26 citations · 64 across the 15 of their papers we have counts for
15 papers
NTK-Guided Few-Shot Class Incremental Learning
Jingren Liu, Zhong Ji, Yanwei Pang +1
The proliferation of Few-Shot Class Incremental Learning (FSCIL) methodologies has highlighted the critical challenge of maintaining robust anti-amnesia capabilities in FSCIL learn…
Dense Affinity Matching for Few-Shot Segmentation
Hao Chen, Yonghan Dong, Zheming Lu +4
Few-Shot Segmentation (FSS) aims to segment the novel class images with a few annotated samples. In this paper, we propose a dense affinity matching (DAM) framework to exploit the…
Multi-Content Interaction Network for Few-Shot Segmentation
Hao Chen, Yunlong Yu, Yonghan Dong +3
Few-Shot Segmentation (FSS) is challenging for limited support images and large intra-class appearance discrepancies. Most existing approaches focus on extracting high-level repres…
CODER: Coupled Diversity-Sensitive Momentum Contrastive Learning for Image-Text Retrieval
Haoran Wang, Dongliang He, Wenhao Wu +7
Image-Text Retrieval (ITR) is challenging in bridging visual and lingual modalities. Contrastive learning has been adopted by most prior arts. Except for limited amount of negative…
On minimizers and convolutional filters: theoretical connections and applications to genome analysis
Yun William Yu
Minimizers and convolutional neural networks (CNNs) are two quite distinct popular techniques that have both been employed to analyze categorical biological sequences. At face valu…
Episode-based Prototype Generating Network for Zero-Shot Learning
Yunlong Yu, Zhong Ji, Zhongfei Zhang +1
We introduce a simple yet effective episode-based training framework for zero-shot learning (ZSL), where the learning system requires to recognize unseen classes given only the cor…
A Semantics-Guided Class Imbalance Learning Model for Zero-Shot Classification
Zhong Ji, Xuejie Yu, Yunlong Yu +2
Zero-Shot Classification (ZSC) equips the learned model with the ability to recognize the visual instances from the novel classes via constructing the interactions between the visu…
Bi-Adversarial Auto-Encoder for Zero-Shot Learning
Yunlong Yu, Zhong Ji, Yanwei Pang +3
Existing generative Zero-Shot Learning (ZSL) methods only consider the unidirectional alignment from the class semantics to the visual features while ignoring the alignment from th…
Stacked Semantic-Guided Attention Model for Fine-Grained Zero-Shot Learning
Yunlong Yu, Zhong Ji, Yanwei Fu +3
Zero-Shot Learning (ZSL) is achieved via aligning the semantic relationships between the global image feature vector and the corresponding class semantic descriptions. However, usi…
Attribute-Guided Network for Cross-Modal Zero-Shot Hashing
Zhong Ji, Yuxin Sun, Yunlong Yu +2
Zero-Shot Hashing aims at learning a hashing model that is trained only by instances from seen categories but can generate well to those of unseen categories. Typically, it is achi…
Zero-Shot Learning via Latent Space Encoding
Yunlong Yu, Zhong Ji, Jichang Guo +2
Zero-Shot Learning (ZSL) is typically achieved by resorting to a class semantic embedding space to transfer the knowledge from the seen classes to unseen ones. Capturing the common…
Semantic Softmax Loss for Zero-Shot Learning
Zhong Ji, Yunxin Sun, Yulong Yu +2
A typical pipeline for Zero-Shot Learning (ZSL) is to integrate the visual features and the class semantic descriptors into a multimodal framework with a linear or bilinear model.…
Transductive Zero-Shot Learning with Adaptive Structural Embedding
Yunlong Yu, Zhong Ji, Jichang Guo +1
Zero-shot learning (ZSL) endows the computer vision system with the inferential capability to recognize instances of a new category that has never seen before. Two fundamental chal…
Transductive Zero-Shot Learning with a Self-training dictionary approach
Yunlong Yu, Zhong Ji, Xi Li +4
As an important and challenging problem in computer vision, zero-shot learning (ZSL) aims at automatically recognizing the instances from unseen object classes without training dat…
Zero-Shot Learning with Multi-Battery Factor Analysis
Zhong Ji, Yuzhong Xie, Yanwei Pang +2
Zero-shot learning (ZSL) extends the conventional image classification technique to a more challenging situation where the test image categories are not seen in the training sample…