Name: Open-LAMP(Learning and Machine Perception Lab.)
Type: Organization
Bio: LAMP evolves from Pri-SDL of UCAS, which focuses on frontier research in AI: Representation Learning, Weakly Supervised Learning, and Life-Long Learning.
Location: Beijing, China
Blog: http://lamp.ucas.ac.cn/
Open-LAMP(Learning and Machine Perception Lab.)'s Projects
Agreement-Discrepancy-Selection: Active Learning with Progressive Distribution Alignment
Code for Multiple Instance Active Learning for Object Detection, CVPR 2021
Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection
HFA: Harmonic Feature Activation for few-shot semantic segmentation.
Prototype Mixture Models for Few-shot Semantic Segmentation
Unofficial PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners
Beyond Bounding-Box: Convex-hull Feature Adaptation for Oriented and Densely Packed Object Detection(CVPR2021).
SIXray : A Large-scale Security Inspection X-ray Benchmark in CVPR 2019
FreeAnchor: Learning to Match Anchors for Visual Object Detection (NeurIPS 2019)
Image-Image Domain Adaptation with Preserved Self-Similarity and Domain-Dissimilarity for Person Re-identification in CVPR'18
A toolbox for object skeleton detection, can also be used for edge detection, building extraction and road extraction.
Side-output Residual Network for Object Symmetry Detection in the Wild
This is the implementation of our paper "Video Playback Rate Perception for Self-supervised Spatio-Temporal Representation Learning".
Selective Sparse Sampling for Fine-grained Image Recognition
Conformer: Local Features Coupling Global Representations for Visual Recognition
Oriented Response Networks, in CVPR 2017
Code for C-MIL: Continuation Multiple Instance Learning for Weakly Supervised Object Detection
DANet: Divergent Activation for Weakly Supervised Object Localization,in ICCV 2019
Weakly Supervised Instance Segmentation using Class Peak Response, in CVPR 2018 (Spotlight)
PyTorch implementation of "Soft Proposal Networks for Weakly Supervised Object Localization", ICCV 2017.
TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization