linzhiqiu

cross_modal_adaptation

Cross-modal few-shot adaptation with CLIP

t2v_metrics

Evaluating text-to-image/video/3D models with VQAScore

visual_gpt_score

VisualGPTScore for visio-linguistic reasoning

CLIP-FlanT5

Training code for CLIP-FlanT5

continual-learning

leco

Learning with Ever-Changing Ontology

linzhiqiu-old.github.io

vl_finetuning

Few-shot Finetuning of CLIP

avalanche

Avalanche: an End-to-End Library for Continual Learning.

clear-benchmark-new.github.io

clear-benchmark.github.io

CLEAR-Challenge

cmu-vision.github.io

debiased-pseudo-labeling

[CVPR 2022] Debiased Learning from Naturally Imbalanced Pseudo-Labels

dino

PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

HRNet-Semantic-Segmentation

The OCR approach is rephrased as Segmentation Transformer: https://arxiv.org/abs/1909.11065. This is an official implementation of semantic segmentation for HRNet. https://arxiv.org/abs/1908.07919

HTML4Vision

A simple HTML visualization tool for computer vision research :hammer_and_wrench:

linzhiqiu.github.io

Zhiqiu Lin's site

LLaVA

[NeurIPS 2023 Oral] Visual Instruction Tuning: LLaVA (Large Language-and-Vision Assistant) built towards GPT-4V level capabilities.

llm-can-optimize-vlm.github.io

lmms-eval

Accelerating the development of large multimodal models (LMMs) with one-click evaluation module - lmms-eval.

mmselfsup

OpenMMLab Self-Supervised Learning Toolbox and Benchmark

PerceptualSimilarity

LPIPS metric. pip install lpips

pytorchvideo

A deep learning library for video understanding research.

streamlit-feedback-video

Collect user feedback from within your Streamlit app

streamlit-video-captioning

Streamlit LLM app

video_annotation

Video Annotation Format

video_captioning

vision-language-models-are-bows

Experiments and data for the paper "When and why vision-language models behave like bags-of-words, and what to do about it?" Oral @ ICLR 2023

why-winoground-hard

Code for 'Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality', EMNLP 2022