Deeply Supervised Flow-Based Generative Models
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationText to Image GenerationText-to-Image GenerationSimilar Papers 제목 키워드 기반
SAAN: Similarity-aware attention flow network for change detection with VHR remote sensing images
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 ObservationGeneralized Sliced Distances for Probability Distributions
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 testingDeeply-Supervised Recurrent Convolutional Neural Network for Saliency Detection
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 PredictionDeeply Unsupervised Patch Re-Identification for Pre-training Object Detectors
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+1Structured Coupled Generative Adversarial Networks for Unsupervised Monocular Depth Estimation
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