Official repository of Uni-AdaFocus (TPAMI 2024).

Jax/Flax implementation of DeiT and DeiT-III (ViT)

Greedy Local Learning with Context Supply for training deep networks.

Official repository of MLLA (NeurIPS 2024)

[TPAMI 2024] Probabilistic Contrastive Learning for Long-Tailed Visual Recognition

[IEEE TIP] Fine-grained Recognition with Learnable Semantic Data Augmentation

Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models arXiv 2023 / CVPR 2024

Official repository of Agent Attention (ECCV2024)

Repository of "Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning" (NeurIPS 2023 Spotlight)

[NeurIPS 2023] Rank-DETR for High Quality Object Detection

[ICCV 2023] Adaptive Rotated Convolution for Rotated Object Detection

本人的科研经验

[IEEE TPAMI] Latency-aware Unified Dynamic Networks for Efficient Image Recognition

Official repository of FLatten Transformer (ICCV2023)

Official implementation of Dynamic Perceiver

Official repository of ActiveNeRF (ECCV2022)

Pytorch implementation of DAPrompt: https://arxiv.org/abs/2202.06687

Official implementation of A Mixture of Surprises for Unsupervised Reinforcement Learning

[ECCV 2022] Learning to Weight Samples for Dynamic Early-exiting Networks

[NeurIPS 2022] Latency-aware Spatial-wise Dynamic Networks

[ICLR 2023 Spotlight] GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation

Code release for Deep Incubation (https://arxiv.org/abs/2212.04129)

[arXiv] Cross-Modal Adapter for Text-Video Retrieval

1.5−3.0× lossless training or pre-training speedup. An off-the-shelf, easy-to-implement algorithm for the efficient training of foundation visual backbones.

A curated reading list of research in Mixture-of-Experts(MoE).

A collection of 3D vision and language (e.g., 3D Visual Grounding, 3D Question Answering and 3D Dense Caption) papers and datasets.

Official repository of ACmix (CVPR2022)

[CVPR 2022] Pseudo-Q: Generating Pseudo Language Queries for Visual Grounding