heekhero / DTL
This repository is the official implementation of "DTL: Disentangled Transfer Learning for Visual Recognition", which is accepted by AAAI 2024.
☆96Updated 11 months ago
Alternatives and similar repositories for DTL:
Users that are interested in DTL are comparing it to the libraries listed below
- A Unified Parameter-Efficient Transfer Learning Benchmark for Computer Vision Tasks☆272Updated 5 months ago
- Pytorch Implementation of "Sinkhorn Distance Minimization for Knowledge Distillation", COLING 2024 and TNNLS 2024☆119Updated last month
- [LMM + AIGC] What do we expect from LMMs as AIGI evaluators and how do they perform?☆143Updated 3 months ago
- PyTorch implementation of the paper : Exploring Regional Clues in CLIP for Zero-Shot Semantic Segmentation.☆42Updated 6 months ago
- Simple PyTorch implementation of "Libra: Building Decoupled Vision System on Large Language Models" (accepted by ICML 2024)☆146Updated last month
- Biomedical Generalist Video Generation Model☆182Updated 2 months ago
- A benchmark for video quality understanding of LMMs☆102Updated 3 months ago
- A curated list of research based on CLIP.☆151Updated 2 months ago
- Official code for TPAMI2024 paper: Pixel Distillation: Cost-flexible Distillation across Image Sizes and Heterogeneous Networks☆55Updated 2 months ago
- This repository contains the official implementation of the paper TokenUnify: Scalable Autoregressive Visual Pre-training with Mixture To…☆50Updated 5 months ago
- VisionFlow is a backend application for image recognition and notification systems, built with Flask, PostgreSQL, Redis, and Docker. It s…☆87Updated last week
- [CVPR'24] DuPL: Dual Student with Trustworthy Progressive Learning for Robust Weakly Supervised Semantic Segmentation.☆70Updated 7 months ago
- Code for paper: DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image Classification [ECCV…☆137Updated last month
- [AAAI'25 Oral] "MIA-Tuner: Adapting Large Language Models as Pre-training Text Detector".☆132Updated 3 weeks ago
- (ICML 24) Residual-Conditioned Optimal Transport: Towards Structure-Preserving Unpaired and Paired Image Restoration☆104Updated last month
- Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image Restoration☆75Updated 2 months ago
- MoH: Multi-Head Attention as Mixture-of-Head Attention☆189Updated 2 months ago
- code for TextSSR paper☆85Updated last week
- ☆342Updated 5 months ago
- MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts☆163Updated 3 months ago
- ARIES (ArXiv Research Intelligent Efficient Summary)☆43Updated last week
- Interactive Medical Image Segmentation: A Benchmark Dataset and Baseline☆176Updated last month
- GPU-Optimized SplineTransformer significantly accelerates the conversion of large data arrays into B-spline bases by leveraging GPU power…☆61Updated 7 months ago
- An cache reconstructed and optimized based on go-cache☆81Updated 3 weeks ago
- [ECML-PKDD'24] Hyperbolic Contrastive Learning with Model-Augmentation for Knowledge-Aware Recommendation☆35Updated last month
- 一个 Vitepress 插件，可以帮助你在编写文档的时候，通过路径引用，直接展示 Vue 组件示例 + 代码☆68Updated 2 months ago
- MDI machine learning SAM model server. Segment WSI(whole slide image) , simple images.☆191Updated 4 months ago
- The official implementation for "Learn from Segment Anything Model: Local Region Homogenizing for Cross-domain Remote Sensing Image Segme…☆111Updated 2 months ago
- Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models☆26Updated 2 years ago