paper-with-me

Papers

Deeply Supervised Flow-Based Generative Models

2025-03-18 · Inkyu Shin, Chenglin Yang, Liang-Chieh Chen

Flow based generative models have charted an impressive path across multiple visual generation tasks by adhering to a simple principle: learning velocity representations of a linear interpolant. However, we observe that training velocity solely from the final layer output underutilizes the rich inter layer representations, potentially impeding model convergence. To address this limitation, we introduce DeepFlow, a novel framework that enhances velocity representation through inter layer communication. DeepFlow partitions transformer layers into balanced branches with deep supervision and inserts a lightweight Velocity Refiner with Acceleration (VeRA) block between adjacent branches, which aligns the intermediate velocity features within transformer blocks. Powered by the improved deep supervision via the internal velocity alignment, DeepFlow converges 8 times faster on ImageNet with equivalent performance and further reduces FID by 2.6 while halving training time compared to previous flow based models without a classifier free guidance. DeepFlow also outperforms baselines in text to image generation tasks, as evidenced by evaluations on MSCOCO and zero shot GenEval.

📄 PDF Abstract BibTeX arXiv:2503.14494

Code (0)

등록된 구현이 없습니다.

Tasks

Image GenerationText to Image GenerationText-to-Image Generation

Similar Papers 제목 키워드 기반

SAAN: Similarity-aware attention flow network for change detection with VHR remote sensing images

2023-08-28 · HaoNan Guo, Xin Su, Chen Wu, Bo Du 외

Change detection (CD) is a fundamental and important task for monitoring the land surface dynamics in the earth observation field. Existing deep learning-based CD methods typically extract bi-temporal image features usin…

Change DetectionDecoderEarth Observation

Generalized Sliced Distances for Probability Distributions

2020-02-28 · Soheil Kolouri, Kimia Nadjahi, Umut Simsekli, Shahin Shahrampour

Probability metrics have become an indispensable part of modern statistics and machine learning, and they play a quintessential role in various applications, including statistical hypothesis testing and generative modeli…

Two-sample testing

Deeply-Supervised Recurrent Convolutional Neural Network for Saliency Detection

2016-08-18 · Youbao Tang, Xiangqian Wu, Wei Bu

This paper proposes a novel saliency detection method by developing a deeply-supervised recurrent convolutional neural network (DSRCNN), which performs a full image-to-image saliency prediction. For saliency detection, t…

Saliency DetectionSaliency Prediction

Deeply Unsupervised Patch Re-Identification for Pre-training Object Detectors

2021-03-08 · Jian Ding, Enze Xie, Hang Xu, Chenhan Jiang 외

Unsupervised pre-training aims at learning transferable features that are beneficial for downstream tasks. However, most state-of-the-art unsupervised methods concentrate on learning global representations for image-leve…

Objectobject-detectionObject DetectionRepresentation Learning+1

Structured Coupled Generative Adversarial Networks for Unsupervised Monocular Depth Estimation

2019-08-15 · Mihai Marian Puscas, Dan Xu, Andrea Pilzer, Nicu Sebe

Inspired by the success of adversarial learning, we propose a new end-to-end unsupervised deep learning framework for monocular depth estimation consisting of two Generative Adversarial Networks (GAN), deeply coupled wit…

Depth EstimationMonocular Depth EstimationUnsupervised Monocular Depth Estimation