Using the Huggingface Transformer-lib to finetune SAM implementing the LoRa technique known from NLP.

Fast Segment Anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

[MICCAI 2024] The official repository for DeSAM: Decoupled Segment Anything Model for Generalizable Medical Image Segmentation.

CVPR2024

[CVPR'24 & IJCV'25] Pytorch Implementation for ReCLIP

[CVPR'24] DuPL: Dual Student with Trustworthy Progressive Learning for Robust Weakly Supervised Semantic Segmentation.

[CVPR 2022] C2AM: Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic Segmentation

Official code for ICLR 2024 paper, "A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation"

[TPAMI 2025|CVPR 2023] Sparsely Annotated Semantic Segmentation with Adaptive Gaussian Mixtures

ID3 implementation for the Iris flower dataset

[AAAI 2024] TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training

PyTorch implementation of the InfoNCE loss for self-supervised learning.

[TMM2025] Tackling Ambiguity from Perspective of Uncertainty Inference and Affinity Diversification for Weakly Supervised Semantic Segmentation

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

[ICCV 2017] Torch code for Grad-CAM

Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentation, CVPR 2018

Official code for the NeurIPS 2023 paper "Switching Temporary Teachers for Semi-Supervised Semantic Segmentation"

Code for GTA-Seg (NeurIPS2022)

This is the official implementation of our PrOmpt cLass lEarning (POLE).

[CVPR 2024] The repository contains the official implementation of "Open-Vocabulary Segmentation with Semantic-Assisted Calibration"

Official PyTorch implementation of "Extract Free Dense Labels from CLIP" (ECCV 22 Oral)

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Code for our TMLR 2024 paper: Adapting Contrastive Language-Image Pretrained (CLIP) Models for Out-of-Distribution Detection https://arxiv.org/abs/2303.05828

[CVPR 2024] Official Implementation of Collaborating Foundation models for Domain Generalized Semantic Segmentation

Official PyTorch implementation of "Weakly Supervised Semantic Segmentation for Driving Scenes", AAAI2024