Pith. sign in

REVIEW 9 cited by

Transferability in Deep Learning: A Survey

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2201.05867 v1 pith:S46HULF6 submitted 2022-01-15 cs.LG

Junguang Jiang , Yang Shu , Jianmin Wang , Mingsheng Long This is my paper · ORCID
classification cs.LG
keywords learningdeepknowledgetransferabilitysurveyabilityadaptationalgorithms
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The success of deep learning algorithms generally depends on large-scale data, while humans appear to have inherent ability of knowledge transfer, by recognizing and applying relevant knowledge from previous learning experiences when encountering and solving unseen tasks. Such an ability to acquire and reuse knowledge is known as transferability in deep learning. It has formed the long-term quest towards making deep learning as data-efficient as human learning, and has been motivating fruitful design of more powerful deep learning algorithms. We present this survey to connect different isolated areas in deep learning with their relation to transferability, and to provide a unified and complete view to investigating transferability through the whole lifecycle of deep learning. The survey elaborates the fundamental goals and challenges in parallel with the core principles and methods, covering recent cornerstones in deep architectures, pre-training, task adaptation and domain adaptation. This highlights unanswered questions on the appropriate objectives for learning transferable knowledge and for adapting the knowledge to new tasks and domains, avoiding catastrophic forgetting and negative transfer. Finally, we implement a benchmark and an open-source library, enabling a fair evaluation of deep learning methods in terms of transferability.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Tabular Image: a method to convert tabular data to images for convolutional neural networks

    cs.CE 2026-08 conditional novelty 6.0 of 10

    Converting tabular credit data into images with target-based feature allocation lets a 2D CNN match or beat XGBoost on large credit scoring benchmarks.

  2. Decomposing the Time Series Forecasting Pipeline: A Modular Approach for Time Series Representation, Information Extraction, and Projection

    cs.AI 2025-07 conditional novelty 6.0 of 10

    REP-Net, a modular pipeline of representation, memory, and projection modules, achieves competitive forecasting accuracy on seven multivariate benchmarks with lower computational cost.

  3. Human Heterogeneity Invariant Stress Sensing

    cs.LG 2025-06 conditional novelty 6.0 of 10

    HHISS uses person-wise pruning intersection, plus continuous-label regularization, to achieve state-of-the-art out-of-distribution stress detection across seven wearable datasets.

  4. Implementing transferable annealing protocols for combinatorial optimisation on neutral atom quantum processors: a case study on smart-charging of electric vehicles

    quant-ph 2024-11 conditional novelty 6.0 of 10

    Optimal Bayesian-designed annealing parameters transfer across similar maximum independent set graph instances, enabling a fixed protocol to be applied from small training graphs to unseen 100-qubit graphs on a Rydber...

  5. Towards Realistic Hand-Object Interaction with Gravity-Field Based Diffusion Bridge

    cs.CV 2025-09 conditional novelty 5.0 of 10

    A gravity-field and diffusion-based optimization refines hand-object contacts to reduce interpenetration and gaps while LLM text prompts guide contact regions.

  6. rETF-semiSL: Semi-Supervised Learning for Neural Collapse in Temporal Data

    cs.LG 2025-08 conditional novelty 5.0 of 10

    rETF-semiSL pre-trains encoders with a rotational equiangular tight frame classifier, center loss, and pseudo-labels, and reports gains in time series classification across LSTM, transformer, and state-space models.

  7. Class-based Subset Selection for Transfer Learning under Extreme Label Shift

    cs.LG 2024-12 conditional novelty 5.0 of 10

    A Wasserstein-distance linear program selects and reweights source classes to reduce transfer distance, improving few-shot target accuracy under extreme label shift including disjoint label sets.

  8. Understanding Knowledge Transferability for Transfer Learning: A Survey

    cs.LG 2025-07 conditional novelty 4.0 of 10

    A survey that classifies transferability metrics by knowledge modality (dataset vs. model) and granularity (task vs. instance), with a theoretical primer and applications to eight learning paradigms.

  9. Comprehensive and Comparative Analysis between Transfer Learning and Custom Built VGG and CNN-SVM Models for Wildfire Detection

    cs.CV 2024-11 conditional novelty 2.0 of 10

    Using pretrained VGG-16 and VGG-19 improved wildfire detection accuracy over small custom CNNs, but the study lacks error bars and released data.

Pith tools