How jindongwang/transferlearning works
This repository is a curated transfer-learning resource, not one integrated application. Its code directory contains independent implementations and experiment entry points for domain adaptation, domain generalization, speech and vision transfer, classical methods, and robustness/pruning. Thus there is no single user-to-result runtime workflow; each experiment generally selects data and a method, then trains or evaluates it. The graph highlights these distinct branches and selected internal layers. Relationships are included only where the README or source index supports them; many listed implementations were not sampled, so their internal wiring is omitted.
Main entry points: analyze_coverage.py Coverage analysis · a-domainbed/main.py CSG experiment · models.py Transfer model · DeepDA/main.py DeepDA runner
Components 30
Domain adaptation
- DeepDA runner
code/DeepDA/main.py - Domain data
code/DeepDA/data_loader.py - Transfer model
code/DeepDA/models.py - Transfer losses
code/DeepDA/transfer_losses.py - Feature backbones
code/DeepDA/backbones.py - DAAN training
code/deep/DAAN/train.py - DeepMEDA training
code/deep/DeepMEDA/main.py - DeepMEDA model
code/deep/DeepMEDA/deep_meda.py - DaNN training
code/deep/DaNN/main.py - DaNN network
code/deep/DaNN/DaNN.py
Generalization methods
- DeepDG runner
code/DeepDG/train.py - DG algorithms
code/DeepDG/alg/algs - DG data loaders
code/DeepDG/datautil - CSG experiment
code/deep/CSG/a-domainbed/main.py - CSG methods
code/deep/CSG/methods - CSG architectures
code/deep/CSG/arch/cnn.py - CSG data loading
code/deep/CSG/utils/preprocess/data_loader.py
Modalities and features
- Speech adaptation
code/ASR/Adapter/e2e_asr_adaptertransformer.py - Speech matching
code/ASR/CMatch/e2e_asr_udatransformer.py - CLIP experiments
code/clip/main.py - CLIP model wrapper
code/clip/clip_model.py - Image-text data
code/clip/data/data_loader.py - Feature extraction
code/feature_extractor/for_image_data/main.py
Classical methods
- Traditional methods
code/traditional
Robustness and pruning
- Coverage analysis
code/deep/ReMoS/CV_adv/nc_prune/analyze_coverage.py - Neuron coverage
code/deep/ReMoS/CV_adv/DNNtest/coverage/my_neuron_coverage.py - Model wrapper
code/deep/ReMoS/CV_adv/DNNtest/coverage/pytorch_wrapper.py - Neuron selection
code/deep/ReMoS/CV_adv/DNNtest/strategy/random.py - Vision datasets
code/deep/ReMoS/CV_adv/dataset - ResNet models
code/deep/ReMoS/CV_adv/model/fe_resnet.py
Connections 18
- DeepDA runner → Domain data: loads domains
code/DeepDA/main.py - DeepDA runner → Transfer model: builds model
code/DeepDA/main.py - Transfer model → Transfer losses: uses losses
code/DeepDA/models.py - Transfer model → Feature backbones: uses backbone
code/DeepDA/models.py - DeepDG runner → DG algorithms: selects algorithm
code/DeepDG/train.py - DeepDG runner → DG data loaders: gets loaders
code/DeepDG/train.py - CSG experiment → CSG data loading: loads data
code/deep/CSG/a-domainbed/main.py - CSG experiment → CSG methods: uses methods
- CSG experiment → CSG architectures: uses architectures
- DeepMEDA training → DeepMEDA model: builds model
code/deep/DeepMEDA/main.py - DaNN training → DaNN network: builds network
code/deep/DaNN/main.py - CLIP experiments → CLIP model wrapper: creates wrapper
code/clip/main.py - CLIP experiments → Image-text data: loads dataset
code/clip/main.py - Coverage analysis → Neuron coverage: uses coverage
code/deep/ReMoS/CV_adv/nc_prune/analyze_coverage.py - Coverage analysis → Model wrapper: wraps model
code/deep/ReMoS/CV_adv/nc_prune/analyze_coverage.py - Coverage analysis → Vision datasets: selects datasets
code/deep/ReMoS/CV_adv/nc_prune/analyze_coverage.py - Coverage analysis → ResNet models: loads network
code/deep/ReMoS/CV_adv/nc_prune/analyze_coverage.py - Coverage analysis → Neuron selection: selects neurons
code/deep/ReMoS/CV_adv/nc_prune/analyze_coverage.py