Search Results for author:
Found 65 papers, 50 papers with code
A Decade's Battle on Dataset Bias: Are We There Yet?
We revisit the "dataset classification" experiment suggested by Torralba and Efros a decade ago, in the new era with large-scale, diverse, and hopefully less biased datasets as well as more capable neural network architectures.
Deconstructing Denoising Diffusion Models for Self-Supervised Learning
In this study, we examine the representation learning abilities of Denoising Diffusion Models (DDM) that were originally purposed for image generation.
Return of Unconditional Generation: A Self-supervised Representation Generation Method
This gap can be attributed to the lack of semantic information provided by labels.
Ranked #1 on
Unconditional Image Generation
on ImageNet 256x256
Scaling Language-Image Pre-training via Masking
We present Fast Language-Image Pre-training (FLIP), a simple and more efficient method for training CLIP.
Masked Autoencoders As Spatiotemporal Learners
We randomly mask out spacetime patches in videos and learn an autoencoder to reconstruct them in pixels.
Exploring Plain Vision Transformer Backbones for Object Detection
This design enables the original ViT architecture to be fine-tuned for object detection without needing to redesign a hierarchical backbone for pre-training.
Ranked #5 on
Instance Segmentation
on LVIS v1.0 val
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
A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning
We present a large-scale study on unsupervised spatiotemporal representation learning from videos.
Ranked #3 on
Self-Supervised Action Recognition
on HMDB51
Representation Learning
Self-Supervised Action Recognition
+1
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
Exploring Simple Siamese Representation Learning
Our experiments show that collapsing solutions do exist for the loss and structure, but a stop-gradient operation plays an essential role in preventing collapsing.
Ranked #94 on
Self-Supervised Image Classification
on ImageNet
Representation Learning
Self-Supervised Image Classification
Graph Structure of Neural Networks
Neural networks are often represented as graphs of connections between neurons.
Designing Network Design Spaces
In this work, we present a new network design paradigm.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
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.
Improved Baselines with Momentum Contrastive Learning
Contrastive unsupervised learning has recently shown encouraging progress, e. g., in Momentum Contrast (MoCo) and SimCLR.
Ranked #3 on
Contrastive Learning
on imagenet-1k
PointRend: Image Segmentation as Rendering
We present a new method for efficient high-quality image segmentation of objects and scenes.
Ranked #3 on
Instance Segmentation
on COCO 2017 val
A Multigrid Method for Efficiently Training Video Models
We empirically demonstrate a general and robust grid schedule that yields a significant out-of-the-box training speedup without a loss in accuracy for different models (I3D, non-local, SlowFast), datasets (Kinetics, Something-Something, Charades), and training settings (with and without pre-training, 128 GPUs or 1 GPU).
Ranked #1 on
Video Classification
on Kinetics
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
Deep Hough Voting for 3D Object Detection in Point Clouds
Current 3D object detection methods are heavily influenced by 2D detectors.
3D Object Detection
3D Object Detection From Monocular Images
+2
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 #118 on
Neural Architecture Search
on ImageNet
TensorMask: A Foundation for Dense Object Segmentation
To formalize this, we treat dense instance segmentation as a prediction task over 4D tensors and present a general framework called TensorMask that explicitly captures this geometry and enables novel operators on 4D tensors.
Ranked #90 on
Instance Segmentation
on COCO test-dev
Panoptic Feature Pyramid Networks
In this work, we perform a detailed study of this minimally extended version of Mask R-CNN with FPN, which we refer to as Panoptic FPN, and show it is a robust and accurate baseline for both tasks.
Ranked #4 on
Panoptic Segmentation
on Indian Driving Dataset
Long-Term Feature Banks for Detailed Video Understanding
To understand the world, we humans constantly need to relate the present to the past, and put events in context.
Ranked #4 on
Egocentric Activity Recognition
on EPIC-KITCHENS-55
SlowFast Networks for Video Recognition
We present SlowFast networks for video recognition.
Ranked #4 on
Action Recognition
on AVA v2.1
Feature Denoising for Improving Adversarial Robustness
This study suggests that adversarial perturbations on images lead to noise in the features constructed by these networks.
Ranked #1 on
Adversarial Defense
on CAAD 2018
GLoMo: Unsupervised Learning of Transferable Relational Graphs
We also show that the learned graphs are generic enough to be transferred to different embeddings on which the graphs have not been trained (including GloVe embeddings, ELMo embeddings, and task-specific RNN hidden units), or embedding-free units such as image pixels.
Rethinking ImageNet Pre-training
We report competitive results on object detection and instance segmentation on the COCO dataset using standard models trained from random initialization.
Ranked #81 on
Object Detection
on COCO minival
GLoMo: Unsupervisedly Learned Relational Graphs as Transferable Representations
We also show that the learned graphs are generic enough to be transferred to different embeddings on which the graphs have not been trained (including GloVe embeddings, ELMo embeddings, and task-specific RNN hidden unit), or embedding-free units such as image pixels.
Exploring the Limits of Weakly Supervised Pretraining
ImageNet classification is the de facto pretraining task for these models.
Ranked #221 on
Image Classification
on ImageNet
(using extra training data)
Group Normalization
FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.
Ranked #140 on
Object Detection
on COCO minival
Panoptic Segmentation
We propose and study a task we name panoptic segmentation (PS).
Ranked #23 on
Panoptic Segmentation
on Cityscapes val
(using extra training data)
Data Distillation: Towards Omni-Supervised Learning
We investigate omni-supervised learning, a special regime of semi-supervised learning in which the learner exploits all available labeled data plus internet-scale sources of unlabeled data.
Learning to Segment Every Thing
Most methods for object instance segmentation require all training examples to be labeled with segmentation masks.
Non-local Neural Networks
Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time.
Ranked #8 on
Action Classification
on Toyota Smarthome dataset
(using extra training data)
Transitive Invariance for Self-supervised Visual Representation Learning
The objects are connected by two types of edges which correspond to two types of invariance: "different instances but a similar viewpoint and category" and "different viewpoints of the same instance".
Focal Loss for Dense Object Detection
Our novel Focal Loss focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training.
Ranked #3 on
Region Proposal
on COCO test-dev
Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
To achieve this result, we adopt a hyper-parameter-free linear scaling rule for adjusting learning rates as a function of minibatch size and develop a new warmup scheme that overcomes optimization challenges early in training.
Detecting and Recognizing Human-Object Interactions
Our hypothesis is that the appearance of a person -- their pose, clothing, action -- is a powerful cue for localizing the objects they are interacting with.
Ranked #53 on
Human-Object Interaction Detection
on HICO-DET
Mask R-CNN
Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask for each instance.
Ranked #1 on
Keypoint Estimation
on GRIT
Feature Pyramid Networks for Object Detection
Feature pyramids are a basic component in recognition systems for detecting objects at different scales.
Ranked #3 on
Pedestrian Detection
on TJU-Ped-campus
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
Is Faster R-CNN Doing Well for Pedestrian Detection?
Detecting pedestrian has been arguably addressed as a special topic beyond general object detection.
Ranked #19 on
Pedestrian Detection
on Caltech
R-FCN: Object Detection via Region-based Fully Convolutional Networks
In contrast to previous region-based detectors such as Fast/Faster R-CNN that apply a costly per-region subnetwork hundreds of times, our region-based detector is fully convolutional with almost all computation shared on the entire image.
Ranked #4 on
Real-Time Object Detection
on PASCAL VOC 2007
ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation
Large-scale data is of crucial importance for learning semantic segmentation models, but annotating per-pixel masks is a tedious and inefficient procedure.
Instance-sensitive Fully Convolutional Networks
In contrast to the previous FCN that generates one score map, our FCN is designed to compute a small set of instance-sensitive score maps, each of which is the outcome of a pixel-wise classifier of a relative position to instances.
Identity Mappings in Deep Residual Networks
Deep residual networks have emerged as a family of extremely deep architectures showing compelling accuracy and nice convergence behaviors.
Ranked #17 on
Image Classification
on Kuzushiji-MNIST
Instance-aware Semantic Segmentation via Multi-task Network Cascades
We develop an algorithm for the nontrivial end-to-end training of this causal, cascaded structure.
Ranked #3 on
Multi-Human Parsing
on PASCAL-Part
Deep Residual Learning for Image Recognition
Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
Ranked #1 on
Image Classification
on cifar100
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals.
Ranked #2 on
Vessel Detection
on Vessel detection Dateset
Sparse Projections for High-Dimensional Binary Codes
This paper addresses the problem of learning long binary codes from high-dimensional data.
A Geodesic-Preserving Method for Image Warping
The image projections will turn the straight lines into curved "geodesic lines", and it is fundamentally impossible to keep all these lines straight.
Accelerating Very Deep Convolutional Networks for Classification and Detection
This paper aims to accelerate the test-time computation of convolutional neural networks (CNNs), especially very deep CNNs that have substantially impacted the computer vision community.
Object Detection Networks on Convolutional Feature Maps
We discover that aside from deep feature maps, a deep and convolutional per-region classifier is of particular importance for object detection, whereas latest superior image classification models (such as ResNets and GoogLeNets) do not directly lead to good detection accuracy without using such a per-region classifier.
BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation
Recent leading approaches to semantic segmentation rely on deep convolutional networks trained with human-annotated, pixel-level segmentation masks.
Ranked #46 on
Semantic Segmentation
on PASCAL VOC 2012 test
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
In this work, we study rectifier neural networks for image classification from two aspects.
Image Super-Resolution Using Deep Convolutional Networks
We further show that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network.
Ranked #2 on
Video Super-Resolution
on Xiph HD - 4x upscaling
Convolutional Neural Networks at Constrained Time Cost
Though recent advanced convolutional neural networks (CNNs) have been improving the image recognition accuracy, the models are getting more complex and time-consuming.
Convolutional Feature Masking for Joint Object and Stuff Segmentation
The current leading approaches for semantic segmentation exploit shape information by extracting CNN features from masked image regions.
Ranked #61 on
Semantic Segmentation
on PASCAL Context
Efficient and Accurate Approximations of Nonlinear Convolutional Networks
This paper aims to accelerate the test-time computation of deep convolutional neural networks (CNNs).
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
This requirement is "artificial" and may reduce the recognition accuracy for the images or sub-images of an arbitrary size/scale.
Ranked #26 on
Object Detection
on PASCAL VOC 2007
Product Sparse Coding
In this paper, we study a special case of sparse coding in which the codebook is a Cartesian product of two subcodebooks.
K-Means Hashing: An Affinity-Preserving Quantization Method for Learning Binary Compact Codes
We propose a novel Affinity-Preserving K-means algorithm which simultaneously performs k-means clustering and learns the binary indices of the quantized cells.
Optimized Product Quantization for Approximate Nearest Neighbor Search
Product quantization is an effective vector quantization approach to compactly encode high-dimensional vectors for fast approximate nearest neighbor (ANN) search.
Single Image Haze Removal Using Dark Channel Prior
The dark channel prior is a kind of statistics of outdoor haze-free images.
Ranked #1 on
Single Image Haze Removal
on RESIDE
