Search Results for author:
Found 46 papers, 39 papers with code
Gemma 3 Technical Report
We introduce Gemma 3, a multimodal addition to the Gemma family of lightweight open models, ranging in scale from 1 to 27 billion parameters.
SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
We introduce SigLIP 2, a family of new multilingual vision-language encoders that build on the success of the original SigLIP.
PaliGemma 2: A Family of Versatile VLMs for Transfer
PaliGemma 2 is an upgrade of the PaliGemma open Vision-Language Model (VLM) based on the Gemma 2 family of language models.
PaliGemma: A versatile 3B VLM for transfer
PaliGemma is an open Vision-Language Model (VLM) that is based on the SigLIP-So400m vision encoder and the Gemma-2B language model.
No Filter: Cultural and Socioeconomic Diversity in Contrastive Vision-Language Models
Third, we introduce the task of geo-localization as a novel evaluation metric to assess cultural diversity in VLMs.
LocCa: Visual Pretraining with Location-aware Captioners
In this paper, we propose a simple visual pretraining method with location-aware captioners (LocCa).
On Scaling Up a Multilingual Vision and Language Model
We explore the boundaries of scaling up a multilingual vision and language model both in terms of size of the components and the breadth of its training task mixture.
PaLI-3 Vision Language Models: Smaller, Faster, Stronger
This paper presents PaLI-3, a smaller, faster, and stronger vision language model (VLM) that compares favorably to similar models that are 10x larger.
Ranked #2 on
Temporal/Casual QA
on NExT-QA
(using extra training data)
Image Captioners Are Scalable Vision Learners Too
We further analyze the effect of the model architecture and scale, as well as the pretraining data on the representation quality, and find that captioning exhibits the same or better scaling behavior along these axes.
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.
Ranked #1 on
Fine-Grained Image Recognition
on OVEN
Three Towers: Flexible Contrastive Learning with Pretrained Image Models
With 3T, we propose a more flexible strategy that allows the image tower to benefit from both pretrained embeddings and contrastive training.
Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design
Scaling laws have been recently employed to derive compute-optimal model size (number of parameters) for a given compute duration.
A Study of Autoregressive Decoders for Multi-Tasking in Computer Vision
A key finding is that a small decoder learned on top of a frozen pretrained encoder works surprisingly well.
Sigmoid Loss for Language Image Pre-Training
We propose a simple pairwise Sigmoid loss for Language-Image Pre-training (SigLIP).
Ranked #1 on
Image-to-Text Retrieval
on COCO
Tuning computer vision models with task rewards
Misalignment between model predictions and intended usage can be detrimental for the deployment of computer vision models.
Scaling Vision Transformers to 22 Billion Parameters
The scaling of Transformers has driven breakthrough capabilities for language models.
Ranked #1 on
Zero-Shot Transfer Image Classification
on ObjectNet
FlexiViT: One Model for All Patch Sizes
Vision Transformers convert images to sequences by slicing them into patches.
VeLO: Training Versatile Learned Optimizers by Scaling Up
While deep learning models have replaced hand-designed features across many domains, these models are still trained with hand-designed optimizers.
PaLI: A Jointly-Scaled Multilingual Language-Image Model
PaLI generates text based on visual and textual inputs, and with this interface performs many vision, language, and multimodal tasks, in many languages.
UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes
We introduce UViM, a unified approach capable of modeling a wide range of computer vision tasks.
Better plain ViT baselines for ImageNet-1k
It is commonly accepted that the Vision Transformer model requires sophisticated regularization techniques to excel at ImageNet-1k scale data.
A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation
In this paper, we comprehensively study three architecture design choices on ViT -- spatial reduction, doubled channels, and multiscale features -- and demonstrate that a vanilla ViT architecture can fulfill this goal without handcrafting multiscale features, maintaining the original ViT design philosophy.
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.
How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers
Vision Transformers (ViT) have been shown to attain highly competitive performance for a wide range of vision applications, such as image classification, object detection and semantic image segmentation.
Knowledge distillation: A good teacher is patient and consistent
In particular, we uncover that there are certain implicit design choices, which may drastically affect the effectiveness of distillation.
Ranked #494 on
Image Classification
on ImageNet
Scaling Vision Transformers
As a result, we successfully train a ViT model with two billion parameters, which attains a new state-of-the-art on ImageNet of 90. 45% top-1 accuracy.
Ranked #3 on
Image Classification
on VTAB-1k
(using extra training data)
MLP-Mixer: An all-MLP Architecture for Vision
Convolutional Neural Networks (CNNs) are the go-to model for computer vision.
Ranked #17 on
Image Classification
on OmniBenchmark
SI-Score: An image dataset for fine-grained analysis of robustness to object location, rotation and size
Before deploying machine learning models it is critical to assess their robustness.
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited.
Ranked #1 on
Image Classification
on CIFAR-10
(using extra training data)
On Robustness and Transferability of Convolutional Neural Networks
Modern deep convolutional networks (CNNs) are often criticized for not generalizing under distributional shifts.
Big Transfer (BiT): General Visual Representation Learning
We conduct detailed analysis of the main components that lead to high transfer performance.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
(using extra training data)
A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark
And, how close are we to general visual representations?
Ranked #7 on
Image Classification
on VTAB-1k
(using extra training data)
The Visual Task Adaptation Benchmark
Representation learning promises to unlock deep learning for the long tail of vision tasks without expansive labelled datasets.
MULEX: Disentangling Exploitation from Exploration in Deep RL
An agent learning through interactions should balance its action selection process between probing the environment to discover new rewards and using the information acquired in the past to adopt useful behaviour.
Deep multi-class learning from label proportions
We propose a learning algorithm capable of learning from label proportions instead of direct data labels.
S4L: Self-Supervised Semi-Supervised Learning
This work tackles the problem of semi-supervised learning of image classifiers.
Ranked #15 on
Semi-Supervised Image Classification
on ImageNet - 10% labeled data
(Top 5 Accuracy metric)
Revisiting Self-Supervised Visual Representation Learning
Unsupervised visual representation learning remains a largely unsolved problem in computer vision research.
Ranked #130 on
Self-Supervised Image Classification
on ImageNet
Representation Learning
Self-Supervised Image Classification
+1
Detection-Tracking for Efficient Person Analysis: The DetTA Pipeline
In the past decade many robots were deployed in the wild, and people detection and tracking is an important component of such deployments.
Deep Person Detection in 2D Range Data
Detecting humans is a key skill for mobile robots and intelligent vehicles in a large variety of applications.
The Atari Grand Challenge Dataset
Recent progress in Reinforcement Learning (RL), fueled by its combination, with Deep Learning has enabled impressive results in learning to interact with complex virtual environments, yet real-world applications of RL are still scarce.
Towards a Principled Integration of Multi-Camera Re-Identification and Tracking through Optimal Bayes Filters
With the rise of end-to-end learning through deep learning, person detectors and re-identification (ReID) models have recently become very strong.
In Defense of the Triplet Loss for Person Re-Identification
In the past few years, the field of computer vision has gone through a revolution fueled mainly by the advent of large datasets and the adoption of deep convolutional neural networks for end-to-end learning.
Ranked #3 on
Person Re-Identification
on CUHK03
(Rank-5 metric)
DROW: Real-Time Deep Learning based Wheelchair Detection in 2D Range Data
We propose a Convolutional Neural Network (CNN) based detector for this task.
