AI Technology & Industry Review
In the new paper DensePose From WiFi, a Carnegie Mellon University research team proposes WiFi-based DensePose, a neural network architecture capable of estimating human dense pose using only WiFi signals in scenarios with occlusion and multiple people.
In the new paper FlexiViT: One Model for All Patch Sizes, a Google Research team presents FlexiViT, a flexible ViT that performs well across a wide range of patch sizes, matching or outperforming standard fixed-patch ViT performance with no extra costs.
In the new paper UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes, a Google Brain research team proposes UViM, a unified approach that leverages language modelling and discrete representation learning to enable the modelling of a wide range of computer vision tasks without task-specific modifications.
A Meta AI research team presents OMNIVORE, a single vision model for various visual modalities that can perform cross-modal generalization and achieves performance at par or better than traditional modality-specific models of the same size.
In the paper A New Foundation Model for Computer Vision, a Microsoft research team proposes Florence, a novel foundation model for computer vision that significantly outperforms previous large-scale pretraining approaches and achieves new SOTA results across a wide range of visual and visual-linguistic benchmarks.
Google recently has launched an adorable new feature for its Arts and Culture app named Pet Portraits that can compare your pet photo to artworks from museums worldwide and find their art doubles.
In a new paper, a Facebook AI team advances autoencoding methods to the computer vision field and shows that masked autoencoders (MAE) are scalable self-supervised learners.
Researchers from Fudan University, University of Surrey and Huawei Noah’s Ark Lab identify the limitations of quadratic complexity for vision transformers (ViTs) as rooted in keeping the softmax self-attention during approximations. The team proposes the first softmax-free transformer (SOFT), which reduces the self-attention computation to linear complexity, achieving a superior trade-off between accuracy and complexity.
A research team from Google Brain and Google Research introduces SCENIC, an open-source JAX library for fast and extensible computer vision research and beyond. JAX currently supports implementations of state-of-the-art vision models such as ViT, DETR and MLP Mixer, and more open-sourced cutting-edge projects will be added in the near future.
On October 13, ICCV 2021 announced its Best Paper Awards, honourable mentions, and Best Student Paper.
A Google Research team presents compressive variants of SimCLR and BYOL that yield better and more robust visual representations.
An Oxford University research team presents PASS, a large (1.28M) image collection excluding humans, created as an ImageNet replacement for self-supervised pretraining without technical, ethical or legal issues.
A research team from University of California San Diego and Microsoft proposes Micro-Factorized Convolution (MF-Conv), a novel approach that can deal with extremely low computational costs (4M–21M FLOPs) and achieves significant performance gains over state of the art models in the low FLOP regime.
A research team from Cross Compass Ltd, Massachusetts Institute of Technology, Tokyo Institute of Technology and University of Tokyo presents CLIPDraw, an algorithm that synthesizes drawings based on natural language input without the need for any training.
A research team from Microsoft Research Asia, University of Science and Technology of China, Huazhong University of Science and Technology, and Tsinghua University takes advantage of the inherent spatiotemporal locality of videos to present a pure-transformer backbone architecture for video recognition that leads to a better speed-accuracy trade-off.
A research team from Google Cloud AI, Google Research and Rutgers University simplifies vision transformers’ complex design, proposing nested transformers (NesT) that simply stack basic transformer layers to process non-overlapping image blocks individually. The approach achieves superior ImageNet classification accuracy and improves model training efficiency.
A research team from NYU and Facebook proposes MDETR, an end-to-end modulated detector that identifies objects in images conditioned on a raw text query and is able to capture a long tail of visual concepts expressed in free-form text.
A research team from Google Research propose a message-passing graph neural network that can explicitly model spatio-temporal relations, use either implicitly or explicitly representations of objects, and generalize previous structured models for video understanding.
A Google Research team accelerates Neural Radiance Fields’ rendering procedure for view-synthesis tasks, enabling it to work in real-time while retaining its ability to represent fine geometric details and convincing view-dependent effects.
Yann LeCun and a team of researchers propose Barlow Twins, a method that learns self-supervised representations through a joint embedding of distorted images, with an objective function that can make the embedding vectors almost identical while reducing redundancy between their components.
A team from Huawei, ISCAS and UCAS propose the novel Transformer-iN-Transformer (TNT) for modelling both patch-level and pixel-level representations.
A novel module that effectively and efficiently propagates information through an arbitrarily long video, with constant complexity w.r.t. number of frames and linear complexity w.r.t. resolution.
Researchers from UC Berkeley and Google Research have introduced BoTNet, a “conceptually simple yet powerful” backbone architecture that boosts performance on computer vision (CV) tasks such as image classification, object detection and instance segmentation.
Recent AI research on speech separation has explored ways to associate lip motions in videos with audio, but this approach suffers when speakers’ lips are occluded, which they often are in busy multi-speaker environments.
VOGUE, an AI-powered optimization method that deforms garments according to a given body shape while preserving pattern and material details to deliver state-of-the-art photorealistic, high-resolution try-on images.
Researchers propose a novel framework and hierarchical predictive model that learns to identify what is predictable from unlabelled video.
The novel approach tackles dynamic 3D human-body synthesis from a sparse set of camera views, bettering existing methods on key metrics by significant margins.
Researchers proposed PGDrive, a driving simulator designed to evaluate and improve end-to-end driving agents’ generalization abilities.
As part of our year-end series, Synced highlights 10 AI-powered art projects that inspired and entertained us in 2020.
Researchers combine the effectiveness of the inductive bias in CNNs with the expressivity of transformers to model and synthesize high resolution images.
In the new paper Canonical Capsules: Unsupervised Capsules in Canonical Pose, Turing Award Honoree Dr. Geoffrey Hinton and a team of researchers propose an architecture for unsupervised learning with 3D point clouds based on capsules.
University of Notre Dame and Facebook AI research propose Img2pose, real-time 6DoF 3D face pose estimation without face detection or landmark localization.
This year, 22 Transformer-related research papers were accepted by NeurIPS, the world’s most prestigious machine learning conference. Synced has selected ten of these works to showcase the latest Transformer trends.
The new AI-powered Multi-Ingredient Pizza Generator (MPG) can deliver all these mouth-watering pies and many more.
The approach dramatically reduces bandwidth requirements by sending only a keypoint representation [of faces] and reconstructing the source video on the receiver side with the help of generative adversarial networks (GANs) to synthesize the talking heads.
A Princeton student designed a GAN framework for Chinese landscape painting generation that is so effective most humans can’t distinguish its works from the real thing.
Researchers from the City University of Hong Kong and SenseTime propose a lightweight matting objective decomposition network (MODNet) that can smoothly process real-time human matting from a single input image with diverse and dynamic backgrounds.
University of Alberta recently proposed U^2-Net, a novel deep network architecture that achieves very competitive performance in salient object detection.
A new study by South China University of Technology and Tencent WeChat AI researchers is the latest fruitful attempt to utilize transformer architectures in object detection.
A new AI-powered image synthesis framework makes “learning” to moonwalk or drop Blackpink dance moves a snap.