1 citations · 4 across the 17 of their papers we have counts for
17 papers
DivControl: Knowledge Diversion for Controllable Image Generation
Yucheng Xie, Fu Feng, Ruixiao Shi +3
Diffusion models have advanced from text-to-image (T2I) to image-to-image (I2I) generation by incorporating structured inputs such as depth maps, enabling fine-grained spatial cont…
Extracting Multimodal Learngene in CLIP: Unveiling the Multimodal Generalizable Knowledge
Ruiming Chen, Junming Yang, Shiyu Xia +3
CLIP (Contrastive Language-Image Pre-training) has attracted widespread attention for its multimodal generalizable knowledge, which is significant for downstream tasks. However, th…
FAD: Frequency Adaptation and Diversion for Cross-domain Few-shot Learning
Ruixiao Shi, Fu Feng, Yucheng Xie +2
Cross-domain few-shot learning (CD-FSL) requires models to generalize from limited labeled samples under significant distribution shifts. While recent methods enhance adaptability…
Distribution-Conditional Generation: From Class Distribution to Creative Generation
Fu Feng, Yucheng Xie, Xu Yang +2
Text-to-image (T2I) diffusion models are effective at producing semantically aligned images, but their reliance on training data distributions limits their ability to synthesize tr…
Towards Better Performance in Incomplete LDL: Addressing Data Imbalance
Zhiqiang Kou, Haoyuan Xuan, Jing Wang +2
Label Distribution Learning (LDL) is a novel machine learning paradigm that addresses the problem of label ambiguity and has found widespread applications. Obtaining complete label…
Redefining <Creative> in Dictionary: Towards an Enhanced Semantic Understanding of Creative Generation
Fu Feng, Yucheng Xie, Xu Yang +2
``Creative'' remains an inherently abstract concept for both humans and diffusion models. While text-to-image (T2I) diffusion models can easily generate out-of-distribution concept…
FINE: Factorizing Knowledge for Initialization of Variable-sized Diffusion Models
Yucheng Xie, Fu Feng, Ruixiao Shi +4
The training of diffusion models is computationally intensive, making effective pre-training essential. However, real-world deployments often demand models of variable sizes due to…
KIND: Knowledge Integration and Diversion for Training Decomposable Models
Yucheng Xie, Fu Feng, Ruixiao Shi +3
Pre-trained models have become the preferred backbone due to the increasing complexity of model parameters. However, traditional pre-trained models often face deployment challenges…
WAVE: Weight Templates for Adaptive Initialization of Variable-sized Models
Fu Feng, Yucheng Xie, Jing Wang +1
The growing complexity of model parameters underscores the significance of pre-trained models. However, deployment constraints often necessitate models of varying sizes, exposing l…
Inaccurate Label Distribution Learning with Dependency Noise
Zhiqiang Kou, Jing Wang, Yuheng Jia +1
In this paper, we introduce the Dependent Noise-based Inaccurate Label Distribution Learning (DN-ILDL) framework to tackle the challenges posed by noise in label distribution learn…
Transferring Core Knowledge via Learngenes
Fu Feng, Jing Wang, Xin Geng
The pre-training paradigm fine-tunes the models trained on large-scale datasets to downstream tasks with enhanced performance. It transfers all knowledge to downstream tasks withou…
RankMatch: A Novel Approach to Semi-Supervised Label Distribution Learning Leveraging Inter-label Correlations
Kouzhiqiang Yucheng Xie, Jing Wang, Yuheng Jia +2
This paper introduces RankMatch, an innovative approach for Semi-Supervised Label Distribution Learning (SSLDL). Addressing the challenge of limited labeled data, RankMatch effecti…
Manipulating the Label Space for In-Context Classification
Haokun Chen, Xu Yang, Yuhang Huang +3
After pre-training by generating the next word conditional on previous words, the Language Model (LM) acquires the ability of In-Context Learning (ICL) that can learn a new task co…
Exploiting Multi-Label Correlation in Label Distribution Learning
Zhiqiang Kou jing wang yuheng jia xin geng
Label Distribution Learning (LDL) is a novel machine learning paradigm that assigns label distribution to each instance. Many LDL methods proposed to leverage label correlation in…
Genes in Intelligent Agents
Fu Feng, Jing Wang, Xu Yang +1
The genes in nature give the lives on earth the current biological intelligence through transmission and accumulation over billions of years. Inspired by the biological intelligenc…
Data Augmentation For Label Enhancement
Zhiqiang Kou, Yuheng Jia, Jing Wang +2
Label distribution (LD) uses the description degree to describe instances, which provides more fine-grained supervision information when learning with label ambiguity. Nevertheless…
Inaccurate Label Distribution Learning
Zhiqiang Kou, Yuheng Jia, Jing Wang +1
Label distribution learning (LDL) trains a model to predict the relevance of a set of labels (called label distribution (LD)) to an instance. The previous LDL methods all assumed t…