Linear evaluation

Benchmarks archive 2025-07-28

No benchmark for this task in the archive.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

2 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 78 papers with code (128 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Emerging Properties in Self-Supervised Vision Transformers
  29 Apr 2021 32 repositories listed Syntology ran 5 of 20 samples · 15 unverified · 2 pointer-only (licence)
  In this paper, we question if self-supervised learning provides new properties to Vision Transformer (ViT) that stand out compared to convolutional networks (convnets).
• Bootstrap your own latent: A new approach to self-supervised Learning
  13 Jun 2020 31 repositories listed Syntology ran 62 of 79 samples · 17 unverified · 46 pointer-only (licence)
  From an augmented view of an image, we train the online network to predict the target network representation of the same image under a different augmented view.
• Bootstrap Your Own Latent - A New Approach to Self-Supervised Learning
  1 Dec 2020 8 repositories listed
  From an augmented view of an image, we train the online network to predict the target network representation of the same image under a different augmented view.
• Self-Supervised Learning with Swin Transformers
  10 May 2021 6 repositories listed
  We are witnessing a modeling shift from CNN to Transformers in computer vision.
• Contrastive Multi-View Representation Learning on Graphs
  10 Jun 2020 5 repositories listed Syntology ran 16 of 22 samples · 6 unverified · 9 pointer-only (licence)
  We achieve new state-of-the-art results in self-supervised learning on 8 out of 8 node and graph classification benchmarks under the linear evaluation protocol.
• Solo-learn: A Library of Self-supervised Methods for Visual Representation Learning
  3 Aug 2021 4 repositories listed Syntology ran 4 of 10 samples · 6 unverified
  This paper presents solo-learn, a library of self-supervised methods for visual representation learning.
• Multi-modal Masked Siamese Network Improves Chest X-Ray Representation Learning
  5 Jul 2024 3 repositories listed
  We evaluate our approach on three publicly available chest X-ray datasets, MIMIC-CXR, CheXpert, and NIH-14, using two vision transformer (ViT) backbones, specifically ViT-Tiny and ViT-Small.
• Matrix Information Theory for Self-Supervised Learning
  27 May 2023 3 repositories listed Syntology ran 5 of 5 samples · 0 unverified · 5 pointer-only (licence)
  Inspired by this framework, we introduce Matrix-SSL, a novel approach that leverages matrix information theory to interpret the maximum entropy encoding loss as matrix uniformity loss.
• BYOL works even without batch statistics
  20 Oct 2020 3 repositories listed Syntology ran 5 of 5 samples · 0 unverified · 3 pointer-only (licence)
  Bootstrap Your Own Latent (BYOL) is a self-supervised learning approach for image representation.
• Learning Representations by Maximizing Mutual Information Across Views
  3 Jun 2019 3 repositories listed Syntology ran 8 of 11 samples · 3 unverified · 3 pointer-only (licence)
  Following our proposed approach, we develop a model which learns image representations that significantly outperform prior methods on the tasks we consider.
• M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation
  4 Jun 2024 2 repositories listed
  Here, we explore a new representation, a general-purpose audio-language representation, that performs well in both ZS and transfer learning.
• Masked Modeling Duo: Towards a Universal Audio Pre-training Framework
  9 Apr 2024 2 repositories listed Syntology ran 7 of 7 samples · 0 unverified · 7 pointer-only (licence)
  This study proposes Masked Modeling Duo (M2D), an improved masked prediction SSL, which learns by predicting representations of masked input signals that serve as training signals.
• Beyond Random Augmentations: Pretraining with Hard Views
  5 Oct 2023 2 repositories listed
  To achieve this invariance, conventional approaches make use of random sampling operations within the image augmentation pipeline.
• Similarity Contrastive Estimation for Image and Video Soft Contrastive Self-Supervised Learning
  21 Dec 2022 2 repositories listed
  A good data representation should contain relations between the instances, or semantic similarity and dissimilarity, that contrastive learning harms by considering all negatives as noise.
• Self-supervised Contrastive Representation Learning for Semi-supervised Time-Series Classification
  13 Aug 2022 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  Specifically, we propose time-series specific weak and strong augmentations and use their views to learn robust temporal relations in the proposed temporal contrasting module, besides learning discriminative…
• Bridging Video-text Retrieval with Multiple Choice Questions
  13 Jan 2022 2 repositories listed Syntology ran 13 of 24 samples · 11 unverified · 6 pointer-only (licence)
  As an additional benefit, our method achieves competitive results with much shorter pre-training videos on single-modality downstream tasks, e.
• Similarity Contrastive Estimation for Self-Supervised Soft Contrastive Learning
  29 Nov 2021 2 repositories listed
  To circumvent this issue, we propose a novel formulation of contrastive learning using semantic similarity between instances called Similarity Contrastive Estimation (SCE).
• When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?
  1 Nov 2021 2 repositories listed Syntology ran 3 of 12 samples · 9 unverified
  We show that AdvCL is able to enhance cross-task robustness transferability without loss of model accuracy and finetuning efficiency.
• Lesion-based Contrastive Learning for Diabetic Retinopathy Grading from Fundus Images
  17 Jul 2021 2 repositories listed
  Instead of taking entire images as the input in the common contrastive learning scheme, lesion patches are employed to encourage the feature extractor to learn representations that are highly discriminative for DR…
• A Broad Study on the Transferability of Visual Representations with Contrastive Learning
  24 Mar 2021 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  Tremendous progress has been made in visual representation learning, notably with the recent success of self-supervised contrastive learning methods.
• Self-Adaptive Training: Bridging Supervised and Self-Supervised Learning
  21 Jan 2021 2 repositories listed
  We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training processes by model predictions without incurring an extra computational cost -- to advance both…
• AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries
  17 Nov 2020 2 repositories listed Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
  Contrastive learning relies on constructing a collection of negative examples that are sufficiently hard to discriminate against positive queries when their representations are self-trained.
• CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients
  27 May 2020 2 repositories listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  This data can be exploited via contrastive learning, a self-supervised pre-training method that encourages representations of instances to be similar to one another.
• How Useful is Self-Supervised Pretraining for Visual Tasks?
  31 Mar 2020 2 repositories listed Syntology ran 2 of 4 samples · 2 unverified
  We investigate what factors may play a role in the utility of these pretraining methods for practitioners.
• SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes
  13 Jun 2025 1 repository listed Syntology ran 5 of 7 samples · 2 unverified
  We thoroughly evaluate SSLAM on standard audio SSL benchmark datasets which are predominantly monophonic and conduct a comprehensive comparative analysis against SOTA methods using a range of high-quality, publicly…
• Frequency-Masked Embedding Inference: A Non-Contrastive Approach for Time Series Representation Learning
  30 Dec 2024 1 repository listed
  To fundamentally overcome the limitations of contrastive learning, this paper introduces Frequency-masked Embedding Inference (FEI), a novel non-contrastive method that completely eliminates the need for positive and…
• Self-supervised learning for radio-astronomy source classification: a benchmark
  21 Nov 2024 1 repository listed
  This study explores the application of SSL to radio astronomy, comparing the performance of SSL-trained models with that of traditional models pretrained on natural images, evaluating the importance of data curation for…
• SynCo: Synthetic Hard Negatives in Contrastive Learning for Better Unsupervised Visual Representations
  3 Oct 2024 1 repository listed
  Our synthetic hard negative generation approach significantly enhances visual representations learned through self-supervised contrastive learning.
• Contrastive Learning with Synthetic Positives
  30 Aug 2024 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  In this paper, we introduce a novel approach called Contrastive Learning with Synthetic Positives (CLSP) that utilizes synthetic images, generated by an unconditional diffusion model, as the additional positives to help…
• Weakly Contrastive Learning via Batch Instance Discrimination and Feature Clustering for Small Sample SAR ATR
  7 Aug 2024 1 repository listed
  Technically, instance labels are assigned to the unlabeled data in per batch and random augmentation and training are performed few times on these augmented data.

Syntology lines on 17 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.