Self-supervised visual representation learning has seen huge progress recently, but no large scale evaluation has compared the many models now available. We evaluate the transfer performance of 13 top self-supervised models on 40 downstream tasks, including many-shot and few-shot recognition, object detection, and dense prediction. We compare their performance to a supervised baseline and show that on most tasks the best self-supervised models outperform supervision, confirming the recently observed trend in the literature. We find ImageNet Top-1 accuracy to be highly correlated with transfer to many-shot recognition, but increasingly less so for few-shot, object detection and dense prediction. No single self-supervised method dominates overall, suggesting that universal pre-training is still unsolved. Our analysis of features suggests that top self-supervised learners fail to preserve colour information as well as supervised alternatives, but tend to induce better classifier calibration, and less attentive overfitting than supervised learners.
Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）
A large gap exists between fully-supervised object detection and weakly-supervised object detection. To narrow this gap, some methods consider knowledge transfer from additional fully-supervised dataset. But these methods do not fully exploit discriminative category information in the fully-supervised dataset, thus causing low mAP. To solve this issue, we propose a novel category transfer framework for weakly supervised object detection. The intuition is to fully leverage both visually-discriminative and semantically-correlated category information in the fully-supervised dataset to enhance th…
Zhejiang University（浙江大学）；The University of Sydney（悉尼大学）；SenseTime Research（商汤科技研究院）；Qing Yuan Research Institute, Shanghai Jiao Tong University（上海交通大学清源研究院）
The pretrain-finetune paradigm is a classical pipeline in visual learning. Recent progress on unsupervised pretraining methods shows superior transfer performance to their supervised counterparts. This paper revisits this phenomenon and sheds new light on understanding the transferability gap between unsupervised and supervised pretraining from a multilayer perceptron (MLP) perspective. While previous works focus on the effectiveness of MLP on unsupervised image classification where pretraining and evaluation are conducted on the same dataset, we reveal that the MLP projector is also the key f…
University of Bern（伯尔尼大学）；University of Maryland Baltimore County（马里兰大学巴尔的摩县分校）
In self-supervised learning, one trains a model to solve a so-called pretext task on a dataset without the need for human annotation. The main objective, however, is to transfer this model to a target domain and task. Currently, the most effective transfer strategy is fine-tuning, which restricts one to use the same model or parts thereof for both pretext and target tasks. In this paper, we present a novel framework for self-supervised learning that overcomes limitations in designing and comparing different tasks, models, and data domains. In particular, our framework decouples the structure o…
Most existing approaches to training object detectors rely on fully supervised learning, which requires the tedious manual annotation of object location in a training set. Recently there has been an increasing interest in developing weakly supervised approach to detector training where the object location is not manually annotated but automatically determined based on binary (weak) labels indicating if a training image contains the object. This is a challenging problem because each image can contain many candidate object locations which partially overlaps the object of interest. Existing appro…
We investigate the direction of training a 3D object detector for new object classes from only 2D bounding box labels of these new classes, while simultaneously transferring information from 3D bounding box labels of the existing classes. To this end, we propose a transferable semi-supervised 3D object detection model that learns a 3D object detector network from training data with two disjoint sets of object classes - a set of strong classes with both 2D and 3D box labels, and another set of weak classes with only 2D box labels. In particular, we suggest a relaxed reprojection loss, box prior…
Technical University of Munich（慕尼黑工业大学）；Tongji University（同济大学）
State-of-the-art lidar-based 3D object detection methods rely on supervised learning and large labeled datasets. However, annotating lidar data is resource-consuming, and depending only on supervised learning limits the applicability of trained models. Self-supervised training strategies can alleviate these issues by learning a general point cloud backbone model for downstream 3D vision tasks. Against this backdrop, we show the relationship between self-supervised multi-frame flow representations and single-frame 3D detection hypotheses. Our main contribution leverages learned flow and motion …
Facebook AI Research（脸书人工智能研究院）；Inria（法国国家信息与自动化研究所）；Sorbonne University（索邦大学）
In this paper, we question if self-supervised learning provides new properties to Vision Transformer (ViT) that stand out compared to convolutional networks (convnets). Beyond the fact that adapting self-supervised methods to this architecture works particularly well, we make the following observations: first, self-supervised ViT features contain explicit information about the semantic segmentation of an image, which does not emerge as clearly with supervised ViTs, nor with convnets. Second, these features are also excellent k-NN classifiers, reaching 78.3% top-1 on ImageNet with a small ViT. …
In this paper, we propose a novel self-supervised representation learning method, Self-EMD, for object detection. Our method directly trained on unlabeled non-iconic image dataset like COCO, instead of commonly used iconic-object image dataset like ImageNet. We keep the convolutional feature maps as the image embedding to preserve spatial structures and adopt Earth Mover's Distance (EMD) to compute the similarity between two embeddings. Our Faster R-CNN (ResNet50-FPN) baseline achieves 39.8% mAP on COCO, which is on par with the state of the art self-supervised methods pre-trained on ImageNet.…
For a robot deployed in the world, it is desirable to have the ability of autonomous learning to improve its initial pre-set knowledge. We formalize this as a bootstrapped self-supervised learning problem where a system is initially bootstrapped with supervised training on a labeled dataset and we look for a self-supervised training method that can subsequently improve the system over the supervised training baseline using only unlabeled data. In this work, we leverage temporal consistency between frames in monocular video to perform this bootstrapped self-supervised training. We show that a w…
Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）；Honda Research Institute（本田研究院）
3D object trackers usually require training on large amounts of annotated data that is expensive and time-consuming to collect. Instead, we propose leveraging vast unlabeled datasets by self-supervised metric learning of 3D object trackers, with a focus on data association. Large scale annotations for unlabeled data are cheaply obtained by automatic object detection and association across frames. We show how these self-supervised annotations can be used in a principled manner to learn point-cloud embeddings that are effective for 3D tracking. We estimate and incorporate uncertainty in self-sup…
The goal of self-supervised learning from images is to construct image representations that are semantically meaningful via pretext tasks that do not require semantic annotations for a large training set of images. Many pretext tasks lead to representations that are covariant with image transformations. We argue that, instead, semantic representations ought to be invariant under such transformations. Specifically, we develop Pretext-Invariant Representation Learning (PIRL, pronounced as "pearl") that learns invariant representations based on pretext tasks. We use PIRL with a commonly used pret…
University of Arkansas（阿肯色大学）；Cyberlogitec Vietnam（越南赛博罗吉泰克公司）；VinAI（越南人工智能研究院）
Capsule network is a recent new deep network architecture that has been applied successfully for medical image segmentation tasks. This work extends capsule networks for volumetric medical image segmentation with self-supervised learning. To improve on the problem of weight initialization compared to previous capsule networks, we leverage self-supervised learning for capsule networks pre-training, where our pretext-task is optimized by self-reconstruction. Our capsule network, SS-3DCapsNet, has a UNet-based architecture with a 3D Capsule encoder and 3D CNNs decoder. Our experiments on multiple…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Microsoft（微软）
In this paper, we propose an effective knowledge transfer framework to boost the weakly supervised object detection accuracy with the help of an external fully-annotated source dataset, whose categories may not overlap with the target domain. This setting is of great practical value due to the existence of many off-the-shelf detection datasets. To more effectively utilize the source dataset, we propose to iteratively transfer the knowledge from the source domain by a one-class universal detector and learn the target-domain detector. The box-level pseudo ground truths mined by the target-domain…
This paper introduces a novel approach to leverage features learned from both supervised and self-supervised paradigms, to improve image classification tasks, specifically for vehicle classification. Two state-of-the-art self-supervised learning methods, DINO and data2vec, were evaluated and compared for their representation learning of vehicle images. The former contrasts local and global views while the latter uses masked prediction on multi-layered representations. In the latter case, supervised learning is employed to finetune a pretrained YOLOR object detector for detecting vehicle wheels…
Despite recent progress made by self-supervised methods in representation learning with residual networks, they still underperform supervised learning on the ImageNet classification benchmark, limiting their applicability in performance-critical settings. Building on prior theoretical insights from ReLIC [Mitrovic et al., 2021], we include additional inductive biases into self-supervised learning. We propose a new self-supervised representation learning method, ReLICv2, which combines an explicit invariance loss with a contrastive objective over a varied set of appropriately constructed data v…
Deep learning has led to great progress in the detection of mobile (i.e. movement-capable) objects in urban driving scenes in recent years. Supervised approaches typically require the annotation of large training sets; there has thus been great interest in leveraging weakly, semi- or self-supervised methods to avoid this, with much success. Whilst weakly and semi-supervised methods require some annotation, self-supervised methods have used cues such as motion to relieve the need for annotation altogether. However, a complete absence of annotation typically degrades their performance, and ambig…
Knowledge transfer using convolutional neural networks (CNNs) can help efficiently train a CNN with fewer parameters or maximize the generalization performance under limited supervision. To enable a more efficient transfer of pretrained knowledge under relaxed conditions, we propose a simple yet powerful knowledge transfer methodology without any restrictions regarding the network structure or dataset used, namely self-supervised knowledge transfer (SSKT), via loosely supervised auxiliary tasks. For this, we devise a training methodology that transfers previously learned knowledge to the curre…
Eindhoven University of Technology（埃因霍温理工大学）；Erasmus Medical Center（伊拉斯谟医学中心）；University of Copenhagen（哥本哈根大学）；University Medical Center Utrecht（乌得勒支大学医学中心）
Machine learning (ML) algorithms have made a tremendous impact in the field of medical imaging. While medical imaging datasets have been growing in size, a challenge for supervised ML algorithms that is frequently mentioned is the lack of annotated data. As a result, various methods which can learn with less/other types of supervision, have been proposed. We review semi-supervised, multiple instance, and transfer learning in medical imaging, both in diagnosis/detection or segmentation tasks. We also discuss connections between these learning scenarios, and opportunities for future research.
Huazhong University of Science and Technology（华中科技大学）
Self-supervised learning presents a remarkable performance to utilize unlabeled data for various video tasks. In this paper, we focus on applying the power of self-supervised methods to improve semi-supervised action proposal generation. Particularly, we design an effective Self-supervised Semi-supervised Temporal Action Proposal (SSTAP) framework. The SSTAP contains two crucial branches, i.e., temporal-aware semi-supervised branch and relation-aware self-supervised branch. The semi-supervised branch improves the proposal model by introducing two temporal perturbations, i.e., temporal feature …
Recently the focus of the computer vision community has shifted from expensive supervised learning towards self-supervised learning of visual representations. While the performance gap between supervised and self-supervised has been narrowing, the time for training self-supervised deep networks remains an order of magnitude larger than its supervised counterparts, which hinders progress, imposes carbon cost, and limits societal benefits to institutions with substantial resources. Motivated by these issues, this paper investigates reducing the training time of recent self-supervised methods by …
In past research on self-supervised learning for image classification, the use of rotation as an augmentation has been common. However, relying solely on rotation as a self-supervised transformation can limit the ability of the model to learn rich features from the data. In this paper, we propose a novel approach to self-supervised learning for image classification using several localizable augmentations with the combination of the gating method. Our approach uses flip and shuffle channel augmentations in addition to the rotation, allowing the model to learn rich features from the data. Furthe…
Limited availability of annotated medical imaging data poses a challenge for deep learning algorithms. Although transfer learning minimizes this hurdle in general, knowledge transfer across disparate domains is shown to be less effective. On the other hand, smaller architectures were found to be more compelling in learning better features. Consequently, we propose a lightweight architecture that uses mixed asymmetric kernels (MAKNet) to reduce the number of parameters significantly. Additionally, we train the proposed architecture using semi-supervised learning to provide pseudo-labels for a l…
Deep neural networks produce state-of-the-art results when trained on a large number of labeled examples but tend to overfit when small amounts of labeled examples are used for training. Creating a large number of labeled examples requires considerable resources, time, and effort. If labeling new data is not feasible, so-called semi-supervised learning can achieve better generalisation than purely supervised learning by employing unlabeled instances as well as labeled ones. The work presented in this paper is motivated by the observation that transfer learning provides the opportunity to poten…
Despite the recent success of video self-supervised learning models, there is much still to be understood about their generalization capability. In this paper, we investigate how sensitive video self-supervised learning is to the current conventional benchmark and whether methods generalize beyond the canonical evaluation setting. We do this across four different factors of sensitivity: domain, samples, actions and task. Our study which encompasses over 500 experiments on 7 video datasets, 9 self-supervised methods and 6 video understanding tasks, reveals that current benchmarks in video self-…
Computer Vision Center（计算机视觉中心）；Universitat Autònoma de Barcelona（巴塞罗那自治大学）
Self-supervised learning has been widely applied to train high-quality vision transformers. Unleashing their excellent performance on memory and compute constraint devices is therefore an important research topic. However, how to distill knowledge from one self-supervised ViT to another has not yet been explored. Moreover, the existing self-supervised knowledge distillation (SSKD) methods focus on ConvNet based architectures are suboptimal for ViT knowledge distillation. In this paper, we study knowledge distillation of self-supervised vision transformers (ViT-SSKD). We show that directly dist…
Super-Selfish is an easy to use PyTorch framework for image-based self-supervised learning. Features can be learned with 13 algorithms that span from simple classification to more complex state of theart contrastive pretext tasks. The framework is easy to use and allows for pretraining any PyTorch neural network with only two lines of code. Simultaneously, full flexibility is maintained through modular design choices. The code can be found at https://github.com/MECLabTUDA/Super_Selfish and installed using pip install super-selfish.
While self-supervised pretraining has proven beneficial for many computer vision tasks, it requires expensive and lengthy computation, large amounts of data, and is sensitive to data augmentation. Prior work demonstrates that models pretrained on datasets dissimilar to their target data, such as chest X-ray models trained on ImageNet, underperform models trained from scratch. Users that lack the resources to pretrain must use existing models with lower performance. This paper explores Hierarchical PreTraining (HPT), which decreases convergence time and improves accuracy by initializing the pre…
University of Science and Technology of China（中国科学技术大学）；Huawei Inc.（华为公司）
Recently, contrastive learning has largely advanced the progress of unsupervised visual representation learning. Pre-trained on ImageNet, some self-supervised algorithms reported higher transfer learning performance compared to fully-supervised methods, seeming to deliver the message that human labels hardly contribute to learning transferrable visual features. In this paper, we defend the usefulness of semantic labels but point out that fully-supervised and self-supervised methods are pursuing different kinds of features. To alleviate this issue, we present a new algorithm named Supervised Co…
The Hong Kong University of Science and Technology（香港科技大学）
Labeled crowd scene images are expensive and scarce. To significantly reduce the requirement of the labeled images, we propose ColorCount, a novel CNN-based approach by combining self-supervised transfer colorization learning and global prior classification to leverage the abundantly available unlabeled data. The self-supervised colorization branch learns the semantics and surface texture of the image by using its color components as pseudo labels. The classification branch extracts global group priors by learning correlations among image clusters. Their fused resultant discriminative features…
Decorrelation-based Self-Supervised Visual Representation Learning for Writer Identification
Ramakrishna Mission Vivekananda Educational and Research Institute（罗摩克里希纳使命维韦卡南达教育与研究院）；Indian Institute of Information Technology, Guwahati（古瓦哈蒂印度信息技术学院）；Indian Statistical Institute, Kolkata（加尔各答印度统计研究所）；Indian Institute of Technology, Kharagpur（克勒格布尔印度理工学院）
In recent years self-supervised learning has emerged as a promising candidate for unsupervised representation learning. In the visual domain its applications are mostly studied in the context of images of natural scenes. However, its applicability is especially interesting in specific areas, like remote sensing and medicine, where it is hard to obtain huge amounts of labeled data. In this work, we conduct an extensive analysis of the applicability of self-supervised learning in remote sensing image classification. We analyze the influence of the number and domain of images used for self-superv…
University of Munich（慕尼黑大学）；Tencent（腾讯）；MIT（麻省理工学院）
While large self-supervised models have rivalled the performance of their supervised counterparts, small models still struggle. In this report, we explore simple baselines for improving small self-supervised models via distillation, called SimDis. Specifically, we present an offline-distillation baseline, which establishes a new state-of-the-art, and an online-distillation baseline, which achieves similar performance with minimal computational overhead. We hope these baselines will provide useful experience for relevant future research. Code is available at: https://github.com/JindongGu/SimDis…
In this paper, we presented a preliminary study for tactical driver behavior detection from untrimmed naturalistic driving recordings. While supervised learning based detection is a common approach, it suffers when labeled data is scarce. Manual annotation is both time-consuming and expensive. To emphasize this problem, we experimented on a 104-hour real-world naturalistic driving dataset with a set of predefined driving behaviors annotated. There are three challenges in the dataset. First, predefined driving behaviors are sparse in a naturalistic driving setting. Second, the distribution of d…
How Well Do Self-Supervised Methods Perform in Cross-Domain Few-Shot Learning?
Artificial Intelligence Research Institute, Zhejiang Lab（之江实验室人工智能研究院）；College of Computer and Information Engineering, Zhejiang Gongshang University（浙江工商大学计算机与信息工程学院）
Georgia Institute of Technology（佐治亚理工学院）；TReNDS Center（TReNDS中心）；Delft University of Technology（代尔夫特理工大学）
Self-supervised learning has enabled significant improvements on natural image benchmarks. However, there is less work in the medical imaging domain in this area. The optimal models have not yet been determined among the various options. Moreover, little work has evaluated the current applicability limits of novel self-supervised methods. In this paper, we evaluate a range of current contrastive self-supervised methods on out-of-distribution generalization in order to evaluate their applicability to medical imaging. We show that self-supervised models are not as robust as expected based on the…
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 …
We present a generalised self-supervised learning approach for monocular estimation of the real depth across scenes with diverse depth ranges from 1--100s of meters. Existing supervised methods for monocular depth estimation require accurate depth measurements for training. This limitation has led to the introduction of self-supervised methods that are trained on stereo image pairs with a fixed camera baseline to estimate disparity which is transformed to depth given known calibration. Self-supervised approaches have demonstrated impressive results but do not generalise to scenes with differen…
Institute of Computing (IC)（计算研究所）；University of Campinas（坎皮纳斯大学）；School of Electrical and Computing Engineering (FEEC)（电气与计算机工程学院）
Self-supervised pre-training appears as an advantageous alternative to supervised pre-trained for transfer learning. By synthesizing annotations on pretext tasks, self-supervision allows to pre-train models on large amounts of pseudo-labels before fine-tuning them on the target task. In this work, we assess self-supervision for the diagnosis of skin lesions, comparing three self-supervised pipelines to a challenging supervised baseline, on five test datasets comprising in- and out-of-distribution samples. Our results show that self-supervision is competitive both in improving accuracies and in…
Understanding the flow in 3D space of sparsely sampled points between two consecutive time frames is the core stone of modern geometric-driven systems such as VR/AR, Robotics, and Autonomous driving. The lack of real, non-simulated, labeled data for this task emphasizes the importance of self- or un-supervised deep architectures. This work presents a new self-supervised training method and an architecture for the 3D scene flow estimation under occlusions. Here we show that smart multi-layer fusion between flow prediction and occlusion detection outperforms traditional architectures by a large …
University of Electronic Science and Technology of China（电子科技大学）
Self-supervised learning, which benefits from automatically constructing labels through pre-designed pretext task, has recently been applied for strengthen supervised learning. Since previous self-supervised pretext tasks are based on input, they may incur huge additional training overhead. In this paper we find that features in CNNs can be also used for self-supervision. Thus we creatively design the \emph{feature-based pretext task} which requires only a small amount of additional training overhead. In our task we discard different particular regions of features, and then train the model to …
This paper proposes a method to construct pretext tasks for self-supervised learning on group equivariant neural networks. Group equivariant neural networks are the models whose structure is restricted to commute with the transformations on the input. Therefore, it is important to construct pretext tasks for self-supervised learning that do not contradict this equivariance. To ensure that training is consistent with the equivariance, we propose two concepts for self-supervised tasks: equivariant pretext labels and invariant contrastive loss. Equivariant pretext labels use a set of labels on wh…
NAVER LABS（NAVER实验室）；University of Maryland（马里兰大学）
Monocular depth estimation in the wild inherently predicts depth up to an unknown scale. To resolve scale ambiguity issue, we present a learning algorithm that leverages monocular simultaneous localization and mapping (SLAM) with proprioceptive sensors. Such monocular SLAM systems can provide metrically scaled camera poses. Given these metric poses and monocular sequences, we propose a self-supervised learning method for the pre-trained supervised monocular depth networks to enable metrically scaled depth estimation. Our approach is based on a teacher-student formulation which guides our netwo…
University of Electronic Science and Technology of China（电子科技大学）
Traditional self-supervised learning requires CNNs using external pretext tasks (i.e., image- or video-based tasks) to encode high-level semantic visual representations. In this paper, we show that feature transformations within CNNs can also be regarded as supervisory signals to construct the self-supervised task, called \emph{internal pretext task}. And such a task can be applied for the enhancement of supervised learning. Specifically, we first transform the internal feature maps by discarding different channels, and then define an additional internal pretext task to identify the discarded …
The Graduate Center, The City University of New York（纽约市立大学研究生中心）
Large-scale labeled data are generally required to train deep neural networks in order to obtain better performance in visual feature learning from images or videos for computer vision applications. To avoid extensive cost of collecting and annotating large-scale datasets, as a subset of unsupervised learning methods, self-supervised learning methods are proposed to learn general image and video features from large-scale unlabeled data without using any human-annotated labels. This paper provides an extensive review of deep learning-based self-supervised general visual feature learning methods…
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；National University of Singapore（新加坡国立大学）
We consider the problem of semi-supervised 3D action recognition which has been rarely explored before. Its major challenge lies in how to effectively learn motion representations from unlabeled data. Self-supervised learning (SSL) has been proved very effective at learning representations from unlabeled data in the image domain. However, few effective self-supervised approaches exist for 3D action recognition, and directly applying SSL for semi-supervised learning suffers from misalignment of representations learned from SSL and supervised learning tasks. To address these issues, we present A…
We propose a new neural network architecture for solving single-image analogies - the generation of an entire set of stylistically similar images from just a single input image. Solving this problem requires separating image style from content. Our network is a modified variational autoencoder (VAE) that supports supervised training of single-image analogies and in-network evaluation of outputs with a structured similarity objective that captures pixel covariances. On the challenging task of generating a 62-letter font from a single example letter we produce images with 22.4% lower dissimilari…
