
-
Exploring Simple Siamese Representation Learning
Siamese networks have become a common structure in various recent models...
read it
-
Graph Structure of Neural Networks
Neural networks are often represented as graphs of connections between n...
read it
-
Designing Network Design Spaces
In this work, we present a new network design paradigm. Our goal is to h...
read it
-
Are Labels Necessary for Neural Architecture Search?
Existing neural network architectures in computer vision — whether desig...
read it
-
Improved Baselines with Momentum Contrastive Learning
Contrastive unsupervised learning has recently shown encouraging progres...
read it
-
PointRend: Image Segmentation as Rendering
We present a new method for efficient high-quality image segmentation of...
read it
-
A Multigrid Method for Efficiently Training Video Models
Training competitive deep video models is an order of magnitude slower t...
read it
-
Momentum Contrast for Unsupervised Visual Representation Learning
We present Momentum Contrast (MoCo) for unsupervised visual representati...
read it
-
Deep Hough Voting for 3D Object Detection in Point Clouds
Current 3D object detection methods are heavily influenced by 2D detecto...
read it
-
Exploring Randomly Wired Neural Networks for Image Recognition
Neural networks for image recognition have evolved through extensive man...
read it
-
TensorMask: A Foundation for Dense Object Segmentation
Sliding-window object detectors that generate bounding-box object predic...
read it
-
Panoptic Feature Pyramid Networks
The recently introduced panoptic segmentation task has renewed our commu...
read it
-
Long-Term Feature Banks for Detailed Video Understanding
To understand the world, we humans constantly need to relate the present...
read it
-
SlowFast Networks for Video Recognition
We present SlowFast networks for video recognition. Our model involves (...
read it
-
Feature Denoising for Improving Adversarial Robustness
Adversarial attacks to image classification systems present challenges t...
read it
-
Rethinking ImageNet Pre-training
We report competitive results on object detection and instance segmentat...
read it
-
GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations
Modern deep transfer learning approaches have mainly focused on learning...
read it
-
Exploring the Limits of Weakly Supervised Pretraining
State-of-the-art visual perception models for a wide range of tasks rely...
read it
-
Group Normalization
Batch Normalization (BN) is a milestone technique in the development of ...
read it
-
Panoptic Segmentation
We propose and study a novel 'Panoptic Segmentation' (PS) task. Panoptic...
read it
-
Data Distillation: Towards Omni-Supervised Learning
We investigate omni-supervised learning, a special regime of semi-superv...
read it
-
Learning to Segment Every Thing
Existing methods for object instance segmentation require all training i...
read it
-
Non-local Neural Networks
Both convolutional and recurrent operations are building blocks that pro...
read it
-
Transitive Invariance for Self-supervised Visual Representation Learning
Learning visual representations with self-supervised learning has become...
read it
-
Focal Loss for Dense Object Detection
The highest accuracy object detectors to date are based on a two-stage a...
read it
-
Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
Deep learning thrives with large neural networks and large datasets. How...
read it
-
Mask R-CNN
We present a conceptually simple, flexible, and general framework for ob...
read it
-
Feature Pyramid Networks for Object Detection
Feature pyramids are a basic component in recognition systems for detect...
read it
-
Aggregated Residual Transformations for Deep Neural Networks
We present a simple, highly modularized network architecture for image c...
read it
-
R-FCN: Object Detection via Region-based Fully Convolutional Networks
We present region-based, fully convolutional networks for accurate and e...
read it
-
ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation
Large-scale data is of crucial importance for learning semantic segmenta...
read it
-
Instance-sensitive Fully Convolutional Networks
Fully convolutional networks (FCNs) have been proven very successful for...
read it
-
Identity Mappings in Deep Residual Networks
Deep residual networks have emerged as a family of extremely deep archit...
read it
-
Instance-aware Semantic Segmentation via Multi-task Network Cascades
Semantic segmentation research has recently witnessed rapid progress, bu...
read it
-
Deep Residual Learning for Image Recognition
Deeper neural networks are more difficult to train. We present a residua...
read it
-
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
State-of-the-art object detection networks depend on region proposal alg...
read it
-
Accelerating Very Deep Convolutional Networks for Classification and Detection
This paper aims to accelerate the test-time computation of convolutional...
read it
-
Fast Guided Filter
The guided filter is a technique for edge-aware image filtering. Because...
read it
-
Object Detection Networks on Convolutional Feature Maps
Most object detectors contain two important components: a feature extrac...
read it
-
BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
Recent leading approaches to semantic segmentation rely on deep convolut...
read it
-
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
Rectified activation units (rectifiers) are essential for state-of-the-a...
read it
-
Image Super-Resolution Using Deep Convolutional Networks
We propose a deep learning method for single image super-resolution (SR)...
read it
-
Convolutional Neural Networks at Constrained Time Cost
Though recent advanced convolutional neural networks (CNNs) have been im...
read it
-
Convolutional Feature Masking for Joint Object and Stuff Segmentation
The topic of semantic segmentation has witnessed considerable progress d...
read it
-
Efficient and Accurate Approximations of Nonlinear Convolutional Networks
This paper aims to accelerate the test-time computation of deep convolut...
read it
-
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
Existing deep convolutional neural networks (CNNs) require a fixed-size ...
read it