data is unavailable. However, existing ZSAD methods either neglect adaptation of…

Customized image generation, which seeks to synthesize images with consistent characters, holds significant relevance for applications such as storytelling, portrait generation, and character design. However, previous approaches have…

Adapter-based approaches have garnered attention for fine-tuning pre-trained Vision-Language Models (VLMs) on few-shot classification tasks. These methods strive to develop a lightweight module that better aligns visual and (category)…

A domain shift exists between the large-scale, internet data used to train a Vision-Language Model (VLM) and the raw image streams collected by a robot. Existing adaptation strategies require the definition of a closed-set of classes, which…

Achieving robust generalization across individuals remains a major challenge in electroencephalogram based imagined speech decoding due to substantial variability in neural activity patterns. This study examined how training dynamics and…

Large pre-trained vision-language (VL) models have shown significant promise in adapting to various downstream tasks. However, fine-tuning the entire network is challenging due to the massive number of model parameters. To address this…

Exemplar-based semantic image synthesis generates images aligned with semantic content while preserving the appearance of an exemplar. Conventional structure-guidance models like ControlNet, are limited as they rely solely on text prompts…

Current face reenactment and swapping methods mainly rely on GAN frameworks, but recent focus has shifted to pre-trained diffusion models for their superior generation capabilities. However, training these models is resource-intensive, and…

Conventional multi-source domain few-shot adaptation (MFDA) faces the challenge of further reducing the load on edge-side devices in low-resource scenarios. Considering the native language-supervised advantage of CLIP and the plug-and-play…

Continual learning with vision-language models like CLIP offers a pathway toward scalable machine learning systems by leveraging its transferable representations. Existing CLIP-based methods adapt the pre-trained image encoder by adding…

Cross-modal alignment aims to map heterogeneous modalities into a shared latent space, as exemplified by models like CLIP, which benefit from large-scale image-text pretraining for strong recognition capabilities. However, when operating in…

Multimodal brain decoding aims to reconstruct semantic information that is consistent with visual stimuli from brain activity signals such as fMRI, and then generate readable natural language descriptions. However, multimodal brain decoding…

In the personalization process of large-scale text-to-image models, overfitting often occurs when learning specific subject from a limited number of images. Existing methods, such as DreamBooth, mitigate this issue through a class-specific…

Contrastive Vision-Language Pre-training, known as CLIP, has provided a new paradigm for learning visual representations using large-scale image-text pairs. It shows impressive performance on downstream tasks by zero-shot knowledge…

Large-scale pre-trained multi-modal models (e.g., CLIP) demonstrate strong zero-shot transfer capability in many discriminative tasks. Their adaptation to zero-shot image-conditioned text generation tasks has drawn increasing interest.…

Pre-trained vision and language models such as CLIP have witnessed remarkable success in connecting images and texts with a primary focus on English texts. Despite recent efforts to extend CLIP to support other languages, disparities in…

Large-scale image-text pre-trained models enable zero-shot classification and provide consistent accuracy across various data distributions. Nonetheless, optimizing these models in downstream tasks typically requires fine-tuning, which…

Semantic segmentation is a powerful method to facilitate visual scene understanding. Each pixel is assigned a label according to a pre-defined list of object classes and semantic entities. This becomes very useful as a means to summarize…

Existing cross-subject fMRI decoding methods typically train a model on multiple scanned subjects and then adapt it to a new subject using substantial paired fMRI-image data. However, in realistic scenarios, new-subject fMRI data are often…