相关论文: Edit2Restore:Few-Shot Image Restoration via Parame…

Prompt learning is effective for fine-tuning foundation models to improve their generalization across a variety of downstream tasks. However, the prompts that are independently optimized along a single modality path, may sacrifice the…

Deep learning models in satellite onboard enable real-time interpretation of remote sensing images, reducing the need for data transmission to the ground and conserving communication resources. As satellite numbers and observation…

Can small language models achieve strong tool-use performance without complex adaptation mechanisms? This paper investigates this question through Meta-Tool, a controlled empirical study comparing hypernetwork-based LoRA adaptation against…

The task of learning from only a few examples (called a few-shot setting) is of key importance and relevance to a real-world setting. For question answering (QA), the current state-of-the-art pre-trained models typically need fine-tuning on…

Image super-resolution (SR) aims to learn a mapping from low-resolution (LR) to high-resolution (HR) using paired HR-LR training images. Conventional SR methods typically gather the paired training data by synthesizing LR images from HR…

Denoising diffusion models have recently achieved remarkable success in image generation, capturing rich information about natural image statistics. This makes them highly promising for image reconstruction, where the goal is to recover a…

Diffusion models have revolutionized text-to-image (T2I) synthesis, producing high-quality, photorealistic images. However, they still struggle to properly render the spatial relationships described in text prompts. To address the lack of…

Most previous few-shot learning algorithms are based on meta-training with fake few-shot tasks as training samples, where large labeled base classes are required. The trained model is also limited by the type of tasks. In this paper we…

Efficient fine-tuning of pre-trained Text-to-Image (T2I) models involves adjusting the model to suit a particular task or dataset while minimizing computational resources and limiting the number of trainable parameters. However, it often…

Low-rank adaptation (LoRA) has emerged as the de facto standard for parameter-efficient fine-tuning (PEFT) of foundation models, enabling the adaptation of billion-parameter networks with minimal computational and memory overhead. Despite…

Speech models have long been known to overfit individual speakers for many classification tasks. This leads to poor generalization in settings where the speakers are out-of-domain or out-of-distribution, as is common in production…

While Foundation Models provide a general tool for rapid content creation, they regularly require task-specific adaptation. Traditionally, this exercise involves careful curation of datasets and repeated fine-tuning of the underlying model.…

We present a novel Parameter-Efficient Fine-Tuning (PEFT) method, dubbed as Adaptive Freezing of Low Rank Adaptation (AFLoRA). Specifically, for each pre-trained frozen weight tensor, we add a parallel path of trainable low-rank matrices,…

This paper introduces a novel Parameter-Efficient Fine-Tuning (PEFT) framework for multi-modal, multi-task transfer learning with pre-trained language models. PEFT techniques such as LoRA, BitFit and IA3 have demonstrated comparable…

Machine unlearning is an emerging technology that removes a subset of the training data from a trained model without significantly affecting the model performance on the remaining data. This topic is becoming increasingly important in…

Few-shot, fine-grained classification in computer vision poses significant challenges due to the need to differentiate subtle class distinctions with limited data. This paper presents a novel method that enhances the Contrastive…

Few-shot learning is the process of learning novel classes using only a few examples and it remains a challenging task in machine learning. Many sophisticated few-shot learning algorithms have been proposed based on the notion that networks…

Instruction-based image editing has made a great process in using natural human language to manipulate the visual content of images. However, existing models are limited by the quality of the dataset and cannot accurately localize editing…

Image diffusion models, trained on massive image collections, have emerged as the most versatile image generator model in terms of quality and diversity. They support inverting real images and conditional (e.g., text) generation, making…

Various adaptation methods, such as LoRA, prompts, and adapters, have been proposed to enhance the performance of pre-trained vision-language models in specific domains. The robustness of these adaptation methods against distribution shifts…