Real-time and accurate open-vocabulary end-to-end object detection
Continuation of an abandoned project fast-coco-eval
This repository contains the implementation for the paper "Revisiting Few Shot Object Detection with Vision-Language Models"
D2Det using mmdetection v2.1, supporting Objects365 and LVIS
DiverGen (CVPR 2024) & BSGAL (ICML 2024)
[ICCV 2021] MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection
[ECCV2022] Gumbel Optimised Loss for Long Tailed Instance Segmentation.
Perception evaluation toolkit in Rust with Python bindings. A pycocotools drop-in for COCO, LVIS, and Open Images detection metrics, up to 36× faster, plus TIDE error analysis, confusion matrices, calibration, model comparison, and a dataset browser.
[TIP 2023] Inverse Image Frequency for long-tailed image recognition.
Grid laser-shot-based LVIS L2 data from NASA into raster data
OVDeploy-Bench: EpisodicAP v2 + OOV-FP for deployment-style open-vocabulary detection
A YOLO instance segmentation model in practice. Identifying and outlining common objects in images.
To associate your repository with the lvis topic, visit your repo's landing page and select "manage topics."