326 citations · 2.5k across the 46 of their papers we have counts for
46 papers
Seedream 4.0: Toward Next-generation Multimodal Image Generation
Team Seedream, :, Yunpeng Chen +48
We introduce Seedream 4.0, an efficient and high-performance multimodal image generation system that unifies text-to-image (T2I) synthesis, image editing, and multi-image compositi…
Seedance 1.0: Exploring the Boundaries of Video Generation Models
Yu Gao, Haoyuan Guo, Tuyen Hoang +41
Notable breakthroughs in diffusion modeling have propelled rapid improvements in video generation, yet current foundational model still face critical challenges in simultaneously b…
SeedEdit 3.0: Fast and High-Quality Generative Image Editing
Peng Wang, Yichun Shi, Xiaochen Lian +5
We introduce SeedEdit 3.0, in companion with our T2I model Seedream 3.0, which significantly improves over our previous SeedEdit versions in both aspects of edit instruction follow…
Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model
Team Seawead, Ceyuan Yang, Zhijie Lin +52
This technical report presents a cost-efficient strategy for training a video generation foundation model. We present a mid-sized research model with approximately 7 billion parame…
Seedream 3.0 Technical Report
Yu Gao, Lixue Gong, Qiushan Guo +28
We present Seedream 3.0, a high-performance Chinese-English bilingual image generation foundation model. We develop several technical improvements to address existing challenges in…
Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Model
Lixue Gong, Xiaoxia Hou, Fanshi Li +25
Rapid advancement of diffusion models has catalyzed remarkable progress in the field of image generation. However, prevalent models such as Flux, SD3.5 and Midjourney, still grappl…
Dressing in the Wild by Watching Dance Videos
Xin Dong, Fuwei Zhao, Zhenyu Xie +6
While significant progress has been made in garment transfer, one of the most applicable directions of human-centric image generation, existing works overlook the in-the-wild image…
Online Multi-Granularity Distillation for GAN Compression
Yuxi Ren, Jie Wu, Xuefeng Xiao +1
Generative Adversarial Networks (GANs) have witnessed prevailing success in yielding outstanding images, however, they are burdensome to deploy on resource-constrained devices due…
One Backward from Ten Forward, Subsampling for Large-Scale Deep Learning
Chaosheng Dong, Xiaojie Jin, Weihao Gao +5
Deep learning models in large-scale machine learning systems are often continuously trained with enormous data from production environments. The sheer volume of streaming training…
Human Motion Transfer from Poses in the Wild
Jian Ren, Menglei Chai, Sergey Tulyakov +3
In this paper, we tackle the problem of human motion transfer, where we synthesize novel motion video for a target person that imitates the movement from a reference video. It is a…
AtomNAS: Fine-Grained End-to-End Neural Architecture Search
Jieru Mei, Yingwei Li, Xiaochen Lian +4
Search space design is very critical to neural architecture search (NAS) algorithms. We propose a fine-grained search space comprised of atomic blocks, a minimal search unit that i…
Neural Epitome Search for Architecture-Agnostic Network Compression
Daquan Zhou, Xiaojie Jin, Qibin Hou +3
The recent WSNet [1] is a new model compression method through sampling filterweights from a compact set and has demonstrated to be effective for 1D convolutionneural networks (CNN…
EnlightenGAN: Deep Light Enhancement without Paired Supervision
Yifan Jiang, Xinyu Gong, Ding Liu +6
Deep learning-based methods have achieved remarkable success in image restoration and enhancement, but are they still competitive when there is a lack of paired training data? As o…
Slimmable Neural Networks
Jiahui Yu, Linjie Yang, Ning Xu +2
We present a simple and general method to train a single neural network executable at different widths (number of channels in a layer), permitting instant and adaptive accuracy-eff…
YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark
Ning Xu, Linjie Yang, Yuchen Fan +4
Learning long-term spatial-temporal features are critical for many video analysis tasks. However, existing video segmentation methods predominantly rely on static image segmentatio…
YouTube-VOS: Sequence-to-Sequence Video Object Segmentation
Ning Xu, Linjie Yang, Yuchen Fan +6
Learning long-term spatial-temporal features are critical for many video analysis tasks. However, existing video segmentation methods predominantly rely on static image segmentatio…
Wide Activation for Efficient and Accurate Image Super-Resolution
Jiahui Yu, Yuchen Fan, Jianchao Yang +4
In this report we demonstrate that with same parameters and computational budgets, models with wider features before ReLU activation have significantly better performance for singl…
Factorized Adversarial Networks for Unsupervised Domain Adaptation
Jian Ren, Jianchao Yang, Ning Xu +1
In this paper, we propose Factorized Adversarial Networks (FAN) to solve unsupervised domain adaptation problems for image classification tasks. Our networks map the data distribut…
EIGEN: Ecologically-Inspired GENetic Approach for Neural Network Structure Searching from Scratch
Jian Ren, Zhe Li, Jianchao Yang +3
Designing the structure of neural networks is considered one of the most challenging tasks in deep learning, especially when there is few prior knowledge about the task domain. In…
Efficient Video Object Segmentation via Network Modulation
Linjie Yang, Yanran Wang, Xuehan Xiong +2
Video object segmentation targets at segmenting a specific object throughout a video sequence, given only an annotated first frame. Recent deep learning based approaches find it ef…
Learning D-FilterMap for Deep Convolutional Neural Networks
Yingzhen Yang, Jianchao Yang, Ning Xu +1
We present a novel and compact architecture for deep Convolutional Neural Networks (CNNs) in this paper, termed D-FilterMap Convolutional Neural Networks (D-FM-CNNs). The con…
Action Recognition with Spatio-Temporal Visual Attention on Skeleton Image Sequences
Zhengyuan Yang, Yuncheng Li, Jianchao Yang +1
Action recognition with 3D skeleton sequences is becoming popular due to its speed and robustness. The recently proposed Convolutional Neural Networks (CNN) based methods have show…
WSNet: Compact and Efficient Networks Through Weight Sampling
Xiaojie Jin, Yingzhen Yang, Ning Xu +4
We present a new approach and a novel architecture, termed WSNet, for learning compact and efficient deep neural networks. Existing approaches conventionally learn full model param…
Learning to Segment Human by Watching YouTube
Xiaodan Liang, Yunchao Wei, Liang Lin +4
An intuition on human segmentation is that when a human is moving in a video, the video-context (e.g., appearance and motion clues) may potentially infer reasonable mask informatio…