This paper presents the Axon AI's solution to the 2nd YouTube-8M Video Understanding Challenge, achieving the final global average precision (GAP) of 88.733% on the private test set (ranked 3rd among 394 teams, not considering the model size constraint), and 87.287% using a model that meets size requirement. Two sets of 7 individual models belonging to 3 different families were trained separately. Then, the inference results on a training data were aggregated from these multiple models and fed to train a compact model that meets the model size requirement. In order to further improve performance we explored and employed data over/sub-sampling in feature space, an additional regularization term during training exploiting label relationship, and learned weights for ensembling different individual models.
Deep learning-based semantic segmentation methods have an intrinsic limitation that training a model requires a large amount of data with pixel-level annotations. To address this challenging issue, many researchers give attention to unsupervised domain adaptation for semantic segmentation. Unsupervised domain adaptation seeks to adapt the model trained on the source domain to the target domain. In this paper, we introduce a self-ensembling technique, one of the successful methods for domain adaptation in classification. However, applying self-ensembling to semantic segmentation is very difficu…
Histopathology whole slide images (WSIs) can reveal significant inter-hospital variability such as illumination, color or optical artifacts. These variations, caused by the use of different scanning protocols across medical centers (staining, scanner), can strongly harm algorithms generalization on unseen protocols. This motivates development of new methods to limit such drop of performances. In this paper, to enhance robustness on unseen target protocols, we propose a new test-time data augmentation based on multi domain image-to-image translation. It allows to project images from unseen prot…
Samsung AI Center Moscow（三星莫斯科人工智能中心）；Swiss Federal Institute of Technology Lausanne (EPFL)（洛桑瑞士联邦理工学院（EPFL））；National Research University Higher School of Economics（国立研究型大学高等经济学院）
Averaging predictions over a set of models -- an ensemble -- is widely used to improve predictive performance and uncertainty estimation of deep learning models. At the same time, many machine learning systems, such as search, matching, and recommendation systems, heavily rely on embeddings. Unfortunately, due to misalignment of features of independently trained models, embeddings, cannot be improved with a naive deep ensemble like approach. In this work, we look at the ensembling of representations and propose mean embeddings with test-time augmentation (MeTTA) simple yet well-performing reci…
Google Research（谷歌研究院）；Brown University（布朗大学）；MIT（麻省理工学院）
We focus on contrastive methods for self-supervised video representation learning. A common paradigm in contrastive learning is to construct positive pairs by sampling different data views for the same instance, with different data instances as negatives. These methods implicitly assume a set of representational invariances to the view selection mechanism (eg, sampling frames with temporal shifts), which may lead to poor performance on downstream tasks which violate these invariances (fine-grained video action recognition that would benefit from temporal information). To overcome this limitati…
Recent self-supervised video representation learning methods focus on maximizing the similarity between multiple augmented views from the same video and largely rely on the quality of generated views. However, most existing methods lack a mechanism to prevent representation learning from bias towards static information in the video. In this paper, we propose frequency augmentation (FreqAug), a spatio-temporal data augmentation method in the frequency domain for video representation learning. FreqAug stochastically removes specific frequency components from the video so that learned representat…
Yonsei University（延世大学）；Cognex Deep Learning Lab（康耐视深度学习实验室）
Deep-Learning-based video recognition has shown promising improvements along with the development of large-scale datasets and spatiotemporal network architectures. In image recognition, learning spatially invariant features is a key factor in improving recognition performance and robustness. Data augmentation based on visual inductive priors, such as cropping, flipping, rotating, or photometric jittering, is a representative approach to achieve these features. Recent state-of-the-art recognition solutions have relied on modern data augmentation strategies that exploit a mixture of augmentation…
Recent generative models can synthesize "views" of artificial images that mimic real-world variations, such as changes in color or pose, simply by learning from unlabeled image collections. Here, we investigate whether such views can be applied to real images to benefit downstream analysis tasks such as image classification. Using a pretrained generator, we first find the latent code corresponding to a given real input image. Applying perturbations to the code creates natural variations of the image, which can then be ensembled together at test-time. We use StyleGAN2 as the source of generativ…
How We Won BraTS-SSA 2025: Brain Tumor Segmentation in the Sub-Saharan African Population Using Segmentation-Aware Data Augmentation and Model Ensembling
Kwame Nkrumah University of Science and Technology（卡布雷·克鲁马大学科学与技术大学）；University of Cape Coast（科克斯特大学）；University of Toronto（多伦多大学）；Department of Biomedical Engineering, McGill University（麦吉尔大学生物医学工程系）；Department of Physics, Federal University of Technology（联邦技术大学物理系）
A Multi-Stage Fine-Tuning and Ensembling Strategy for Pancreatic Tumor Segmentation in Diagnostic and Therapeutic MRI
German Cancer Research Center (DKFZ) Heidelberg（德国癌症研究中心（DKFZ）海德堡）；Faculty of Mathematics and Computer Science（数学与计算机科学学院）；Heidelberg University（海德堡大学）；Helmholtz Imaging, DKFZ（海德堡影像中心，DKFZ）；Pattern Analysis and Learning Group（模式分析与学习小组）；Department of Radiation Oncology（放射肿瘤科）；Heidelberg University Hospital（海德堡大学医院）；International School of Medicine（国际医学院）；Istanbul Medipol University（伊斯坦布尔梅迪波尔大学）
Indiana University Bloomington（印第安纳大学伯明顿分校）；Midea ETC（美的集团中央研究院）
Transferring knowledge across different datasets is an important approach to successfully train deep models with a small-scale target dataset or when few labeled instances are available. In this paper, we aim at developing a model that can generalize across multiple domain shifts, so that this model can adapt from a single source to multiple targets. This can be achieved by randomizing the generation of the data of various styles to mitigate the domain mismatch. First, we present a new adaptation to the CycleGAN model to produce stochastic style transfer between two image batches of different …
Robust White Blood Cell Classification with Stain-Normalized Decoupled Learning and Ensembling
University of Technology, Ho Chi Minh City, Vietnam（越南胡志明市技术大学）；University of Science, Ho Chi Minh City, Vietnam（越南胡志明市科学大学）；Vietnam National University, Ho Chi Minh City, Vietnam（越南国家大学）；Carnegie Mellon University, Pittsburgh, PA, USA（卡内基梅隆大学）；Northwestern University, Chicago, IL, USA（西北大学）
This document describes Pythia v0.1, the winning entry from Facebook AI Research (FAIR)'s A-STAR team to the VQA Challenge 2018. Our starting point is a modular re-implementation of the bottom-up top-down (up-down) model. We demonstrate that by making subtle but important changes to the model architecture and the learning rate schedule, fine-tuning image features, and adding data augmentation, we can significantly improve the performance of the up-down model on VQA v2.0 dataset -- from 65.67% to 70.22%. Furthermore, by using a diverse ensemble of models trained with different features and on d…
Mohamed Bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
Vision Transformers (ViT) are competing to replace Convolutional Neural Networks (CNN) for various computer vision tasks in medical imaging such as classification and segmentation. While the vulnerability of CNNs to adversarial attacks is a well-known problem, recent works have shown that ViTs are also susceptible to such attacks and suffer significant performance degradation under attack. The vulnerability of ViTs to carefully engineered adversarial samples raises serious concerns about their safety in clinical settings. In this paper, we propose a novel self-ensembling method to enhance the …
Graduate School of Engineering（研究生院）；University of Fukui（福井大学）
In the research field of activity recognition, although it is difficult to collect a large amount of measured sensor data, there has not been much discussion about data augmentation (DA). In this study, I propose Octave Mix as a new synthetic-style DA method for sensor-based activity recognition. Octave Mix is a simple DA method that combines two types of waveforms by intersecting low and high frequency waveforms using frequency decomposition. In addition, I propose a DA ensemble model and its training algorithm to acquire robustness to the original sensor data while remaining a wide variety o…
Technical University of Denmark（丹麦技术大学）；MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）
Data augmentation is a key element in training high-dimensional models. In this approach, one synthesizes new observations by applying pre-specified transformations to the original training data; e.g.~new images are formed by rotating old ones. Current augmentation schemes, however, rely on manual specification of the applied transformations, making data augmentation an implicit form of feature engineering. With an eye towards true end-to-end learning, we suggest learning the applied transformations on a per-class basis. Particularly, we align image pairs within each class under the assumption…
Data augmentation reduces the generalization error by forcing a model to learn invariant representations given different transformations of the input image. In computer vision, on top of the standard image processing functions, data augmentation techniques based on regional dropout such as CutOut, MixUp, and CutMix and policy-based selection such as AutoAugment demonstrated state-of-the-art (SOTA) results. With an increasing number of data augmentation algorithms being proposed, the focus is always on optimizing the input-output mapping while not realizing that there might be an untapped value…
Image segmentation is an important task in many medical applications. Methods based on convolutional neural networks attain state-of-the-art accuracy; however, they typically rely on supervised training with large labeled datasets. Labeling medical images requires significant expertise and time, and typical hand-tuned approaches for data augmentation fail to capture the complex variations in such images. We present an automated data augmentation method for synthesizing labeled medical images. We demonstrate our method on the task of segmenting magnetic resonance imaging (MRI) brain scans. Our …
Hon Hai Research Institute（鸿海研究院）；National Central University（国立中央大学）
In recent years, self-supervised learning has been studied to deal with the limitation of available labeled-dataset. Among the major components of self-supervised learning, the data augmentation pipeline is one key factor in enhancing the resulting performance. However, most researchers manually designed the augmentation pipeline, and the limited collections of transformation may cause the lack of robustness of the learned feature representation. In this work, we proposed Multi-Augmentations for Self-Supervised Representation Learning (MA-SSRL), which fully searched for various augmentation po…
Off-the-shelf convolutional neural network features achieve outstanding results in many image retrieval tasks. However, their invariance to target data is pre-defined by the network architecture and training data. Existing image retrieval approaches require fine-tuning or modification of pre-trained networks to adapt to variations unique to the target data. In contrast, our method enhances the invariance of off-the-shelf features by aggregating features extracted from images augmented at test-time, with augmentations guided by a policy learned through reinforcement learning. The learned policy…
Missouri State University（密苏里州立大学）；Tampere University（坦佩雷大学）
Bioimage classification plays a crucial role in many biological problems. In this work, we present a new General Purpose (GenP) ensemble that boosts performance by combining local features, dense sampling features, and deep learning approaches. First, we introduce three new methods for data augmentation based on PCA/DCT; second, we show that different data augmentation approaches can boost the performance of an ensemble of CNNs; and, finally, we propose a set of handcrafted/learned descriptors that are highly generalizable. Each handcrafted descriptor is used to train a different Support Vecto…
Existing methods based on meta-learning predict novel-class labels for (target domain) testing tasks via meta knowledge learned from (source domain) training tasks of base classes. However, most existing works may fail to generalize to novel classes due to the probably large domain discrepancy across domains. To address this issue, we propose a novel adversarial feature augmentation (AFA) method to bridge the domain gap in few-shot learning. The feature augmentation is designed to simulate distribution variations by maximizing the domain discrepancy. During adversarial training, the domain dis…
Delft University of Technology（代尔夫特理工大学）；University of Alcalá（阿尔卡拉大学）
We present the first edition of "VIPriors: Visual Inductive Priors for Data-Efficient Deep Learning" challenges. We offer four data-impaired challenges, where models are trained from scratch, and we reduce the number of training samples to a fraction of the full set. Furthermore, to encourage data efficient solutions, we prohibited the use of pre-trained models and other transfer learning techniques. The majority of top ranking solutions make heavy use of data augmentation, model ensembling, and novel and efficient network architectures to achieve significant performance increases compared to …
PETR: Prompt Ensembling with Training-free Routing for Vision-Language Models
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所多模态人工智能系统国家重点实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Purple Mountain Laboratories（紫金山实验室）；Beijing University of Posts and Telecommunications（北京邮电大学）
A common practice in unsupervised representation learning is to use labeled data to evaluate the quality of the learned representations. This supervised evaluation is then used to guide critical aspects of the training process such as selecting the data augmentation policy. However, guiding an unsupervised training process through supervised evaluations is not possible for real-world data that does not actually contain labels (which may be the case, for example, in privacy sensitive fields such as medical imaging). Therefore, in this work we show that evaluating the learned representations wit…
University of Edinburgh（爱丁堡大学）；Samsung AI Research（三星人工智能研究院）
Self-supervised learning is a powerful paradigm for representation learning on unlabelled images. A wealth of effective new methods based on instance matching rely on data-augmentation to drive learning, and these have reached a rough agreement on an augmentation scheme that optimises popular recognition benchmarks. However, there is strong reason to suspect that different tasks in computer vision require features to encode different (in)variances, and therefore likely require different augmentation strategies. In this paper, we measure the invariances learned by contrastive methods and confir…
Data augmentation is a critical component of training deep learning models. Although data augmentation has been shown to significantly improve image classification, its potential has not been thoroughly investigated for object detection. Given the additional cost for annotating images for object detection, data augmentation may be of even greater importance for this computer vision task. In this work, we study the impact of data augmentation on object detection. We first demonstrate that data augmentation operations borrowed from image classification may be helpful for training detection model…
Deep learning models with large learning capacities often overfit to medical imaging datasets. This is because training sets are often relatively small due to the significant time and financial costs incurred in medical data acquisition and labelling. Data augmentation is therefore often used to expand the availability of training data and to increase generalization. However, augmentation strategies are often chosen on an ad-hoc basis without justification. In this paper, we present an augmentation policy search method with the goal of improving model classification performance. We include in …
Goethe University Frankfurt（法兰克福歌德大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
Recently, a number of new Semi-Supervised Learning methods have emerged. As the accuracy for ImageNet and similar datasets increased over time, the performance on tasks beyond the classification of natural images is yet to be explored. Most Semi-Supervised Learning methods rely on a carefully manually designed data augmentation pipeline that is not transferable for learning on images of other domains. In this work, we propose a Semi-Supervised Learning method that automatically selects the most effective data augmentation policy for a particular dataset. We build upon the Fixmatch method and e…
Istituto Italiano di Tecnologia（意大利理工学院）；Stanford University（斯坦福大学）；Università di Verona（维罗纳大学）
Recent works showed that Generative Adversarial Networks (GANs) can be successfully applied in unsupervised domain adaptation, where, given a labeled source dataset and an unlabeled target dataset, the goal is to train powerful classifiers for the target samples. In particular, it was shown that a GAN objective function can be used to learn target features indistinguishable from the source ones. In this work, we extend this framework by (i) forcing the learned feature extractor to be domain-invariant, and (ii) training it through data augmentation in the feature space, namely performing featur…
Unsupervised Anomaly detection (AD) requires building a notion of normalcy, distinguishing in-distribution (ID) and out-of-distribution (OOD) data, using only available ID samples. Recently, large gains were made on this task for the domain of natural images using self-supervised contrastive feature learning as a first step followed by kNN or traditional one-class classifiers for feature scoring. Learned representations that are non-uniformly distributed on the unit hypersphere have been shown to be beneficial for this task. We go a step further and investigate how the \emph {geometrical compa…
This paper describes our approach to the DSTL Satellite Imagery Feature Detection challenge run by Kaggle. The primary goal of this challenge is accurate semantic segmentation of different classes in satellite imagery. Our approach is based on an adaptation of fully convolutional neural network for multispectral data processing. In addition, we defined several modifications to the training objective and overall training pipeline, e.g. boundary effect estimation, also we discuss usage of data augmentation strategies and reflectance indices. Our solution scored third place out of 419 entries. It…
To perform well on unseen and potentially out-of-distribution samples, it is desirable for machine learning models to have a predictable response with respect to transformations affecting the factors of variation of the input. Here, we study the relative importance of several types of inductive biases towards such predictable behavior: the choice of data, their augmentations, and model architectures. Invariance is commonly achieved through hand-engineered data augmentation, but do standard data augmentations address transformations that explain variations in real data? While prior work has foc…
University of Milano – Bicocca（米兰比可卡大学）；Computer Vision Center（计算机视觉中心）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）；University of Florence（佛罗伦萨大学）
Several recent works on self-supervised learning are trained by mapping different augmentations of the same image to the same feature representation. The data augmentations used are of crucial importance to the quality of learned feature representations. In this paper, we analyze how the color jitter traditionally used in data augmentation negatively impacts the quality of the color features in learned feature representations. To address this problem, we propose a more realistic, physics-based color data augmentation - which we call Planckian Jitter - that creates realistic variations in chrom…
Data augmentation is a commonly used approach to improving the generalization of deep learning models. Recent works show that learned data augmentation policies can achieve better generalization than hand-crafted ones. However, most of these works use unified augmentation policies for all samples in a dataset, which is observed not necessarily beneficial for all labels in multi-label classification tasks, i.e., some policies may have negative impacts on some labels while benefitting the others. To tackle this problem, we propose a novel Label-Based AutoAugmentation (LB-Aug) method for multi-la…
Rutgers University（罗格斯大学）；IBM Research AI（IBM人工智能研究院）
Data augmentation is one of the most important tools in training modern deep neural networks. Recently, great advances have been made in searching for optimal augmentation policies in the image classification domain. However, two key points related to data augmentation remain uncovered by the current methods. First is that most if not all modern augmentation search methods are offline and learning policies are isolated from their usage. The learned policies are mostly constant throughout the training process and are not adapted to the current training model state. Second, the policies rely on …
Escola Politècnica Superior, Universitat de Girona（赫罗纳大学高等理工学院）
Fully automatic detection of skin lesions in dermatoscopic images can facilitate early diagnosis and repression of malignant melanoma and non-melanoma skin cancer. Although convolutional neural networks are a powerful solution, they are limited by the illumination spectrum of annotated dermatoscopic screening images, where color is an important discriminative feature. In this paper, we propose an adaptive color augmentation technique to amplify data expression and model performance, while regulating color difference and saturation to minimize the risks of using synthetic data. Through deep vis…
Learning self-supervised video representation predominantly focuses on discriminating instances generated from simple data augmentation schemes. However, the learned representation often fails to generalize over unseen camera viewpoints. To this end, we propose ViewCLR, that learns self-supervised video representation invariant to camera viewpoint changes. We introduce a view-generator that can be considered as a learnable augmentation for any self-supervised pre-text tasks, to generate latent viewpoint representation of a video. ViewCLR maximizes the similarities between the latent viewpoint …
Samsung AI Center Moscow（三星莫斯科人工智能中心）；Samsung-HSE Laboratory, National Research University Higher School of Economics（国立研究型大学高等经济学院三星-高等经济学院实验室）；National Research University Higher School of Economics（国立研究型大学高等经济学院）；Skolkovo Institute of Science and Technology（斯科尔科沃科学技术研究院）
Test-time data augmentation$-$averaging the predictions of a machine learning model across multiple augmented samples of data$-$is a widely used technique that improves the predictive performance. While many advanced learnable data augmentation techniques have emerged in recent years, they are focused on the training phase. Such techniques are not necessarily optimal for test-time augmentation and can be outperformed by a policy consisting of simple crops and flips. The primary goal of this paper is to demonstrate that test-time augmentation policies can be successfully learned too. We introdu…
Human-designed data augmentation strategies have been replaced by automatically learned augmentation policy in the past two years. Specifically, recent work has empirically shown that the superior performance of the automated data augmentation methods stems from increasing the diversity of augmented data \cite{autoaug, randaug}. However, two factors regarding the diversity of augmented data are still missing: 1) the explicit definition (and thus measurement) of diversity and 2) the quantifiable relationship between diversity and its regularization effects. To bridge this gap, we propose a dive…
IIIT Hyderabad（海得拉巴国际信息技术学院）；Queensland University of Technology（昆士兰科技大学）
Sparse local feature matching is pivotal for many computer vision and robotics tasks. To improve their invariance to challenging appearance conditions and viewing angles, and hence their usefulness, existing learning-based methods have primarily focused on data augmentation-based training. In this work, we propose an alternative, complementary approach that centers on inducing bias in the model architecture itself to generate `rotation-specific' features using Steerable E2-CNNs, that are then group-pooled to achieve rotation-invariant local features. We demonstrate that this high performance, …
