A Python library to fetch the marine substrates datasets from dbSEABED (https://instaar.colorado.edu/~jenkinsc/dbseabed/)

Visual question answering with rationales

Official implementation for the paper "Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps"

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

The official GitHub page for ''Evaluating Object Hallucination in Large Vision-Language Models''

Large Language-and-Vision Assistant for Biomedicine, built towards multimodal GPT-4 level capabilities.

[ICLR 2024] Analyzing and Mitigating Object Hallucination in Large Vision-Language Models

A repository and benchmark for online test-time adaptation.

A list of papers that studies Novel Class Discovery

Code for Continuously Changing Corruptions (CCC) benchmark + evaluation

Refine high-quality datasets and visual AI models

Collection of awesome test-time (domain/batch/instance) adaptation methods

This repository includes the official project of TransUNet, presented in our paper: TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation.

A python interface for training Reinforcement Learning bots to battle on pokemon showdown

[NeurIPS 2024] This repo contains evaluation code for the paper "Are We on the Right Way for Evaluating Large Vision-Language Models"

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

Project Page for "LISA: Reasoning Segmentation via Large Language Model"

PixelLM is an effective and efficient LMM for pixel-level reasoning and understanding. PixelLM is accepted by CVPR 2024.

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows".

This is an official implementation for "SimMIM: A Simple Framework for Masked Image Modeling".

Fine-tuning SAM with Multi-Modal Prompts for Mobility Infrastructure Segmentation

Segment Anything Model, SAM, Sonar images

Official implementation of "Interpreting and Controlling Vision Foundation Models via Text Explanations"

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

Code for the paper "A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks".

An interactive toolbox for downloading satellite imagery, applying image segmentation models, mapping shoreline positions and more. The mapping extension for CoastSat and Zoo.

Open-source interface for processing recreation-grade side scan sonar datasets and reproducibly mapping benthic habitat