21 citations · 72 across the 13 of their papers we have counts for
13 papers
Prototype Fission: Closing Set for Robust Open-set Semi-supervised Learning
Xuwei Tan, Yi-Jie Huang, Yaqian Li
Semi-supervised Learning (SSL) has been proven vulnerable to out-of-distribution (OOD) samples in realistic large-scale unsupervised datasets due to over-confident pseudo-labeling…
CLIP Brings Better Features to Visual Aesthetics Learners
Liwu Xu, Jinjin Xu, Yuzhe Yang +3
Image Aesthetics Assessment (IAA) is a challenging task due to its subjective nature and expensive manual annotations. Recent large-scale vision-language models, such as Contrastiv…
Recognize Anything: A Strong Image Tagging Model
Youcai Zhang, Xinyu Huang, Jinyu Ma +9
We present the Recognize Anything Model (RAM): a strong foundation model for image tagging. RAM makes a substantial step for large models in computer vision, demonstrating the zero…
Box-Level Active Detection
Mengyao Lyu, Jundong Zhou, Hui Chen +7
Active learning selects informative samples for annotation within budget, which has proven efficient recently on object detection. However, the widely used active detection benchma…
Knowledge Distillation from Single to Multi Labels: an Empirical Study
Youcai Zhang, Yuzhuo Qin, Hengwei Liu +3
Knowledge distillation (KD) has been extensively studied in single-label image classification. However, its efficacy for multi-label classification remains relatively unexplored. I…
Tag2Text: Guiding Vision-Language Model via Image Tagging
Xinyu Huang, Youcai Zhang, Jinyu Ma +6
This paper presents Tag2Text, a vision language pre-training (VLP) framework, which introduces image tagging into vision-language models to guide the learning of visual-linguistic…
IDEA: Increasing Text Diversity via Online Multi-Label Recognition for Vision-Language Pre-training
Xinyu Huang, Youcai Zhang, Ying Cheng +7
Vision-Language Pre-training (VLP) with large-scale image-text pairs has demonstrated superior performance in various fields. However, the image-text pairs co-occurrent on the Inte…
Mixed Sample Augmentation for Online Distillation
Yiqing Shen, Liwu Xu, Yuzhe Yang +2
Mixed Sample Regularization (MSR), such as MixUp or CutMix, is a powerful data augmentation strategy to generalize convolutional neural networks. Previous empirical analysis has il…
Personalized Image Aesthetics Assessment with Rich Attributes
Yuzhe Yang, Liwu Xu, Leida Li +4
Personalized image aesthetics assessment (PIAA) is challenging due to its highly subjective nature. People's aesthetic tastes depend on diversified factors, including image charact…
Self-Distillation from the Last Mini-Batch for Consistency Regularization
Yiqing Shen, Liwu Xu, Yuzhe Yang +2
Knowledge distillation (KD) shows a bright promise as a powerful regularization strategy to boost generalization ability by leveraging learned sample-level soft targets. Yet, emplo…
Simple and Robust Loss Design for Multi-Label Learning with Missing Labels
Youcai Zhang, Yuhao Cheng, Xinyu Huang +4
Multi-label learning in the presence of missing labels (MLML) is a challenging problem. Existing methods mainly focus on the design of network structures or training schemes, which…
Towards Communication-Efficient and Privacy-Preserving Federated Representation Learning
Haizhou Shi, Youcai Zhang, Zijin Shen +4
This paper investigates the feasibility of federated representation learning under the constraints of communication cost and privacy protection. Existing works either conduct annot…
On the Efficacy of Small Self-Supervised Contrastive Models without Distillation Signals
Haizhou Shi, Youcai Zhang, Siliang Tang +4
It is a consensus that small models perform quite poorly under the paradigm of self-supervised contrastive learning. Existing methods usually adopt a large off-the-shelf model to t…