awesome-repositories.com
Blog
MCP
awesome-repositories.com

Discover the best open-source repositories with AI-powered search.

ExploreCurated searchesOpen-source alternativesSelf-hosted softwareBlogSitemap
ProjectMCP serverAboutHow we rankPress
LegalPrivacyTerms
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
PrasannaPulakurthi avatar

PrasannaPulakurthi/Foreground-Background-Augmentation

0
View on GitHub↗
9 stars·0 forks·Python·MIT·7 viewsdoi.org/10.1117/12.3058627↗

Foreground Background Augmentation

ReID + SFDA - Dual-Region Augmentation (Foreground Noise + Background Shuffle) for robust person re-identification (ReID) and source-free domain adaptation (SFDA).

Features

  • Multi-Target Adaptation - Dual-region augmentation for reduced labeled data reliance.
  • Person Re-identification - Dual-region augmentation to reduce reliance on labeled data.
  • Source Free Domain Adaptation - Dual-region augmentation for data-efficient source-free adaptation.

Star history

Star history chart for prasannapulakurthi/foreground-background-augmentationStar history chart for prasannapulakurthi/foreground-background-augmentation

How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.

AI search

Explore more awesome repositories

Describe what you need in plain English — the AI ranks thousands of curated open-source projects by relevance.

Start searching with AI

Frequently asked questions

What does prasannapulakurthi/foreground-background-augmentation do?

ReID + SFDA - Dual-Region Augmentation (Foreground Noise + Background Shuffle) for robust person re-identification (ReID) and source-free domain adaptation (SFDA).

What are the main features of prasannapulakurthi/foreground-background-augmentation?

The main features of prasannapulakurthi/foreground-background-augmentation are: Multi-Target Adaptation, Person Re-identification, Source Free Domain Adaptation.

Which projects share features with prasannapulakurthi/foreground-background-augmentation?

Projects with overlapping indexed features include: vcl-iisc/conmix — Source free Single and Multi target Unsupervised Domain Adaptation. prasannapulakurthi/spm — Shuffle PatchMix (SPM) for Source-Free Domain Adaptation (ICIP 2025); patch-shuffle augmentation + confidence-margin… kaiyangzhou/deep-person-reid — This project is a PyTorch person re-identification framework designed for training and evaluating models that identify… thuml/transfer-learning-library — This project is a comprehensive library for transfer learning and domain adaptation in computer vision. It serves as a… nwojke/deep_sort — DeepSORT is a real-time multi-object tracking framework designed to maintain consistent identities of multiple objects… helioszhao/m3l — Pytorch implementation for M^3L. CVPR 2021.

Projects sharing features with Foreground Background Augmentation

These projects share indexed features with Foreground Background Augmentation. Shared tags can include platform or build tooling; verify the primary use case before treating a result as a replacement.
  • vcl-iisc/conmixvcl-iisc avatar

    vcl-iisc/CoNMix

    19View on GitHub↗

    Source free Single and Multi target Unsupervised Domain Adaptation

    Python
    View on GitHub↗19
  • prasannapulakurthi/spmPrasannaPulakurthi avatar

    PrasannaPulakurthi/SPM

    4View on GitHub↗

    Shuffle PatchMix (SPM) for Source-Free Domain Adaptation (ICIP 2025); patch-shuffle augmentation confidence-margin pseudo-labels. New SOTA on PACS (+7.3%), strong results on DomainNet-126 and VisDA-C.

    Python
    View on GitHub↗4
  • kaiyangzhou/deep-person-reidKaiyangZhou avatar

    KaiyangZhou/deep-person-reid

    4,849View on GitHub↗

    This project is a PyTorch person re-identification framework designed for training and evaluating models that identify individuals across different camera views. It provides a complete model training pipeline, a deep learning feature extractor for converting images into numeric vectors, and a suite of computer vision benchmarking tools to measure identity retrieval accuracy. The framework includes a specialized transfer learning toolkit that supports layer freezing, staged learning rate optimization, and differential learning rates for fine-tuning pretrained models. It distinguishes itself th

    Pythoncomputer-visioncross-domaindeep-learning
    View on GitHub↗4,849
  • nwojke/deep_sortnwojke avatar

    nwojke/deep_sort

    6,148View on GitHub↗

    DeepSORT is a real-time multi-object tracking framework designed to maintain consistent identities of multiple objects across video frames. It integrates deep learning appearance features with motion descriptors to track objects through a sequence of video data. The system uses a deep convolutional neural network to generate high-dimensional visual descriptors for person re-identification. These appearance features are combined with motion estimation via Kalman filtering and solved using the Hungarian algorithm to optimally associate detections with existing tracks. The framework includes ca

    Python
    View on GitHub↗6,148
Compare all 24 related projects→