Search Results for author:
Found 33 papers, 27 papers with code
CiT: Curation in Training for Effective Vision-Language Data
Large vision-language models are generally applicable to many downstream tasks, but come at an exorbitant training cost that only large institutions can afford.
ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders
This co-design of self-supervised learning techniques and architectural improvement results in a new model family called ConvNeXt V2, which significantly improves the performance of pure ConvNets on various recognition benchmarks, including ImageNet classification, COCO detection, and ADE20K segmentation.
Ranked #2 on
Object Detection
on COCO 2017 val
(box AP metric)
Scalable Diffusion Models with Transformers
We explore a new class of diffusion models based on the transformer architecture.
Ranked #2 on
Image Generation
on ImageNet 512x512
Exploring Long-Sequence Masked Autoencoders
Masked Autoencoding (MAE) has emerged as an effective approach for pre-training representations across multiple domains.
A ConvNet for the 2020s
The "Roaring 20s" of visual recognition began with the introduction of Vision Transformers (ViTs), which quickly superseded ConvNets as the state-of-the-art image classification model.
Ranked #4 on
Domain Generalization
on ImageNet-Sketch
(using extra training data)
A Fistful of Words: Learning Transferable Visual Models from Bag-of-Words Supervision
In this paper, we focus on teasing out what parts of the language supervision are essential for training zero-shot image classification models.
SLIP: Self-supervision meets Language-Image Pre-training
Across ImageNet and a battery of additional datasets, we find that SLIP improves accuracy by a large margin.
Masked Feature Prediction for Self-Supervised Visual Pre-Training
We present Masked Feature Prediction (MaskFeat) for self-supervised pre-training of video models.
Ranked #4 on
Action Recognition
on AVA v2.2
(using extra training data)
Benchmarking Detection Transfer Learning with Vision Transformers
The complexity of object detection methods can make this benchmarking non-trivial when new architectures, such as Vision Transformer (ViT) models, arrive.
Masked Autoencoders Are Scalable Vision Learners
Our MAE approach is simple: we mask random patches of the input image and reconstruct the missing pixels.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
Pri3D: Can 3D Priors Help 2D Representation Learning?
Inspired by these advances in geometric understanding, we aim to imbue image-based perception with representations learned under geometric constraints.
An Empirical Study of Training Self-Supervised Vision Transformers
In this work, we go back to basics and investigate the effects of several fundamental components for training self-supervised ViT.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
Out-of-Distribution Generalization
Self-Supervised Image Classification
+1
On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness
Invariance to a broad array of image corruptions, such as warping, noise, or color shifts, is an important aspect of building robust models in computer vision.
Is Robustness Robust? On the interaction between augmentations and corruptions
Invariance to a broad array of image corruptions, such as warping, noise, or color shifts, is an important aspect of building robust models in computer vision.
Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts
The rapid progress in 3D scene understanding has come with growing demand for data; however, collecting and annotating 3D scenes (e. g. point clouds) are notoriously hard.
Ranked #2 on
3D Semantic Segmentation
on ScanNet200
PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding
To this end, we select a suite of diverse datasets and tasks to measure the effect of unsupervised pre-training on a large source set of 3D scenes.
Graph Structure of Neural Networks
Neural networks are often represented as graphs of connections between neurons.
FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
We propose a masking mechanism for feature map reuse, so that memory and computational costs stay nearly constant as the search space expands.
Ranked #67 on
Neural Architecture Search
on ImageNet
Are Labels Necessary for Neural Architecture Search?
Existing neural network architectures in computer vision -- whether designed by humans or by machines -- were typically found using both images and their associated labels.
Momentum Contrast for Unsupervised Visual Representation Learning
This enables building a large and consistent dictionary on-the-fly that facilitates contrastive unsupervised learning.
Ranked #11 on
Contrastive Learning
on imagenet-1k
Decoupling Representation and Classifier for Long-Tailed Recognition
The long-tail distribution of the visual world poses great challenges for deep learning based classification models on how to handle the class imbalance problem.
Ranked #3 on
Long-tail learning with class descriptors
on CUB-LT
Neural Architecture Search by Learning Action Space for Monte Carlo Tree Search
As a result, using manually designed action space to perform NAS often leads to sample-inefficient explorations of architectures and thus can be sub-optimal.
Sample-Efficient Neural Architecture Search by Learning Action Space
To improve the sample efficiency, this paper proposes Latent Action Neural Architecture Search (LaNAS), which learns actions to recursively partition the search space into good or bad regions that contain networks with similar performance metrics.
On Network Design Spaces for Visual Recognition
Compared to current methodologies of comparing point and curve estimates of model families, distribution estimates paint a more complete picture of the entire design landscape.
Exploring Randomly Wired Neural Networks for Image Recognition
In this paper, we explore a more diverse set of connectivity patterns through the lens of randomly wired neural networks.
Ranked #115 on
Neural Architecture Search
on ImageNet
Sample-Efficient Neural Architecture Search by Learning Action Space for Monte Carlo Tree Search
To improve the sample efficiency, this paper proposes Latent Action Neural Architecture Search (LaNAS), which learns actions to recursively partition the search space into good or bad regions that contain networks with similar performance metrics.
Ranked #15 on
Image Classification
on CIFAR-10
Attentional ShapeContextNet for Point Cloud Recognition
We tackle the problem of point cloud recognition.
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification
Despite the steady progress in video analysis led by the adoption of convolutional neural networks (CNNs), the relative improvement has been less drastic as that in 2D static image classification.
Ranked #23 on
Action Recognition
on UCF101
(using extra training data)
Aggregated Residual Transformations for Deep Neural Networks
Our simple design results in a homogeneous, multi-branch architecture that has only a few hyper-parameters to set.
Ranked #3 on
Image Classification
on GasHisSDB
Top-Down Learning for Structured Labeling with Convolutional Pseudoprior
Current practice in convolutional neural networks (CNN) remains largely bottom-up and the role of top-down process in CNN for pattern analysis and visual inference is not very clear.
Hyper-Class Augmented and Regularized Deep Learning for Fine-Grained Image Classification
We demonstrate the success of the proposed framework on two small-scale fine-grained datasets (Stanford Dogs and Stanford Cars) and on a large-scale car dataset that we collected.
Holistically-Nested Edge Detection
We develop a new edge detection algorithm that tackles two important issues in this long-standing vision problem: (1) holistic image training and prediction; and (2) multi-scale and multi-level feature learning.
Deeply-Supervised Nets
Our proposed deeply-supervised nets (DSN) method simultaneously minimizes classification error while making the learning process of hidden layers direct and transparent.
Ranked #25 on
Image Classification
on SVHN
