Jihun Kim's repositories
UniIR
Official code for paper "UniIR: Training and Benchmarking Universal Multimodal Information Retrievers"
Retrieval-Augmented-Visual-Question-Answering
This is the official repository for Retrieval Augmented Visual Question Answering
TCL
code for TCL: Vision-Language Pre-Training with Triple Contrastive Learning, CVPR 2022
LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
mmdetection
OpenMMLab Detection Toolbox and Benchmark
object-detection-detectron2
A series of notebooks to dive deep into popular datasets for object detection and learn how to train Detectron2 on a custom dataset
laplacian_classify_recapture_image
classify recapture images using laplacian filter and CNN network
ko-lm-evaluation-harness
Forked repo from https://github.com/EleutherAI/lm-evaluation-harness/commit/1f66adc
DeepSpeedExamples
Example models using DeepSpeed
lm-evaluation-harness
A framework for few-shot evaluation of autoregressive language models.
train-CLIP
A PyTorch Lightning solution to training OpenAI's CLIP from scratch.
ComposeAE
Official code for WACV 2021 paper - Compositional Learning of Image-Text Query for Image Retrieval
BalancedMetaSoftmax-Classification
Code for the paper "Balanced Meta-Softmax for Long-Tailed Visual Recognition" on long-tailed visual recognition datasets
MiSLAS
Improving Calibration for Long-Tailed Recognition (CVPR2021)
TADE-AgnosticLT
This repository is the official Pytorch implementation of Test-Agnostic Long-Tailed Recognition by Test-Time Aggregating Diverse Experts with Self-Supervision.
koclip
KoCLIP: Korean port of OpenAI CLIP, in Flax
image_recapture_detection
AutoEncoder trained on ImageNet
Parametric-Contrastive-Learning
Parametric Contrastive Learning (ICCV2021)
productive-box
Are you an early 🐤 or a night 🦉? Let's check out in gist
VL-LTR
VL-LTR: Learning Class-wise Visual-Linguistic Representation for Long-Tailed Visual Recognition
ALBEF
Code for ALBEF: a new vision-language pre-training method
DECA
DECA: Detailed Expression Capture and Animation (SIGGRAPH 2021)
nerfies
This is the code for Deformable Neural Radiance Fields, a.k.a. Nerfies.