Image Augmentation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

1 leaderboard table shown for this task, 1 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

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

1 dataset 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.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 127 papers with code (308 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.

• AutoAugment: Learning Augmentation Policies from Data
  24 May 2018 33 repositories listed Syntology ran 6 of 43 samples · 37 unverified · 2 pointer-only (licence)
  In our implementation, we have designed a search space where a policy consists of many sub-policies, one of which is randomly chosen for each image in each mini-batch.
• Improved Regularization of Convolutional Neural Networks with Cutout
  15 Aug 2017 28 repositories listed Syntology ran 21 of 24 samples · 3 unverified · 5 pointer-only (licence)
  Convolutional neural networks are capable of learning powerful representational spaces, which are necessary for tackling complex learning tasks.
• Unsupervised Data Augmentation for Consistency Training
  29 Apr 2019 20 repositories listed Syntology ran 15 of 52 samples · 37 unverified · 9 pointer-only (licence)
  In this work, we present a new perspective on how to effectively noise unlabeled examples and argue that the quality of noising, specifically those produced by advanced data augmentation methods, plays a crucial role in…
• Random Erasing Data Augmentation
  16 Aug 2017 18 repositories listed
  In this paper, we introduce Random Erasing, a new data augmentation method for training the convolutional neural network (CNN).
• Fast AutoAugment
  1 May 2019 11 repositories listed Syntology ran 22 of 40 samples · 18 unverified · 3 pointer-only (licence)
  Data augmentation is an essential technique for improving generalization ability of deep learning models.
• Learning Data Augmentation Strategies for Object Detection
  26 Jun 2019 6 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  Importantly, the best policy found on COCO may be transferred unchanged to other detection datasets and models to improve predictive accuracy.
• Augmentor: An Image Augmentation Library for Machine Learning
  11 Aug 2017 6 repositories listed
  The generation of artificial data based on existing observations, known as data augmentation, is a technique used in machine learning to improve model accuracy, generalisation, and to control overfitting.
• Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation
  13 Dec 2020 5 repositories listed Syntology ran 2 of 2 samples · 0 unverified
  Our baseline model outperforms the LVIS 2020 Challenge winning entry by +3.
• Kornia: an Open Source Differentiable Computer Vision Library for PyTorch
  5 Oct 2019 5 repositories listed Syntology ran 0 of 20 samples · 20 unverified
  This work presents Kornia -- an open source computer vision library which consists of a set of differentiable routines and modules to solve generic computer vision problems.
• Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels
  28 Apr 2020 4 repositories listed Syntology ran 6 of 10 samples · 4 unverified · 8 pointer-only (licence)
  We propose a simple data augmentation technique that can be applied to standard model-free reinforcement learning algorithms, enabling robust learning directly from pixels without the need for auxiliary losses or…
• Albumentations: fast and flexible image augmentations
  18 Sep 2018 4 repositories listed Syntology ran 0 of 10 samples · 10 unverified
  We provide examples of image augmentations for different computer vision tasks and show that Albumentations is faster than other commonly used image augmentation tools on the most of commonly used image transformations.
• Policy Gradient-Driven Noise Mask
  29 Apr 2024 3 repositories listed
  In this study, we propose a novel pretraining pipeline that learns to generate conditional noise mask specifically tailored to improve performance on multi-modal and multi-organ datasets.
• CascadeTabNet: An approach for end to end table detection and structure recognition from image-based documents
  27 Apr 2020 3 repositories listed Syntology ran 0 of 2 samples · 2 unverified
  In this paper, we present an improved deep learning-based end to end approach for solving both problems of table detection and structure recognition using a single Convolution Neural Network (CNN) model.
• Learn to Augment: Joint Data Augmentation and Network Optimization for Text Recognition
  14 Mar 2020 3 repositories listed
  An agent network learns from the output of the recognition network and controls the fiducial points to generate more proper training samples for the recognition network.
• Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules
  14 May 2019 3 repositories listed Syntology ran 0 of 18 samples · 18 unverified · 18 pointer-only (licence)
  A key challenge in leveraging data augmentation for neural network training is choosing an effective augmentation policy from a large search space of candidate operations.
• DenseNet Models for Tiny ImageNet Classification
  23 Apr 2019 3 repositories listed
  The architecture of the networks is designed based on the image resolution of this specific dataset and by calculating the Receptive Field of the convolution layers.
• 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.
• Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?
  10 Jun 2022 2 repositories listed Syntology ran 5 of 7 samples · 2 unverified
  We investigate whether self-supervised learning (SSL) can improve online reinforcement learning (RL) from pixels.
• Deep PCB To COCO Convertor
  1 May 2022 2 repositories listed
  It has 1500 image pairs.
• Improving the Transferability of Targeted Adversarial Examples through Object-Based Diverse Input
  17 Mar 2022 2 repositories listed Syntology ran 2 of 4 samples · 2 unverified
  To tackle this limitation, we propose the object-based diverse input (ODI) method that draws an adversarial image on a 3D object and induces the rendered image to be classified as the target class.
• Detectron2 Object Detection & Manipulating Images using Cartoonization
  1 Aug 2021 2 repositories listed
  In today's world, there is a rapid increase in the autonomous vehicle.
• Salient Objects in Clutter
  7 May 2021 2 repositories listed
  This design bias has led to a saturation in performance for state-of-the-art SOD models when evaluated on existing datasets.
• Multi-Disease Detection in Retinal Imaging based on Ensembling Heterogeneous Deep Learning Models
  26 Mar 2021 2 repositories listed
  Preventable or undiagnosed visual impairment and blindness affect billion of people worldwide.
• FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding
  10 Mar 2021 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  We present Few-Shot object detection via Contrastive proposals Encoding (FSCE), a simple yet effective approach to learning contrastive-aware object proposal encodings that facilitate the classification of detected…
• An Efficient and Scalable Deep Learning Approach for Road Damage Detection
  18 Nov 2020 2 repositories listed
  Pavement condition evaluation is essential to time the preventative or rehabilitative actions and control distress propagation.
• Prompt-Free Conditional Diffusion for Multi-object Image Augmentation
  8 Jul 2025 1 repository listed
  Specifically, we introduce a local-global semantic fusion strategy to extract semantics from images to replace text, and inject knowledge into the diffusion model through LoRA to alleviate the category deviation between…
• When Large Multimodal Models Confront Evolving Knowledge:Challenges and Pathways
  30 May 2025 1 repository listed Syntology ran 4 of 6 samples · 2 unverified · 2 pointer-only (licence)
  Previous work focused on constructing textual knowledge datasets and exploring knowledge injection in LLMs, lacking exploration of multimodal evolving knowledge injection in LMMs.
• Language-Driven Dual Style Mixing for Single-Domain Generalized Object Detection
  12 May 2025 1 repository listed
  Then, we propose image-level style mixing between the diversified images and source domain images.
• Batch Augmentation with Unimodal Fine-tuning for Multimodal Learning
  10 May 2025 1 repository listed
  We also prescribe pre-training initial layers with investigated medical data before the multimodal training.
• Effective Dual-Region Augmentation for Reduced Reliance on Large Amounts of Labeled Data
  17 Apr 2025 1 repository listed
  This paper introduces a novel dual-region augmentation approach designed to reduce reliance on large-scale labeled datasets while improving model robustness and adaptability across diverse computer vision tasks,…

Syntology lines on 15 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.