1 citations · 1 across the 12 of their papers we have counts for
9 papers · 1 filter
Video-Mirai: Autoregressive Video Diffusion Models Need Foresight
Yonghao Yu, Lang Huang, Runyi Li +2
Causal video generators must predict from the past, but they need not learn only from it. In streaming autoregressive video diffusion, each emitted segment becomes a commitment tha…
A Multihead Continual Learning Framework for Fine-Grained Fashion Image Retrieval with Contrastive Learning and Exponential Moving Average Distillation
Ling Xiao, Toshihiko Yamasaki
Most fine-grained fashion image retrieval (FIR) methods assume a static setting, requiring full retraining when new attributes appear, which is costly and impractical for dynamic s…
Reward Incremental Learning in Text-to-Image Generation
Maorong Wang, Jiafeng Mao, Xueting Wang +1
The recent success of denoising diffusion models has significantly advanced text-to-image generation. While these large-scale pretrained models show excellent performance in genera…
Dealing with Synthetic Data Contamination in Online Continual Learning
Maorong Wang, Nicolas Michel, Jiafeng Mao +1
Image generation has shown remarkable results in generating high-fidelity realistic images, in particular with the advancement of diffusion-based models. However, the prevalence of…
Difficulty Controlled Diffusion Model for Synthesizing Effective Training Data
Zerun Wang, Jiafeng Mao, Xueting Wang +1
Generative models have become a powerful tool for synthesizing training data in computer vision tasks. Current approaches solely focus on aligning generated images with the target…
SCOMatch: Alleviating Overtrusting in Open-set Semi-supervised Learning
Zerun Wang, Liuyu Xiang, Lang Huang +3
Open-set semi-supervised learning (OSSL) leverages practical open-set unlabeled data, comprising both in-distribution (ID) samples from seen classes and out-of-distribution (OOD) s…
From Obstacles to Resources: Semi-supervised Learning Faces Synthetic Data Contamination
Zerun Wang, Jiafeng Mao, Liuyu Xiang +1
Semi-supervised learning (SSL) can improve model performance by leveraging unlabeled images, which can be collected from public image sources with low costs. In recent years, synth…
Language-Guided Self-Supervised Video Summarization Using Text Semantic Matching Considering the Diversity of the Video
Tomoya Sugihara, Shuntaro Masuda, Ling Xiao +1
Current video summarization methods rely heavily on supervised computer vision techniques, which demands time-consuming and subjective manual annotations. To overcome these limitat…
Online Open-set Semi-supervised Object Detection with Dual Competing Head
Zerun Wang, Ling Xiao, Liuyu Xiang +2
Open-set semi-supervised object detection (OSSOD) task leverages practical open-set unlabeled datasets that comprise both in-distribution (ID) and out-of-distribution (OOD) instanc…