Linear probing (LP) (and $k$-NN) on the upstream dataset with labels (e.g., ImageNet) and transfer learning (TL) to various downstream datasets are commonly employed to evaluate the quality of visual representations learned via self-supervised learning (SSL). Although existing SSL methods have shown good performances under those evaluation protocols, we observe that the performances are very sensitive to the hyperparameters involved in LP and TL. We argue that this is an undesirable behavior since truly generic representations should be easily adapted to any other visual recognition task, i.e., the learned representations should be robust to the settings of LP and TL hyperparameters. In this work, we try to figure out the cause of performance sensitivity by conducting extensive experiments with state-of-the-art SSL methods. First, we find that input normalization for LP is crucial to eliminate performance variations according to the hyperparameters. Specifically, batch normalization before feeding inputs to a linear classifier considerably improves the stability of evaluation, and also resolves inconsistency of $k$-NN and LP metrics. Second, for TL, we demonstrate that a weight decay parameter in SSL significantly affects the transferability of learned representations, which cannot be identified by LP or $k$-NN evaluations on the upstream dataset. We believe that the findings of this study will be beneficial for the community by drawing attention to the shortcomings in the current SSL evaluation schemes and underscoring the need to reconsider them.

A core component of the recent success of self-supervised learning is cropping data augmentation, which selects sub-regions of an image to be used as positive views in the self-supervised loss. The underlying assumption is that randomly cropped and resized regions of a given image share information about the objects of interest, which the learned representation will capture. This assumption is mostly satisfied in datasets such as ImageNet where there is a large, centered object, which is highly likely to be present in random crops of the full image. However, in other datasets such as OpenImages or COCO, which are more representative of real world uncurated data, there are typically multiple small objects in an image. In this work, we show that self-supervised learning based on the usual random cropping performs poorly on such datasets. We propose replacing one or both of the random crops with crops obtained from an object proposal algorithm. This encourages the model to learn both object and scene level semantic representations. Using this approach, which we call object-aware cropping, results in significant improvements over scene cropping on classification and object detection benchmarks. For example, on OpenImages, our approach achieves an improvement of 8.8% mAP over random scene-level cropping using MoCo-v2 based pre-training. We also show significant improvements on COCO and PASCAL-VOC object detection and segmentation tasks over the state-of-the-art self-supervised learning approaches. Our approach is efficient, simple and general, and can be used in most existing contrastive and non-contrastive self-supervised learning frameworks.

Prediction of chemical shift in NMR using machine learning methods is typically done with the maximum amount of data available to achieve the best results. In some cases, such large amounts of data are not available, e.g. for heteronuclei. We demonstrate a novel machine learning model which is able to achieve good results with comparatively low amounts of data. We show this by predicting 19F and 13C NMR chemical shifts of small molecules in specific solvents.

Most recent self-supervised learning methods are pre-trained on the well-curated ImageNet-1K dataset. In this work, given the excellent scalability of web data, we consider self-supervised pre-training on noisy web sourced image-text paired data. First, we conduct a benchmark study of representative self-supervised pre-training methods on large-scale web data in a like-for-like setting. We compare a range of methods, including single-modal ones that use masked training objectives and multi-modal ones that use image-text constrastive training. We observe that existing multi-modal methods do not outperform their single-modal counterparts on vision transfer learning tasks. We derive an information-theoretical view to explain these benchmark results, which provides insight into how to design a novel vision learner. Inspired by this insight, we present a new visual representation pre-training method, MUlti-modal Generator~(MUG), that learns from scalable web sourced image-text data. MUG achieves state-of-the-art transfer performance on a variety of tasks and demonstrates promising scaling properties. Pre-trained models and code will be made public upon acceptance.

The topic of this internship is related to Self-Supervised Learning, with the main idea of finding innovative methods to train a neural network in order to make a step forward in this field. A major problem that constrains our research is the use of the smallest possible amount of annotated data to obtain good final results. The aim is to enable new AIs to understand their environment and task more efficiently and with the least amount of data possible, so that they become accessible to companies that do not have the billions of data available to Google for example. The objective of this internship is to propose an innovative method that uses unlabelled data, i.e. data that will allow the AI to automatically learn to predict the correct outcome. To reach this stage, the steps to be followed can be defined as follows: (1) consult the state of the art and position ourself against it, (2) come up with ideas for development paths, (3) implement these ideas, (4) and finally test them to position ourself against the state of the art, and then start the sequence again.

Quantifying predictive uncertainty of neural networks has recently attracted increasing attention. In this work, we focus on measuring uncertainty of graph neural networks (GNNs) for the task of node classification. Most existing GNNs model message passing among nodes. The messages are often deterministic. Questions naturally arise: Does there exist uncertainty in the messages? How could we propagate such uncertainty over a graph together with messages? To address these issues, we propose a Bayesian uncertainty propagation (BUP) method, which embeds GNNs in a Bayesian modeling framework, and models predictive uncertainty of node classification with Bayesian confidence of predictive probability and uncertainty of messages. Our method proposes a novel uncertainty propagation mechanism inspired by Gaussian models. Moreover, we present an uncertainty oriented loss for node classification that allows the GNNs to clearly integrate predictive uncertainty in learning procedure. Consequently, the training examples with large predictive uncertainty will be penalized. We demonstrate the BUP with respect to prediction reliability and out-of-distribution (OOD) predictions. The learned uncertainty is also analyzed in depth. The relations between uncertainty and graph topology, as well as predictive uncertainty in the OOD cases are investigated with extensive experiments. The empirical results with popular benchmark datasets demonstrate the superior performance of the proposed method.

Given a 3D object, kinematic motion prediction aims to identify the mobile parts as well as the corresponding motion parameters. Due to the large variations in both topological structure and geometric details of 3D objects, this remains a challenging task and the lack of large scale labeled data also constrain the performance of deep learning based approaches. In this paper, we tackle the task of object kinematic motion prediction problem in a semi-weakly supervised manner. Our key observations are two-fold. First, although 3D dataset with fully annotated motion labels is limited, there are existing datasets and methods for object part semantic segmentation at large scale. Second, semantic part segmentation and mobile part segmentation is not always consistent but it is possible to detect the mobile parts from the underlying 3D structure. Towards this end, we propose a graph neural network to learn the map between hierarchical part-level segmentation and mobile parts parameters, which are further refined based on geometric alignment. This network can be first trained on PartNet-Mobility dataset with fully labeled mobility information and then applied on PartNet dataset with fine-grained and hierarchical part-level segmentation. The network predictions yield a large scale of 3D objects with pseudo labeled mobility information and can further be used for weakly-supervised learning with pre-existing segmentation. Our experiments show there are significant performance boosts with the augmented data for previous method designed for kinematic motion prediction on 3D partial scans.

Self-supervised learning is a rapidly evolving field in deep learning that has shown great promise for learning useful representations from unlabeled data. It is unsupervised learning, where the goal is to learn a representation of the data that is useful for downstream tasks such as classification, object detection, or segmentation. In contrast to traditional supervised learning, where the model is trained on labeled data, self-supervised learning involves training the model on unlabeled data, using techniques such as contrastive learning or generative modeling to learn meaningful representations. In a recent study, researchers at Facebook AI and NYU demonstrated that self-supervised learning can achieve state-of-the-art results on a range of natural language processing tasks, including text classification, question answering, and machine translation. The researchers used a self-supervised pretraining approach called T5, which was trained on a massive dataset of 800 billion words.

This paper shows that Masking the Deep hierarchical features is an efficient self-supervised method, denoted as MaskDeep. MaskDeep treats each patch in the representation space as an independent instance. We mask part of patches in the representation space and then utilize sparse visible patches to reconstruct high semantic image representation. The intuition of MaskDeep lies in the fact that models can reason from sparse visible patches semantic to the global semantic of the image. We further propose three designs in our framework: 1) a Hierarchical Deep-Masking module to concern the hierarchical property of patch representations, 2) a multi-group strategy to improve the efficiency without any extra computing consumption of the encoder and 3) a multi-target strategy to provide more description of the global semantic. Our MaskDeep brings decent improvements. Trained on ResNet50 with 200 epochs, MaskDeep achieves state-of-the-art results of 71.2% Top1 accuracy linear classification on ImageNet. On COCO object detection tasks, MaskDeep outperforms the self-supervised method SoCo, which specifically designed for object detection. When trained with 100 epochs, MaskDeep achieves 69.6% Top1 accuracy, which surpasses current methods trained with 200 epochs, such as HCSC, by 0.4% .

Representation learning, by training deep neural networks as feature extractors to generate compact embedding vectors from images, is a fundamental component in computer vision. Metric learning, a kind of representation learning using supervised data, has been widely applied to image recognition, clustering, and retrieval [Schroff et al., 2015; Weinberger and Saul, 2009; Weyand et al., 2020]. Machine learning models have the capacity to memorize training data [Carlini et al., 2019, 2021], leading to privacy risks when the models are deployed. Privacy risk can also be audited by membership inference attacks [Carlini et al., 2022; Shokri et al., 2017], i.e. detecting whether certain data was used to train a model and potentially exposing users' usage behaviors. Defending against such risks is a critical responsibility when training on privacy-sensitive data. Differential Privacy (DP) [Dwork et al., 2006] is an extensively used quantifiable measurement of privacy risk, now generally accepted as a standard notion of privacy in both industry and government [Apple Privacy Team, 2017; Ding et al., 2017; McMahan and Thakurta, 2022; US Census Bureau, 2021]. Applied to machine learning, DP requires a training procedure with explicit randomness, and guarantees that the distribution over output models is quantifiably similar given a certain scope of change to the training dataset. A DP guarantee with respect to the change of a single arbitrary training example is known as example-level DP, which provides plausible deniability (in the binary hypothesis testing sense of [Kairouz et al., 2015]) that any single example (e.g., image) occurred The first two authors contributed equally.