15 citations · 49 across the 24 of their papers we have counts for
24 papers
TEPA: Revoking Stale Memories for Conflict-Robust Language Agents
Yan Zhou, Yue Ouyang, Kaiyang Zheng +1
Long-term memory enables language agents to reuse past facts, preferences, and task experience. Persistence also creates a central falsifiability problem: when the world changes, s…
ExFusion: Efficient Transformer Training via Multi-Experts Fusion
Jiacheng Ruan, Daize Dong, Xiaoye Qu +5
Mixture-of-Experts (MoE) models substantially improve performance by increasing the capacity of dense architectures. However, directly training MoE models requires considerable com…
Understanding Robustness of Parameter-Efficient Tuning for Image Classification
Jiacheng Ruan, Xian Gao, Suncheng Xiang +3
Parameter-efficient tuning (PET) techniques calibrate the model's predictions on downstream tasks by freezing the pre-trained models and introducing a small number of learnable par…
iDAT: inverse Distillation Adapter-Tuning
Jiacheng Ruan, Jingsheng Gao, Mingye Xie +4
Adapter-Tuning (AT) method involves freezing a pre-trained model and introducing trainable adapter modules to acquire downstream knowledge, thereby calibrating the model for better…
Oceanship: A Large-Scale Dataset for Underwater Audio Target Recognition
Zeyu Li, Suncheng Xiang, Tong Yu +5
The recognition of underwater audio plays a significant role in identifying a vessel while it is in motion. Underwater target recognition tasks have a wide range of applications in…
LAMM: Label Alignment for Multi-Modal Prompt Learning
Jingsheng Gao, Jiacheng Ruan, Suncheng Xiang +5
With the success of pre-trained visual-language (VL) models such as CLIP in visual representation tasks, transferring pre-trained models to downstream tasks has become a crucial pa…
Supervised Contrastive Learning for Fine-grained Chromosome Recognition
Ruijia Chang, Suncheng Xiang, Chengyu Zhou +3
Chromosome recognition is an essential task in karyotyping, which plays a vital role in birth defect diagnosis and biomedical research. However, existing classification methods fac…
GIST: Improving Parameter Efficient Fine Tuning via Knowledge Interaction
Jiacheng Ruan, Jingsheng Gao, Mingye Xie +4
The Parameter-Efficient Fine-Tuning (PEFT) method, which adjusts or introduces fewer trainable parameters to calibrate pre-trained models on downstream tasks, has become a recent r…
Towards Open-set Gesture Recognition via Feature Activation Enhancement and Orthogonal Prototype Learning
Chen Liu, Can Han, Chengfeng Zhou +4
Gesture recognition is a foundational task in human-machine interaction (HMI). While there has been significant progress in gesture recognition based on surface electromyography (s…
Learning Multi-axis Representation in Frequency Domain for Medical Image Segmentation
Jiacheng Ruan, Jingsheng Gao, Mingye Xie +1
Recently, Visual Transformer (ViT) has been extensively used in medical image segmentation (MIS) due to applying self-attention mechanism in the spatial domain to modeling global k…
Colo-ReID: Discriminative Representation Embedding with Meta-learning for Colonoscopic Polyp Re-Identification
Suncheng Xiang, Chengfeng Zhou, Zhengjie Zhang +2
Colonoscopic Polyp Re-Identification aims to match the same polyp from a large gallery with images from different views taken using different cameras and plays an important role in…
AutoKary2022: A Large-Scale Densely Annotated Dataset for Chromosome Instance Segmentation
Dan You, Pengcheng Xia, Qiuzhu Chen +3
Automated chromosome instance segmentation from metaphase cell microscopic images is critical for the diagnosis of chromosomal disorders (i.e., karyotype analysis). However, it is…
Learning Robust Visual-Semantic Embedding for Generalizable Person Re-identification
Suncheng Xiang, Jingsheng Gao, Mengyuan Guan +5
Generalizable person re-identification (Re-ID) is a very hot research topic in machine learning and computer vision, which plays a significant role in realistic scenarios due to it…
Colo-SCRL: Self-Supervised Contrastive Representation Learning for Colonoscopic Video Retrieval
Qingzhong Chen, Shilun Cai, Crystal Cai +3
Colonoscopic video retrieval, which is a critical part of polyp treatment, has great clinical significance for the prevention and treatment of colorectal cancer. However, retrieval…
CluCDD:Contrastive Dialogue Disentanglement via Clustering
Jingsheng Gao, Zeyu Li, Suncheng Xiang +2
A huge number of multi-participant dialogues happen online every day, which leads to difficulty in understanding the nature of dialogue dynamics for both humans and machines. Dialo…
Deep Multimodal Fusion for Generalizable Person Re-identification
Suncheng Xiang, Hao Chen, Wei Ran +4
Person re-identification plays a significant role in realistic scenarios due to its various applications in public security and video surveillance. Recently, leveraging the supervi…
MALUNet: A Multi-Attention and Light-weight UNet for Skin Lesion Segmentation
Jiacheng Ruan, Suncheng Xiang, Mingye Xie +2
Recently, some pioneering works have preferred applying more complex modules to improve segmentation performances. However, it is not friendly for actual clinical environments due…
MEW-UNet: Multi-axis representation learning in frequency domain for medical image segmentation
Jiacheng Ruan, Mingye Xie, Suncheng Xiang +2
Recently, Visual Transformer (ViT) has been widely used in various fields of computer vision due to applying self-attention mechanism in the spatial domain to modeling global knowl…
SubFace: Learning with Softmax Approximation for Face Recognition
Hongwei Xu, Suncheng Xiang, Dahong Qian
The softmax-based loss functions and its variants (e.g., cosface, sphereface, and arcface) significantly improve the face recognition performance in wild unconstrained scenes. A co…
Rethinking Person Re-Identification via Semantic-Based Pretraining
Suncheng Xiang, Jingsheng Gao, Zirui Zhang +5
Pretraining is a dominant paradigm in computer vision. Generally, supervised ImageNet pretraining is commonly used to initialize the backbones of person re-identification (Re-ID) m…
Less is More: Learning from Synthetic Data with Fine-grained Attributes for Person Re-Identification
Suncheng Xiang, Guanjie You, Mengyuan Guan +4
Person re-identification (re-ID) plays an important role in applications such as public security and video surveillance. Recently, learning from synthetic data, which benefits from…
Learning from Self-Discrepancy via Multiple Co-teaching for Cross-Domain Person Re-Identification
Suncheng Xiang, Yuzhuo Fu, Mengyuan Guan +1
Employing clustering strategy to assign unlabeled target images with pseudo labels has become a trend for person re-identification (re-ID) algorithms in domain adaptation. A potent…
Taking A Closer Look at Synthesis: Fine-grained Attribute Analysis for Person Re-Identification
Suncheng Xiang, Yuzhuo Fu, Guanjie You +1
Person re-identification (re-ID) plays an important role in applications such as public security and video surveillance. Recently, learning from synthetic data, which benefits from…
Attribute analysis with synthetic dataset for person re-identification
Suncheng Xiang, Yuzhuo Fu, Guanjie You +1
Person re-identification (re-ID) plays an important role in applications such as public security and video surveillance. Recently, learning from synthetic data, which benefits from…