Florian Bordes

Nicolas Ballas

Trevor Darrell

Amir Globerson

Yann LeCun

Masked Image Modeling (MIM) is a promising self-supervised learning approach that enables learning from unlabeled images. Despite its recent… (voir plus) success, learning good representations through MIM remains challenging because it requires predicting the right semantic content in accurate locations. For example, given an incomplete picture of a dog, we can guess that there is a tail, but we cannot determine its exact location. In this work, we propose to incorporate location uncertainty into MIM by using stochastic positional embeddings (StoP). Specifically, we condition the model on stochastic masked token positions drawn from a Gaussian distribution. StoP reduces overfitting to location features and guides the model toward learning features that are more robust to location uncertainties. Quantitatively, StoP improves downstream MIM performance on a variety of downstream tasks, including

2024-05-01

ICML.cc/2024/Conference (poster)

A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions

Jack Urbanek

Florian Bordes

Pietro Astolfi

Mary Williamson

Vasu Sharma

Adriana Romero Soriano

2023-12-14

ArXiv (prépublication)

Feedback-guided Data Synthesis for Imbalanced Classification

Reyhane Askari Hemmat

Mohammad Pezeshki

Florian Bordes

Michal Drozdzal

Adriana Romero Soriano

Current status quo in machine learning is to use static datasets of real images for training, which often come from long-tailed distribution… (voir plus)s. With the recent advances in generative models, researchers have started augmenting these static datasets with synthetic data, reporting moderate performance improvements on classification tasks. We hypothesize that these performance gains are limited by the lack of feedback from the classifier to the generative model, which would promote the usefulness of the generated samples to improve the classifier's performance. In this work, we introduce a framework for augmenting static datasets with useful synthetic samples, which leverages one-shot feedback from the classifier to drive the sampling of the generative model. In order for the framework to be effective, we find that the samples must be close to the support of the real data of the task at hand, and be sufficiently diverse. We validate three feedback criteria on a long-tailed dataset (ImageNet-LT) as well as a group-imbalanced dataset (NICO++). On ImageNet-LT, we achieve state-of-the-art results, with over 4 percent improvement on underrepresented classes while being twice efficient in terms of the number of generated synthetic samples. NICO++ also enjoys marked boosts of over 5 percent in worst group accuracy. With these results, our framework paves the path towards effectively leveraging state-of-the-art text-to-image models as data sources that can be queried to improve downstream applications.

2023-10-30

NeurIPS.cc/2023/Workshop/SyntheticData4ML (poster)

PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning

Florian Bordes

Shashank Shekhar

Mark Ibrahim

Diane Bouchacourt

Ari S. Morcos

Synthetic image datasets offer unmatched advantages for designing and evaluating deep neural networks: they make it possible to (i) render a… (voir plus)s many data samples as needed, (ii) precisely control each scene and yield granular ground truth labels (and captions), (iii) precisely control distribution shifts between training and testing to isolate variables of interest for sound experimentation. Despite such promise, the use of synthetic image data is still limited -- and often played down -- mainly due to their lack of realism. Most works therefore rely on datasets of real images, which have often been scraped from public images on the internet, and may have issues with regards to privacy, bias, and copyright, while offering little control over how objects precisely appear. In this work, we present a path to democratize the use of photorealistic synthetic data: we develop a new generation of interactive environments for representation learning research, that offer both controllability and realism. We use the Unreal Engine, a powerful game engine well known in the entertainment industry, to produce PUG (Photorealistic Unreal Graphics) environments and datasets for representation learning. In this paper, we demonstrate the potential of PUG to enable more rigorous evaluations of vision models.

Do SSL Models Have Déjà Vu? A Case of Unintended Memorization in Self-supervised Learning

Casey Meehan

Florian Bordes

Kamalika Chaudhuri

Chuan Guo

Self-supervised learning (SSL) algorithms can produce useful image representations by learning to associate different parts of natural image… (voir plus)s with one another. However, when taken to the extreme, SSL models can unintendedly memorize specific parts in individual training samples rather than learning semantically meaningful associations. In this work, we perform a systematic study of the unintended memorization of image-specific information in SSL models -- which we refer to as d\'ej\`a vu memorization. Concretely, we show that given the trained model and a crop of a training image containing only the background (e.g., water, sky, grass), it is possible to infer the foreground object with high accuracy or even visually reconstruct it. Furthermore, we show that d\'ej\`a vu memorization is common to different SSL algorithms, is exacerbated by certain design choices, and cannot be detected by conventional techniques for evaluating representation quality. Our study of d\'ej\`a vu memorization reveals previously unknown privacy risks in SSL models, as well as suggests potential practical mitigation strategies. Code is available at https://github.com/facebookresearch/DejaVu.

Guillotine Regularization: Why removing layers is needed to improve generalization in Self-Supervised Learning

Florian Bordes

Randall Balestriero

Quentin Garrido

Adrien Bardes

One unexpected technique that emerged in recent years consists in training a Deep Network (DN) with a Self-Supervised Learning (SSL) method,… (voir plus) and using this network on downstream tasks but with its last few projector layers entirely removed. This trick of throwing away the projector is actually critical for SSL methods to display competitive performances on ImageNet for which more than 30 percentage points can be gained that way. This is a little vexing, as one would hope that the network layer at which invariance is explicitly enforced by the SSL criterion during training (the last projector layer) should be the one to use for best generalization performance downstream. But it seems not to be, and this study sheds some light on why. This trick, which we name Guillotine Regularization (GR), is in fact a generically applicable method that has been used to improve generalization performance in transfer learning scenarios. In this work, we identify the underlying reasons behind its success and show that the optimal layer to use might change significantly depending on the training setup, the data or the downstream task. Lastly, we give some insights on how to reduce the need for a projector in SSL by aligning the pretext SSL task and the downstream task.

2023-05-23

TMLR (accepté)

A surprisingly simple technique to control the pretraining bias for better transfer: Expand or Narrow your representation

Florian Bordes

Samuel Lavoie

Randall Balestriero

Nicolas Ballas

2023-04-11

ArXiv (prépublication)

Objectives Matter: Understanding the Impact of Self-Supervised Objectives on Vision Transformer Representations

Shashank Shekhar

Florian Bordes

Ari S. Morcos

Joint-embedding based learning (e.g., SimCLR, MoCo, DINO) and reconstruction-based learning (e.g., BEiT, SimMIM, MAE) are the two leading pa… (voir plus)radigms for self-supervised learning of vision transformers, but they differ substantially in their transfer performance. Here, we aim to explain these differences by analyzing the impact of these objectives on the structure and transferability of their representations. Our analysis reveals that reconstruction-based learning features are significantly dissimilar to joint-embedding based learning features and that models trained with similar objectives learn similar features even across architectures. These differences arise early in the network, primarily driven by attention and normalization layers. We find that joint-embedding features yield better linear probe transfer for classification because the different objectives drive different distributions of information and invariances in the representation. These differences explain opposite trends in transfer performance for downstream tasks that require spatial specificity in features. Finally, we address how fine-tuning changes reconstructive representations to enable better transfer, showing that it re-organizes the information to be more similar to pre-trained joint embedding models.

2023-03-04

ICLR.cc/2023/Workshop/ME-FoMo (spotlight)

Towards Democratizing Joint-Embedding Self-Supervised Learning

Florian Bordes

Randall Balestriero

Joint Embedding Self-Supervised Learning (JE-SSL) has seen rapid developments in recent years, due to its promise to effectively leverage la… (voir plus)rge unlabeled data. The development of JE-SSL methods was driven primarily by the search for ever increasing downstream classification accuracies, using huge computational resources, and typically built upon insights and intuitions inherited from a close parent JE-SSL method. This has led unwittingly to numerous pre-conceived ideas that carried over across methods e.g. that SimCLR requires very large mini batches to yield competitive accuracies; that strong and computationally slow data augmentations are required. In this work, we debunk several such ill-formed a priori ideas in the hope to unleash the full potential of JE-SSL free of unnecessary limitations. In fact, when carefully evaluating performances across different downstream tasks and properly optimizing hyper-parameters of the methods, we most often -- if not always -- see that these widespread misconceptions do not hold. For example we show that it is possible to train SimCLR to learn useful representations, while using a single image patch as negative example, and simple Gaussian noise as the only data augmentation for the positive pair. Along these lines, in the hope to democratize JE-SSL and to allow researchers to easily make more extensive evaluations of their methods, we introduce an optimized PyTorch library for SSL.

2023-03-03

ArXiv (prépublication)

The Hidden Uniform Cluster Prior in Self-Supervised Learning

Mahmoud Assran

Randall Balestriero

Quentin Duval

Florian Bordes

Ishan Misra

Piotr Bojanowski

Michael Rabbat

Nicolas Ballas

A successful paradigm in representation learning is to perform self-supervised pretraining using tasks based on mini-batch statistics (e.g.,… (voir plus) SimCLR, VICReg, SwAV, MSN). We show that in the formulation of all these methods is an overlooked prior to learn features that enable uniform clustering of the data. While this prior has led to remarkably semantic representations when pretraining on class-balanced data, such as ImageNet, we demonstrate that it can hamper performance when pretraining on class-imbalanced data. By moving away from conventional uniformity priors and instead preferring power-law distributed feature clusters, we show that one can improve the quality of the learned representations on real-world class-imbalanced datasets. To demonstrate this, we develop an extension of the Masked Siamese Networks (MSN) method to support the use of arbitrary features priors.

2023-02-01

ICLR.cc/2023/Conference (poster)

High Fidelity Visualization of What Your Self-Supervised Representation Knows About

Florian Bordes

Randall Balestriero

Discovering what is learned by neural networks remains a challenge. In self-supervised learning, classification is the most common task used… (voir plus) to evaluate how good a representation is. However, relying only on such downstream task can limit our understanding of what information is retained in the representation of a given input. In this work, we showcase the use of a Representation Conditional Diffusion Model (RCDM) to visualize in data space the representations learned by self-supervised models. The use of RCDM is motivated by its ability to generate high-quality samples -- on par with state-of-the-art generative models -- while ensuring that the representations of those samples are faithful i.e. close to the one used for conditioning. By using RCDM to analyze self-supervised models, we are able to clearly show visually that i) SSL (backbone) representation are not invariant to the data augmentations they were trained with -- thus debunking an often restated but mistaken belief; ii) SSL post-projector embeddings appear indeed invariant to these data augmentation, along with many other data symmetries; iii) SSL representations appear more robust to small adversarial perturbation of their inputs than representations trained in a supervised manner; and iv) that SSL-trained representations exhibit an inherent structure that can be explored thanks to RCDM visualization and enables image manipulation.

2022-08-15

TMLR (accepté)

Masked Siamese Networks for Label-Efficient Learning

Mahmoud Assran

Mathilde Caron

Ishan Misra

Piotr Bojanowski

Florian Bordes

Armand Joulin

Michael Rabbat

Nicolas Ballas

We propose Masked Siamese Networks (MSN), a self-supervised learning framework for learning image representations. Our approach matches the … (voir plus)representation of an image view containing randomly masked patches to the representation of the original unmasked image. This self-supervised pre-training strategy is particularly scalable when applied to Vision Transformers since only the unmasked patches are processed by the network. As a result, MSNs improve the scalability of joint-embedding architectures, while producing representations of a high semantic level that perform competitively on low-shot image classification. For instance, on ImageNet-1K, with only 5,000 annotated images, our base MSN model achieves 72.4% top-1 accuracy, and with 1% of ImageNet-1K labels, we achieve 75.7% top-1 accuracy, setting a new state-of-the-art for self-supervised learning on this benchmark. Our code is publicly available.

2022-04-14

ArXiv (preprint)