Feature Augmentation for Self-supervised Contrastive Learning: A Closer Look
Shenzhen Institute of Advanced Technology, CAS（中国科学院深圳先进技术研究院）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Sangfor Technologies Inc.（深信服科技股份有限公司）
Self-supervised contrastive learning heavily relies on the view variance brought by data augmentation, so that it can learn a view-invariant pre-trained representation. Beyond increasing the view variance for contrast, this work focuses on improving the diversity of training data, to improve the generalization and robustness of the pre-trained models. To this end, we propose a unified framework to conduct data augmentation in the feature space, known as feature augmentation. This strategy is domain-agnostic, which augments similar features to the original ones and thus improves the data diversity. We perform a systematic investigation of various feature augmentation architectures, the gradient-flow skill, and the relationship between feature augmentation and traditional data augmentation. Our study reveals some practical principles for feature augmentation in self-contrastive learning. By integrating feature augmentation on the instance discrimination or the instance similarity paradigm, we consistently improve the performance of pre-trained feature learning and gain better generalization over the downstream image classification and object detection task.
We propose an augmentation policy for Contrastive Self-Supervised Learning (SSL) in the form of an already established Salient Image Segmentation technique entitled Global Contrast based Salient Region Detection. This detection technique, which had been devised for unrelated Computer Vision tasks, was empirically observed to play the role of an augmentation facilitator within the SSL protocol. This observation is rooted in our practical attempts to learn, by SSL-fashion, aerial imagery of solar panels, which exhibit challenging boundary patterns. Upon the successful integration of this techniq…
Carnegie Mellon University（卡内基梅隆大学）；Facebook AI Research（Facebook 人工智能研究院）
Self-supervised representation learning approaches have recently surpassed their supervised learning counterparts on downstream tasks like object detection and image classification. Somewhat mysteriously the recent gains in performance come from training instance classification models, treating each image and it's augmented versions as samples of a single class. In this work, we first present quantitative experiments to demystify these gains. We demonstrate that approaches like MOCO and PIRL learn occlusion-invariant representations. However, they fail to capture viewpoint and category instanc…
A data augmentation module is utilized in contrastive learning to transform the given data example into two views, which is considered essential and irreplaceable. However, the predetermined composition of multiple data augmentations brings two drawbacks. First, the artificial choice of augmentation types brings specific representational invariances to the model, which have different degrees of positive and negative effects on different downstream tasks. Treating each type of augmentation equally during training makes the model learn non-optimal representations for various downstream tasks and…
University of Science and Technology of China（中国科学技术大学）
Contrastive learning (CL) is a form of self-supervised learning and has been widely used for various tasks. Different from widely studied instance-level contrastive learning, pixel-wise contrastive learning mainly helps with pixel-wise tasks such as medical landmark detection. The counterpart to an instance in instance-level CL is a pixel, along with its neighboring context, in pixel-wise CL. Aiming to build better feature representation, there is a vast literature about designing instance augmentation strategies for instance-level CL; but there is little similar work on pixel augmentation for…
In this paper, we propose an augmentation-free graph contrastive learning framework, namely ACTIVE, to solve the problem of partial multi-view clustering. Notably, we suppose that the representations of similar samples (i.e., belonging to the same cluster) and their multiply views features should be similar. This is distinct from the general unsupervised contrastive learning that assumes an image and its augmentations share a similar representation. Specifically, relation graphs are constructed using the nearest neighbours to identify existing similar samples, then the constructed inter-instan…
The University of Tokyo（东京大学）；NTT Corporation（日本电报电话公司）
Rotation is frequently listed as a candidate for data augmentation in contrastive learning but seldom provides satisfactory improvements. We argue that this is because the rotated image is always treated as either positive or negative. The semantics of an image can be rotation-invariant or rotation-variant, so whether the rotated image is treated as positive or negative should be determined based on the content of the image. Therefore, we propose a novel augmentation strategy, adaptive Positive or Negative Data Augmentation (PNDA), in which an original and its rotated image are a positive pair…
University of Chinese Academy of Sciences（中国科学院大学）；Microsoft Research Asia（微软亚洲研究院）
Data augmentation is usually adopted to increase the amount of training data, prevent overfitting and improve the performance of deep models. However, in practice, random data augmentation, such as random image cropping, is low-efficiency and might introduce many uncontrolled background noises. In this paper, we propose Weakly Supervised Data Augmentation Network (WS-DAN) to explore the potential of data augmentation. Specifically, for each training image, we first generate attention maps to represent the object's discriminative parts by weakly supervised learning. Next, we augment the image g…
In this paper, we propose the $K$-Shot Contrastive Learning (KSCL) of visual features by applying multiple augmentations to investigate the sample variations within individual instances. It aims to combine the advantages of inter-instance discrimination by learning discriminative features to distinguish between different instances, as well as intra-instance variations by matching queries against the variants of augmented samples over instances. Particularly, for each instance, it constructs an instance subspace to model the configuration of how the significant factors of variations in $K$-shot…
Self-supervised skeleton-based action recognition with contrastive learning has attracted much attention. Recent literature shows that data augmentation and large sets of contrastive pairs are crucial in learning such representations. In this paper, we found that directly extending contrastive pairs based on normal augmentations brings limited returns in terms of performance, because the contribution of contrastive pairs from the normal data augmentation to the loss get smaller as training progresses. Therefore, we delve into hard contrastive pairs for contrastive learning. Motivated by the su…
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…
MetAug: Contrastive Learning via Meta Feature Augmentation
Institute of Software Chinese Academy of Sciences（中国科学院软件研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Southern Marine Science and Engineering Guangdong Laboratory (Guangzhou)（南方海洋科学与工程广东省实验室（广州））；Renmin University of China（中国人民大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；The Hong Kong University of Science and Technology（香港科技大学）
University of South China（南华大学）；Ulster University（阿尔斯特大学）；University of Science and Technology Beijing（北京科技大学）
While deep learning has contributed to the advancement of sensor-based Human Activity Recognition (HAR), it is usually a costly and challenging supervised task with the needs of a large amount of labeled data. To alleviate this issue, contrastive learning has been applied for sensor-based HAR. Data augmentation is an essential part of contrastive learning and has a significant impact on the performance of downstream tasks. However, current popular augmentation methods do not achieve competitive performance in contrastive learning for sensor-based HAR. Motivated by this issue, we propose a new …
Recent self-supervised contrastive methods have been able to produce impressive transferable visual representations by learning to be invariant to different data augmentations. However, these methods implicitly assume a particular set of representational invariances (e.g., invariance to color), and can perform poorly when a downstream task violates this assumption (e.g., distinguishing red vs. yellow cars). We introduce a contrastive learning framework which does not require prior knowledge of specific, task-dependent invariances. Our model learns to capture varying and invariant factors for v…
Superpixel Graph Contrastive Clustering with Semantic-Invariant Augmentations for Hyperspectral Images
School of Software Engineering, Southeast University（东南大学软件学院）；School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China（新一代人工智能技术及交叉应用关键实验室（东南大学））；Department of Computing and Information Sciences, Saint Francis University（圣弗朗西斯大学计算机与信息科学系）；Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系）
Pose estimation is usually tackled as either a bin classification or a regression problem. In both cases, the idea is to directly predict the pose of an object. This is a non-trivial task due to appearance variations between similar poses and similarities between dissimilar poses. Instead, we follow the key idea that comparing two poses is easier than directly predicting one. Render-and-compare approaches have been employed to that end, however, they tend to be unstable, computationally expensive, and slow for real-time applications. We propose doing category-level pose estimation by learning …
School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）；Artificial Intelligence Industrial Technology Research Institute, Nanjing Institute of Technology（南京工程学院人工智能产业技术研究院）；School of Computer Science, Nanjing University（南京大学计算机科学学院）
针对无监督骨骼动作识别中随机增强难以产生直接语义扰动且会软化正负对的问题，提出 A²MC，利用攻击增强生成困难正样本并由 PNM 混合生成困难负样本，在三个公开数据集上达到与 SOTA 相当的性能。
Contrastive learning of auditory and visual perception has been extremely successful when investigated individually. However, there are still major questions on how we could integrate principles learned from both domains to attain effective audiovisual representations. In this paper, we present a contrastive framework to learn audiovisual representations from unlabeled videos. The type and strength of augmentations utilized during self-supervised pre-training play a crucial role for contrastive frameworks to work sufficiently. Hence, we extensively investigate composition of temporal augmentat…
Data Augmentation of Contrastive Learning is Estimating Positive-incentive Noise
The University of Hong Kong（香港大学）；Institute of Artificial Intelligence (TeleAI), China Telecom（中国电信人工智能研究院）；Fudan University（复旦大学）；School of Artificial Intelligence, OPtics（人工智能学院）；ElectroNics (iOPEN), Northwestern Polytechnical University（西北工业大学电子学院）
What role do augmentations play in contrastive learning? Recent work suggests that good augmentations are label-preserving with respect to a specific downstream task. We complicate this picture by showing that label-destroying augmentations can be useful in the foundation model setting, where the goal is to learn diverse, general-purpose representations for multiple downstream tasks. We perform contrastive learning experiments on a range of image and audio datasets with multiple downstream tasks (e.g. for digits superimposed on photographs, predicting the class of one vs. the other). We find t…
Queen’s University（女王大学）；Ingenuity Labs Research Institute（英格纽蒂实验室研究院）
We propose a self-supervised contrastive learning approach for facial expression recognition (FER) in videos. We propose a novel temporal sampling-based augmentation scheme to be utilized in addition to standard spatial augmentations used for contrastive learning. Our proposed temporal augmentation scheme randomly picks from one of three temporal sampling techniques: (1) pure random sampling, (2) uniform sampling, and (3) sequential sampling. This is followed by a combination of up to three standard spatial augmentations. We then use a deep R(2+1)D network for FER, which we train in a self-sup…
Domain generalisation (DG) methods address the problem of domain shift, when there is a mismatch between the distributions of training and target domains. Data augmentation approaches have emerged as a promising alternative for DG. However, data augmentation alone is not sufficient to achieve lower generalisation errors. This project proposes a new method that combines data augmentation and domain distance minimisation to address the problems associated with data augmentation and provide a guarantee on the learning performance, under an existing framework. Empirically, our method outperforms b…
Samsung Semiconductor US（美国三星半导体）；National Yang Ming Chiao Tung University（国立阳明交通大学）
Point cloud data plays an essential role in robotics and self-driving applications. Yet, annotating point cloud data is time-consuming and nontrivial while they enable learning discriminative 3D representations that empower downstream tasks, such as classification and segmentation. Recently, contrastive learning-based frameworks have shown promising results for learning 3D representations in a self-supervised manner. However, existing contrastive learning methods cannot precisely encode and associate structural features and search the higher dimensional augmentation space efficiently. In this …
South China Agricultural University（华南农业大学）；Sun Yat-sen University（中山大学）
Deep clustering has attracted increasing attention in recent years due to its capability of joint representation learning and clustering via deep neural networks. In its latest developments, the contrastive learning has emerged as an effective technique to substantially enhance the deep clustering performance. However, the existing contrastive learning based deep clustering algorithms mostly focus on some carefully-designed augmentations (often with limited transformations to preserve the structure), referred to as weak augmentations, but cannot go beyond the weak augmentations to explore the …
Centrum Wiskunde & Informatica（荷兰数学与计算机科学研究中心）；University of Trieste（的里雅斯特大学）；Leiden University Medical Center（莱顿大学医学中心）；Delft University of Technology（代尔夫特理工大学）
Emotion recognition in children can help the early identification of, and intervention on, psychological complications that arise in stressful situations such as cancer treatment. Though deep learning models are increasingly being adopted, data scarcity is often an issue in pediatric medicine, including for facial emotion recognition in children. In this paper, we study the application of data augmentation-based contrastive learning to overcome data scarcity in facial emotion recognition for children. We explore the idea of ignoring generational gaps, by adding abundantly available adult data …
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
Recent works in Generative Adversarial Networks (GANs) are actively revisiting various data augmentation techniques as an effective way to prevent discriminator overfitting. It is still unclear, however, that which augmentations could actually improve GANs, and in particular, how to apply a wider range of augmentations in training. In this paper, we propose a novel way to address these questions by incorporating a recent contrastive representation learning scheme into the GAN discriminator, coined ContraD. This "fusion" enables the discriminators to work with much stronger augmentations withou…
The Chinese University of Hong Kong（香港中文大学）；Australian National University（澳大利亚国立大学）；Data61/CSIRO（Data61/澳大利亚联邦科学与工业研究组织）
Although augmentations (e.g., perturbation of graph edges, image crops) boost the efficiency of Contrastive Learning (CL), feature level augmentation is another plausible, complementary yet not well researched strategy. Thus, we present a novel spectral feature argumentation for contrastive learning on graphs (and images). To this end, for each data view, we estimate a low-rank approximation per feature map and subtract that approximation from the map to obtain its complement. This is achieved by the proposed herein incomplete power iteration, a non-standard power iteration regime which enjoys…
Representation learning has significantly been developed with the advance of contrastive learning methods. Most of those methods have benefited from various data augmentations that are carefully designated to maintain their identities so that the images transformed from the same instance can still be retrieved. However, those carefully designed transformations limited us to further explore the novel patterns exposed by other transformations. Meanwhile, as found in our experiments, the strong augmentations distorted the images' structures, resulting in difficult retrieval. Thus, we propose a ge…
Recently, contrastiveness-based augmentation surges a new climax in the computer vision domain, where some operations, including rotation, crop, and flip, combined with dedicated algorithms, dramatically increase the model generalization and robustness. Following this trend, some pioneering attempts employ the similar idea to graph data. Nevertheless, unlike images, it is much more difficult to design reasonable augmentations without changing the nature of graphs. Although exciting, the current graph contrastive learning does not achieve as promising performance as visual contrastive learning.…
Recently, contrastive learning has risen to be a promising approach for large-scale self-supervised learning. However, theoretical understanding of how it works is still unclear. In this paper, we propose a new guarantee on the downstream performance without resorting to the conditional independence assumption that is widely adopted in previous work but hardly holds in practice. Our new theory hinges on the insight that the support of different intra-class samples will become more overlapped under aggressive data augmentations, thus simply aligning the positive samples (augmented views of the …
Self-supervised learning aims to learn a embedding space where semantically similar samples are close. Contrastive learning methods pull views of samples together and push different samples away, which utilizes semantic invariance of augmentation but ignores the relationship between samples. To better exploit the power of augmentation, we observe that semantically similar samples are more likely to have similar augmented views. Therefore, we can take the augmented views as a special description of a sample. In this paper, we model such a description as the augmentation distribution and we call…
UT Austin（得克萨斯大学奥斯汀分校）；MIS, Germany（德国曼海姆应用科学大学）；Weill Cornell Medicine（威尔康奈尔医学院）
Computer-aided diagnosis plays a salient role in more accessible and accurate cardiopulmonary diseases classification and localization on chest radiography. Millions of people get affected and die due to these diseases without an accurate and timely diagnosis. Recently proposed contrastive learning heavily relies on data augmentation, especially positive data augmentation. However, generating clinically-accurate data augmentations for medical images is extremely difficult because the common data augmentation methods in computer vision, such as sharp, blur, and crop operations, can severely alt…
Google Research（谷歌研究院）；Cornell University（康奈尔大学）；Cornell Tech（康奈尔科技校区）
We present a self-supervised Contrastive Video Representation Learning (CVRL) method to learn spatiotemporal visual representations from unlabeled videos. Our representations are learned using a contrastive loss, where two augmented clips from the same short video are pulled together in the embedding space, while clips from different videos are pushed away. We study what makes for good data augmentations for video self-supervised learning and find that both spatial and temporal information are crucial. We carefully design data augmentations involving spatial and temporal cues. Concretely, we p…
Contrastive self-supervised learning has shown impressive results in learning visual representations from unlabeled images by enforcing invariance against different data augmentations. However, the learned representations are often contextually biased to the spurious scene correlations of different objects or object and background, which may harm their generalization on the downstream tasks. To tackle the issue, we develop a novel object-aware contrastive learning framework that first (a) localizes objects in a self-supervised manner and then (b) debias scene correlations via appropriate data …
DiffAug: Enhance Unsupervised Contrastive Learning with Domain-Knowledge-Free Diffusion-based Data Augmentation
Westlake University（西湖大学）；DAMO Academy, Alibaba Group（阿里巴巴集团达摩院）；National University of Singapore（新加坡国立大学）；Hupan Lab, Zhejiang Province（浙江省湖畔实验室）；AI Lab, Research Center for Industries of the Future, Westlake University（西湖大学未来产业研究中心人工智能实验室）
How can neural networks trained by contrastive learning extract features from the unlabeled data? Why does contrastive learning usually need much stronger data augmentations than supervised learning to ensure good representations? These questions involve both the optimization and statistical aspects of deep learning, but can hardly be answered by analyzing supervised learning, where the target functions are the highest pursuit. Indeed, in self-supervised learning, it is inevitable to relate to the optimization/generalization of neural networks to how they can encode the latent structures in th…
