paper-with-me

Papers

Replay-Based Continual Learning with Dual-Layered Distillation and a Streamlined U-Net for Efficient Text-to-Image Generation

2025-05-11 · Md. Naimur Asif Borno, Md Sakib Hossain Shovon, Asmaa Soliman Al-Moisheer, Mohammad Ali Moni

Recent advancements in text-to-image diffusion models are hindered by high computational demands, limiting accessibility and scalability. This paper introduces KDC-Diff, a novel stable diffusion framework that enhances efficiency while maintaining image quality. KDC-Diff features a streamlined U-Net architecture with nearly half the parameters of the original U-Net (482M), significantly reducing model complexity. We propose a dual-layered distillation strategy to ensure high-fidelity generation, transferring semantic and structural insights from a teacher to a compact student model while minimizing quality degradation. Additionally, replay-based continual learning is integrated to mitigate catastrophic forgetting, allowing the model to retain prior knowledge while adapting to new data. Despite operating under extremely low computational resources, KDC-Diff achieves state-of-the-art performance on the Oxford Flowers and Butterflies & Moths 100 Species datasets, demonstrating competitive metrics such as FID, CLIP, and LPIPS. Moreover, it significantly reduces inference time compared to existing models. These results establish KDC-Diff as a highly efficient and adaptable solution for text-to-image generation, particularly in computationally constrained environments.

📄 PDF Abstract BibTeX arXiv:2505.06995

Code (0)

등록된 구현이 없습니다.

Tasks

Continual LearningImage GenerationText to Image GenerationText-to-Image Generation

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Concatenated Skip Connection A Concatenated Skip Connection is a type of skip connection that seeks to reuse features by concatenating them to new layers, allowing more information to be retained from…
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
U-Net 설명 없음
CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Continual Hand-Eye Calibration for Open-world Robotic Manipulation

2026-04-17 · Fazeng Li, Gan Sun, Chenxi Liu, Yao He 외 arxiv

Hand-eye calibration through visual localization is a critical capability for robotic manipulation in open-world environments. However, most deep learning-based calibration models suffer from catastrophic forgetting when…

Visual LocalizationContinual Learning

nVFNet-RDC: Replay and Non-Local Distillation Collaboration for Continual Object Detection

2022-09-08 · Jinxiang Lai, Wenlong Liu, Jun Liu

Continual Learning (CL) focuses on developing algorithms with the ability to adapt to new environments and learn new skills. This very challenging task has generated a lot of interest in recent years, with new solutions …

Continual Learningobject-detectionObject Detection

Distilled Replay: Overcoming Forgetting through Synthetic Samples

2021-03-29 · Andrea Rosasco, Antonio Carta, Andrea Cossu, Vincenzo Lomonaco 외

Replay strategies are Continual Learning techniques which mitigate catastrophic forgetting by keeping a buffer of patterns from previous experiences, which are interleaved with new data during training. The amount of pat…

Continual Learning

Continual Learning of Diffusion Models with Generative Distillation

2023-11-23 · Sergi Masip, Pau Rodriguez, Tinne Tuytelaars, Gido M. van de Ven

Diffusion models are powerful generative models that achieve state-of-the-art performance in image synthesis. However, training them demands substantial amounts of data and computational resources. Continual learning wou…

Continual LearningDenoisingImage Generation

Sparse Distributed Memory is a Continual Learner

2023-03-20 · Trenton Bricken, Xander Davies, Deepak Singh, Dmitry Krotov 외

Continual learning is a problem for artificial neural networks that their biological counterparts are adept at solving. Building on work using Sparse Distributed Memory (SDM) to connect a core neural circuit with the pow…

Continual Learning