158 citations · 343 across the 24 of their papers we have counts for
18 papers · 1 filter
Controllable-Continuous Color Editing in Diffusion Model via Color Mapping
Yuqi Yang, Dongliang Chang, Yuanchen Fang +3
In recent years, text-driven image editing has made significant progress. However, due to the inherent ambiguity and discreteness of natural language, color editing still faces cha…
HumanRecon: Neural Reconstruction of Dynamic Human Using Geometric Cues and Physical Priors
Junhui Yin, Wei Yin, Hao Chen +4
Recent methods for dynamic human reconstruction have attained promising reconstruction results. Most of these methods rely only on RGB color supervision without considering explici…
Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image Classification
Jijie Wu, Dongliang Chang, Aneeshan Sain +5
The main challenge for fine-grained few-shot image classification is to learn feature representations with higher inter-class and lower intra-class variations, with a mere few labe…
Learning Invariant Visual Representations for Compositional Zero-Shot Learning
Tian Zhang, Kongming Liang, Ruoyi Du +3
Compositional Zero-Shot Learning (CZSL) aims to recognize novel compositions using knowledge learned from seen attribute-object compositions in the training set. Previous works mai…
A Survey on Long-Tailed Visual Recognition
Lu Yang, He Jiang, Qing Song +1
The heavy reliance on data is one of the major reasons that currently limit the development of deep learning. Data quality directly dominates the effect of deep learning models, an…
Clue Me In: Semi-Supervised FGVC with Out-of-Distribution Data
Ruoyi Du, Dongliang Chang, Zhanyu Ma +2
Despite great strides made on fine-grained visual classification (FGVC), current methods are still heavily reliant on fully-supervised paradigms where ample expert labels are calle…
Making a Bird AI Expert Work for You and Me
Dongliang Chang, Kaiyue Pang, Ruoyi Du +3
As powerful as fine-grained visual classification (FGVC) is, responding your query with a bird name of "Whip-poor-will" or "Mallard" probably does not make much sense. This however…
DF^2AM: Dual-level Feature Fusion and Affinity Modeling for RGB-Infrared Cross-modality Person Re-identification
Junhui Yin, Zhanyu Ma, Jiyang Xie +3
RGB-infrared person re-identification is a challenging task due to the intra-class variations and cross-modality discrepancy. Existing works mainly focus on learning modality-share…
Unsupervised Person Re-identification via Simultaneous Clustering and Consistency Learning
Junhui Yin, Jiayan Qiu, Siqing Zhang +3
Unsupervised person re-identification (re-ID) has become an important topic due to its potential to resolve the scalability problem of supervised re-ID models. However, existing me…
A Comprehensive Evaluation Framework for Deep Model Robustness
Jun Guo, Wei Bao, Jiakai Wang +7
Deep neural networks (DNNs) have achieved remarkable performance across a wide range of applications, while they are vulnerable to adversarial examples, which motivates the evaluat…
Progressive Co-Attention Network for Fine-grained Visual Classification
Tian Zhang, Dongliang Chang, Zhanyu Ma +1
Fine-grained visual classification aims to recognize images belonging to multiple sub-categories within a same category. It is a challenging task due to the inherently subtle varia…
Your "Flamingo" is My "Bird": Fine-Grained, or Not
Dongliang Chang, Kaiyue Pang, Yixiao Zheng +3
Whether what you see in Figure 1 is a "flamingo" or a "bird", is the question we ask in this paper. While fine-grained visual classification (FGVC) strives to arrive at the former,…
SSKD: Self-Supervised Knowledge Distillation for Cross Domain Adaptive Person Re-Identification
Junhui Yin, Jiayan Qiu, Siqing Zhang +2
Domain adaptive person re-identification (re-ID) is a challenging task due to the large discrepancy between the source domain and the target domain. To reduce the domain discrepanc…
ReMarNet: Conjoint Relation and Margin Learning for Small-Sample Image Classification
Xiaoxu Li, Liyun Yu, Xiaochen Yang +4
Despite achieving state-of-the-art performance, deep learning methods generally require a large amount of labeled data during training and may suffer from overfitting when the samp…
OSLNet: Deep Small-Sample Classification with an Orthogonal Softmax Layer
Xiaoxu Li, Dongliang Chang, Zhanyu Ma +5
A deep neural network of multiple nonlinear layers forms a large function space, which can easily lead to overfitting when it encounters small-sample data. To mitigate overfitting…
Mind the Gap: Enlarging the Domain Gap in Open Set Domain Adaptation
Dongliang Chang, Aneeshan Sain, Zhanyu Ma +2
Unsupervised domain adaptation aims to leverage labeled data from a source domain to learn a classifier for an unlabeled target domain. Among its many variants, open set domain ada…
Fine-Grained Visual Classification via Progressive Multi-Granularity Training of Jigsaw Patches
Ruoyi Du, Dongliang Chang, Ayan Kumar Bhunia +4
Fine-grained visual classification (FGVC) is much more challenging than traditional classification tasks due to the inherently subtle intra-class object variations. Recent works ma…
OVC-Net: Object-Oriented Video Captioning with Temporal Graph and Detail Enhancement
Fangyi Zhu, Jenq-Neng Hwang, Zhanyu Ma +2
Traditional video captioning requests a holistic description of the video, yet the detailed descriptions of the specific objects may not be available. Without associating the movin…