Latest Research
Lens functions for exploring UMAP Projections with Domain Knowledge
The effectiveness of the lens functions is demonstrated in two use cases and their computational cost is analysed in a synthetic benchmark.
MMFusion: Multi-modality Diffusion Model for Lymph Node Metastasis Diagnosis in Esophageal Cancer
In addition, efficient and effective interactions between multi-modal representations need to be further explored, lacking insightful exploration of prognostic correlation in multi-modality features.
OpenGait: A Comprehensive Benchmark Study for Gait Recognition towards Better Practicality
shiqiyu/opengait
•
•
To this end, we first develop OpenGait, a flexible and efficient gait recognition platform.
Improving Transformers with Dynamically Composable Multi-Head Attention
At the core of DCMHA is a $\it{Compose}$ function that transforms the attention score and weight matrices in an input-dependent way.
Dual-level Hypergraph Contrastive Learning with Adaptive Temperature Enhancement
graphprojects/HyGCL-AdT
•
•
International World Wide Web Conference 2024
However, these works have the following limitations in modeling the high-order relationships over unlabeled data: (i) They primarily focus on maximizing the agreements among individual node embeddings while neglecting the capture of group-wise collective behaviors within hypergraphs; (ii) Most of them disregard the importance of the temperature index in discriminating contrastive pairs during contrast optimization.
Self-Distillation Improves DNA Sequence Inference
Self-supervised pretraining (SSP) has been recognized as a method to enhance prediction accuracy in various downstream tasks.
EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic Camera
We propose Endoscopic Depth Any Camera (EndoDAC) which is an efficient self-supervised depth estimation framework that adapts foundation models to endoscopic scenes.
Output-decomposed Learning of Mealy Machines
We present an active automata learning algorithm which learns a decomposition of a finite state machine, based on projecting onto individual outputs.
Multimodal Collaboration Networks for Geospatial Vehicle Detection in Dense, Occluded, and Large-Scale Events
shank2358/mudet
•
•
To this end, we first construct two multimodal dense and occlusion vehicle detection datasets for large-scale events, utilizing RGB and height map modalities.
Efficient Vision-Language Pre-training by Cluster Masking
zi-hao-wei/efficient-vision-language-pre-training-by-cluster-masking
•
•
We propose a simple strategy for masking image patches during visual-language contrastive learning that improves the quality of the learned representations and the training speed.
