Alert button
Picture for Daniel Keysers

Daniel Keysers

Alert button

Video OWL-ViT: Temporally-consistent open-world localization in video

Aug 22, 2023
Georg Heigold, Matthias Minderer, Alexey Gritsenko, Alex Bewley, Daniel Keysers, Mario Lučić, Fisher Yu, Thomas Kipf

Figure 1 for Video OWL-ViT: Temporally-consistent open-world localization in video
Figure 2 for Video OWL-ViT: Temporally-consistent open-world localization in video
Figure 3 for Video OWL-ViT: Temporally-consistent open-world localization in video
Figure 4 for Video OWL-ViT: Temporally-consistent open-world localization in video

We present an architecture and a training recipe that adapts pre-trained open-world image models to localization in videos. Understanding the open visual world (without being constrained by fixed label spaces) is crucial for many real-world vision tasks. Contrastive pre-training on large image-text datasets has recently led to significant improvements for image-level tasks. For more structured tasks involving object localization applying pre-trained models is more challenging. This is particularly true for video tasks, where task-specific data is limited. We show successful transfer of open-world models by building on the OWL-ViT open-vocabulary detection model and adapting it to video by adding a transformer decoder. The decoder propagates object representations recurrently through time by using the output tokens for one frame as the object queries for the next. Our model is end-to-end trainable on video data and enjoys improved temporal consistency compared to tracking-by-detection baselines, while retaining the open-world capabilities of the backbone detector. We evaluate our model on the challenging TAO-OW benchmark and demonstrate that open-world capabilities, learned from large-scale image-text pre-training, can be transferred successfully to open-world localization across diverse videos.

* ICCV 2023 
Viaarxiv icon

PaLI-X: On Scaling up a Multilingual Vision and Language Model

May 29, 2023
Xi Chen, Josip Djolonga, Piotr Padlewski, Basil Mustafa, Soravit Changpinyo, Jialin Wu, Carlos Riquelme Ruiz, Sebastian Goodman, Xiao Wang, Yi Tay, Siamak Shakeri, Mostafa Dehghani, Daniel Salz, Mario Lucic, Michael Tschannen, Arsha Nagrani, Hexiang Hu, Mandar Joshi, Bo Pang, Ceslee Montgomery, Paulina Pietrzyk, Marvin Ritter, AJ Piergiovanni, Matthias Minderer, Filip Pavetic, Austin Waters, Gang Li, Ibrahim Alabdulmohsin, Lucas Beyer, Julien Amelot, Kenton Lee, Andreas Peter Steiner, Yang Li, Daniel Keysers, Anurag Arnab, Yuanzhong Xu, Keran Rong, Alexander Kolesnikov, Mojtaba Seyedhosseini, Anelia Angelova, Xiaohua Zhai, Neil Houlsby, Radu Soricut

Figure 1 for PaLI-X: On Scaling up a Multilingual Vision and Language Model
Figure 2 for PaLI-X: On Scaling up a Multilingual Vision and Language Model
Figure 3 for PaLI-X: On Scaling up a Multilingual Vision and Language Model
Figure 4 for PaLI-X: On Scaling up a Multilingual Vision and Language Model

We present the training recipe and results of scaling up PaLI-X, a multilingual vision and language model, both in terms of size of the components and the breadth of its training task mixture. Our model achieves new levels of performance on a wide-range of varied and complex tasks, including multiple image-based captioning and question-answering tasks, image-based document understanding and few-shot (in-context) learning, as well as object detection, video question answering, and video captioning. PaLI-X advances the state-of-the-art on most vision-and-language benchmarks considered (25+ of them). Finally, we observe emerging capabilities, such as complex counting and multilingual object detection, tasks that are not explicitly in the training mix.

Viaarxiv icon

Scaling Vision Transformers to 22 Billion Parameters

Feb 10, 2023
Mostafa Dehghani, Josip Djolonga, Basil Mustafa, Piotr Padlewski, Jonathan Heek, Justin Gilmer, Andreas Steiner, Mathilde Caron, Robert Geirhos, Ibrahim Alabdulmohsin, Rodolphe Jenatton, Lucas Beyer, Michael Tschannen, Anurag Arnab, Xiao Wang, Carlos Riquelme, Matthias Minderer, Joan Puigcerver, Utku Evci, Manoj Kumar, Sjoerd van Steenkiste, Gamaleldin F. Elsayed, Aravindh Mahendran, Fisher Yu, Avital Oliver, Fantine Huot, Jasmijn Bastings, Mark Patrick Collier, Alexey Gritsenko, Vighnesh Birodkar, Cristina Vasconcelos, Yi Tay, Thomas Mensink, Alexander Kolesnikov, Filip Pavetić, Dustin Tran, Thomas Kipf, Mario Lučić, Xiaohua Zhai, Daniel Keysers, Jeremiah Harmsen, Neil Houlsby

Figure 1 for Scaling Vision Transformers to 22 Billion Parameters
Figure 2 for Scaling Vision Transformers to 22 Billion Parameters
Figure 3 for Scaling Vision Transformers to 22 Billion Parameters
Figure 4 for Scaling Vision Transformers to 22 Billion Parameters

The scaling of Transformers has driven breakthrough capabilities for language models. At present, the largest large language models (LLMs) contain upwards of 100B parameters. Vision Transformers (ViT) have introduced the same architecture to image and video modelling, but these have not yet been successfully scaled to nearly the same degree; the largest dense ViT contains 4B parameters (Chen et al., 2022). We present a recipe for highly efficient and stable training of a 22B-parameter ViT (ViT-22B) and perform a wide variety of experiments on the resulting model. When evaluated on downstream tasks (often with a lightweight linear model on frozen features), ViT-22B demonstrates increasing performance with scale. We further observe other interesting benefits of scale, including an improved tradeoff between fairness and performance, state-of-the-art alignment to human visual perception in terms of shape/texture bias, and improved robustness. ViT-22B demonstrates the potential for "LLM-like" scaling in vision, and provides key steps towards getting there.

Viaarxiv icon

LiT: Zero-Shot Transfer with Locked-image Text Tuning

Nov 15, 2021
Xiaohua Zhai, Xiao Wang, Basil Mustafa, Andreas Steiner, Daniel Keysers, Alexander Kolesnikov, Lucas Beyer

Figure 1 for LiT: Zero-Shot Transfer with Locked-image Text Tuning
Figure 2 for LiT: Zero-Shot Transfer with Locked-image Text Tuning
Figure 3 for LiT: Zero-Shot Transfer with Locked-image Text Tuning
Figure 4 for LiT: Zero-Shot Transfer with Locked-image Text Tuning

This paper presents contrastive-tuning, a simple method employing contrastive training to align image and text models while still taking advantage of their pre-training. In our empirical study we find that locked pre-trained image models with unlocked text models work best. We call this instance of contrastive-tuning "Locked-image Text tuning" (LiT-tuning), which just teaches a text model to read out good representations from a pre-trained image model for new tasks. A LiT-tuned model gains the capability of zero-shot transfer to new vision tasks, such as image classification or retrieval. The proposed LiT-tuning is widely applicable; it works reliably with multiple pre-training methods (supervised and unsupervised) and across diverse architectures (ResNet, Vision Transformers and MLP-Mixer) using three different image-text datasets. With the transformer-based pre-trained ViT-g/14 model, the LiT-tuned model achieves 84.5% zero-shot transfer accuracy on the ImageNet test set, and 81.1% on the challenging out-of-distribution ObjectNet test set.

* Xiaohua, Xiao, Basil, Andreas and Lucas contributed equally 
Viaarxiv icon

The Impact of Reinitialization on Generalization in Convolutional Neural Networks

Sep 01, 2021
Ibrahim Alabdulmohsin, Hartmut Maennel, Daniel Keysers

Figure 1 for The Impact of Reinitialization on Generalization in Convolutional Neural Networks
Figure 2 for The Impact of Reinitialization on Generalization in Convolutional Neural Networks
Figure 3 for The Impact of Reinitialization on Generalization in Convolutional Neural Networks
Figure 4 for The Impact of Reinitialization on Generalization in Convolutional Neural Networks

Recent results suggest that reinitializing a subset of the parameters of a neural network during training can improve generalization, particularly for small training sets. We study the impact of different reinitialization methods in several convolutional architectures across 12 benchmark image classification datasets, analyzing their potential gains and highlighting limitations. We also introduce a new layerwise reinitialization algorithm that outperforms previous methods and suggest explanations of the observed improved generalization. First, we show that layerwise reinitialization increases the margin on the training examples without increasing the norm of the weights, hence leading to an improvement in margin-based generalization bounds for neural networks. Second, we demonstrate that it settles in flatter local minima of the loss surface. Third, it encourages learning general rules and discourages memorization by placing emphasis on the lower layers of the neural network. Our takeaway message is that the accuracy of convolutional neural networks can be improved for small datasets using bottom-up layerwise reinitialization, where the number of reinitialized layers may vary depending on the available compute budget.

* 12 figures, 7 tables 
Viaarxiv icon

Continental-Scale Building Detection from High Resolution Satellite Imagery

Jul 29, 2021
Wojciech Sirko, Sergii Kashubin, Marvin Ritter, Abigail Annkah, Yasser Salah Eddine Bouchareb, Yann Dauphin, Daniel Keysers, Maxim Neumann, Moustapha Cisse, John Quinn

Figure 1 for Continental-Scale Building Detection from High Resolution Satellite Imagery
Figure 2 for Continental-Scale Building Detection from High Resolution Satellite Imagery
Figure 3 for Continental-Scale Building Detection from High Resolution Satellite Imagery
Figure 4 for Continental-Scale Building Detection from High Resolution Satellite Imagery

Identifying the locations and footprints of buildings is vital for many practical and scientific purposes. Such information can be particularly useful in developing regions where alternative data sources may be scarce. In this work, we describe a model training pipeline for detecting buildings across the entire continent of Africa, using 50 cm satellite imagery. Starting with the U-Net model, widely used in satellite image analysis, we study variations in architecture, loss functions, regularization, pre-training, self-training and post-processing that increase instance segmentation performance. Experiments were carried out using a dataset of 100k satellite images across Africa containing 1.75M manually labelled building instances, and further datasets for pre-training and self-training. We report novel methods for improving performance of building detection with this type of model, including the use of mixup (mAP +0.12) and self-training with soft KL loss (mAP +0.06). The resulting pipeline obtains good results even on a wide variety of challenging rural and urban contexts, and was used to create the Open Buildings dataset of 516M Africa-wide detected footprints.

Viaarxiv icon

A Generalized Lottery Ticket Hypothesis

Jul 26, 2021
Ibrahim Alabdulmohsin, Larisa Markeeva, Daniel Keysers, Ilya Tolstikhin

Figure 1 for A Generalized Lottery Ticket Hypothesis
Figure 2 for A Generalized Lottery Ticket Hypothesis
Figure 3 for A Generalized Lottery Ticket Hypothesis
Figure 4 for A Generalized Lottery Ticket Hypothesis

We introduce a generalization to the lottery ticket hypothesis in which the notion of "sparsity" is relaxed by choosing an arbitrary basis in the space of parameters. We present evidence that the original results reported for the canonical basis continue to hold in this broader setting. We describe how structured pruning methods, including pruning units or factorizing fully-connected layers into products of low-rank matrices, can be cast as particular instances of this "generalized" lottery ticket hypothesis. The investigations reported here are preliminary and are provided to encourage further research along this direction.

* Workshop on Sparsity in Neural Networks: Advancing Understanding and Practice (SNN'21). Updates: New curve on Figure 2(left) and discussion on Li et al 
Viaarxiv icon

Scaling Vision with Sparse Mixture of Experts

Jun 10, 2021
Carlos Riquelme, Joan Puigcerver, Basil Mustafa, Maxim Neumann, Rodolphe Jenatton, André Susano Pinto, Daniel Keysers, Neil Houlsby

Figure 1 for Scaling Vision with Sparse Mixture of Experts
Figure 2 for Scaling Vision with Sparse Mixture of Experts
Figure 3 for Scaling Vision with Sparse Mixture of Experts
Figure 4 for Scaling Vision with Sparse Mixture of Experts

Sparsely-gated Mixture of Experts networks (MoEs) have demonstrated excellent scalability in Natural Language Processing. In Computer Vision, however, almost all performant networks are "dense", that is, every input is processed by every parameter. We present a Vision MoE (V-MoE), a sparse version of the Vision Transformer, that is scalable and competitive with the largest dense networks. When applied to image recognition, V-MoE matches the performance of state-of-the-art networks, while requiring as little as half of the compute at inference time. Further, we propose an extension to the routing algorithm that can prioritize subsets of each input across the entire batch, leading to adaptive per-image compute. This allows V-MoE to trade-off performance and compute smoothly at test-time. Finally, we demonstrate the potential of V-MoE to scale vision models, and train a 15B parameter model that attains 90.35% on ImageNet.

* 44 pages, 38 figures 
Viaarxiv icon