MediaBrain-SJTU

MING

明医 (MING)：中文医疗问诊大模型

MedKLIP

The official code for MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training in Radiology. We propose to leverage medical specific knowledge enhancing language-image pre-training method, significantly advancing the ability of pre-trained models to handle unseen diseases on zero-shot classification and grounding tasks.

LED

[CVPR2023] Leapfrog Diffusion Model for Stochastic Trajectory Prediction

EqMotion

[CVPR2023] EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning

BCL

[ICML2022] Contrastive Learning with Boosted Memorization

MVFA-AD

[CVPR2024 Highlight] Adapting Visual-Language Models for Generalizable Anomaly Detection in Medical Images

GenMedicalEval

CoBEVFlow

[NeurIPS 2023] Asynchrony-Robust Collaborative Perception via Bird’s Eye View Flow

FedDisco

FedDG-GA

[CVPR 2023] Federated Domain Generalization with Generalization Adjustment

AuxFormer

[ICCV2023] Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction

pFedGraph

JRTransformer

[ICCV2023] Joint-Relation Transformer for Multi-Person Motion Prediction

Geometric-Harmonization

[NeurIPS 2023 Spotlight] Combating Representation Learning Disparity with Geometric Harmonization

ECGAD

[MICCAI2023 Early Accept] Multi-scale Cross-restoration Framework for Electrocardiogram Anomaly Detection

GPFL-GRACE

[MICCAI 2023] GRACE: Enhancing Federated Learning for Medical Imaging with Generalized and Personalized Gradient Correction

CoFormer

FedGELA

[NeurIPS 2023]Federated Learning with Bilateral Curation for Partially Class-Disjoint Data

K-Diag

FedLESAM

[ICML 2024 spotlight] This repository contains the implementation details for the paper "Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization"

DISAM

This repository contains the implementation details for the paper "Domain-Inspired Sharpness-Aware Minimization Under Domain Shifts," accepted at the ICLR 2024.

OC_LT

Official code base for "Long-Tailed Diffusion Models With Oriented Calibration" ICLR2024

ECISQA

[NeurIPS 2023] Emergent communication in interactive sketch question answering

FedMR

[TMLR 2023]Federated Learning under Partially Class-Disjoint Data via Manifold Reshaping

LoRKD

GSC

FreeAlign

mediabrain-sjtu.github.io

SHE

[ICLR 2024] PyTorch implementation for "On Harmonizing Implicit Subpopulations"

DivBS

[ICML 2024] PyTorch implementation for "Diversified Batch Selection for Training Acceleration"