Search Results for author:
Found 12 papers, 6 papers with code
Time-, Memory- and Parameter-Efficient Visual Adaptation
Here, we outperform a prior adaptor-based method which could only scale to a 1 billion parameter backbone, or fully-finetuning a smaller backbone, with the same GPU and less training time.
Video OWL-ViT: Temporally-consistent open-world localization in video
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.
Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution
The ubiquitous and demonstrably suboptimal choice of resizing images to a fixed resolution before processing them with computer vision models has not yet been successfully challenged.
Scaling Open-Vocabulary Object Detection
However, with OWL-ST, we can scale to over 1B examples, yielding further large improvement: With an L/14 architecture, OWL-ST improves AP on LVIS rare classes, for which the model has seen no human box annotations, from 31. 2% to 44. 6% (43% relative improvement).
Ranked #1 on
Zero-Shot Object Detection
on LVIS v1.0 minival
(using extra training data)
End-to-End Spatio-Temporal Action Localisation with Video Transformers
The most performant spatio-temporal action localisation models use external person proposals and complex external memory banks.
Ranked #1 on
Action Recognition
on AVA v2.1
(using extra training data)
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
Imagen Video: High Definition Video Generation with Diffusion Models
We present Imagen Video, a text-conditional video generation system based on a cascade of video diffusion models.
Ranked #1 on
Video Generation
on LAION-400M
Beyond Transfer Learning: Co-finetuning for Action Localisation
Transfer learning is the predominant paradigm for training deep networks on small target datasets.
Simple Open-Vocabulary Object Detection with Vision Transformers
Combining simple architectures with large-scale pre-training has led to massive improvements in image classification.
Ranked #1 on
One-Shot Object Detection
on MS COCO
Video Diffusion Models
Generating temporally coherent high fidelity video is an important milestone in generative modeling research.
VUT: Versatile UI Transformer for Multi-Modal Multi-Task User Interface Modeling
Our model consists of a multimodal Transformer encoder that jointly encodes UI images and structures, and performs UI object detection when the UI structures are absent in the input.
SCENIC: A JAX Library for Computer Vision Research and Beyond
Scenic is an open-source JAX library with a focus on Transformer-based models for computer vision research and beyond.
