Stars
[TPAMI 2025] Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detection
[CVPR2025] AnomalyNCD: Towards Novel Anomaly Class Discovery in Industrial Scenarios. Paper is available at https://arxiv.org/abs/2410.14379
Paper list and datasets for industrial image anomaly/defect detection (updating). 工业异常/瑕疵检测论文及数据集检索库(持续更新)。
Object Detection using YOLOv8 trained on MS-COCO dataset (GUI included)
A Few-shot Object Detection Method for Remote Sensing Images
Multi-Faceted Distillation of Base-Novel Commonality for Few-shot Object Detection, ECCV 2022
[NeurIPS 2022] Decoupling Classifier for Boosting Few-shot Object Detection and Instance Segmentation
Code for reproducing the results in our TGRS-2024 paper Few-Shot Object Detection in Remote Sensing Images via Label-Consistent Classifier and Gradual Regression.
collection of few-shot papers
Learning and Building Convolutional Neural Networks using PyTorch
Official code of the paper "Fine-Grained Prototypes Distillation for Few-Shot Object Detection (AAAI 2024)"
Novel Instances Mining with Pseudo-Margin Evaluation for Few-Shot Object Detection
Leaderboard, taxonomy, and curated list of few-shot object detection papers.
Alignment Attention Fusion framework for Few-Shot Object Detection
Official implementation of the paper 'Exploring Robust Features for Few-Shot Object Detection in Satellite Imagery'
Source code of paper "NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer"
PyTorch implementation of Deep Semantic Dictionary Learning for Multi-label Image Classification, AAAI 2021.
Official PyTorch code for ICCV 2023 paper 'Learning Adaptive Neighborhoods for Graph Neural Networks'.
"GraphSHA: Synthesizing Harder Samples for Class-Imbalanced Node Classification" in KDD'23
Latest paper about small object detection
FSANet: Feature-and-Spatial-Aligned Network for Tiny Object Detection in Remote Sensing Images (TGRS 2022)
This project provides an implementation for "Generalized Few-Shot Object Detection without Forgetting" (CVPR2021) on PyTorch.
FewX is an open-source toolbox on top of Detectron2 for data-limited instance-level recognition tasks.
Inner-IoU: More Effective Intersection over Union Loss with Auxiliary Bounding Box
[ECCV 2020] PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer
Collect some papers and datastes about few-shot object detection for computer vision.