Search Results for author:
Found 33 papers, 29 papers with code
Segment Anything
We introduce the Segment Anything (SA) project: a new task, model, and dataset for image segmentation.
Ranked #2 on
Zero-Shot Instance Segmentation
on LVIS v1.0 val
The effectiveness of MAE pre-pretraining for billion-scale pretraining
While MAE has only been shown to scale with the size of models, we find that it scales with the size of the training dataset as well.
Ranked #1 on
Few-Shot Image Classification
on ImageNet - 10-shot
(using extra training data)
Revisiting Weakly Supervised Pre-Training of Visual Perception Models
Model pre-training is a cornerstone of modern visual recognition systems.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
(using extra training data)
Fine-Grained Image Classification
Out-of-Distribution Generalization
+3
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
Early Convolutions Help Transformers See Better
To test whether this atypical design choice causes an issue, we analyze the optimization behavior of ViT models with their original patchify stem versus a simple counterpart where we replace the ViT stem by a small number of stacked stride-two 3*3 convolutions.
Boundary IoU: Improving Object-Centric Image Segmentation Evaluation
We perform an extensive analysis across different error types and object sizes and show that Boundary IoU is significantly more sensitive than the standard Mask IoU measure to boundary errors for large objects and does not over-penalize errors on smaller objects.
Fast and Accurate Model Scaling
This leads us to propose a simple fast compound scaling strategy that encourages primarily scaling model width, while scaling depth and resolution to a lesser extent.
Evaluating Large-Vocabulary Object Detectors: The Devil is in the Details
On one hand, this is desirable as it treats all classes equally.
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.
LVIS: A Dataset for Large Vocabulary Instance Segmentation
We plan to collect ~2 million high-quality instance segmentation masks for over 1000 entry-level object categories in 164k images.
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.
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
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
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.
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
Learning Features by Watching Objects Move
Given the extensive evidence that motion plays a key role in the development of the human visual system, we hope that this straightforward approach to unsupervised learning will be more effective than cleverly designed 'pretext' tasks studied in the literature.
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
A MultiPath Network for Object Detection
To address these challenges, we test three modifications to the standard Fast R-CNN object detector: (1) skip connections that give the detector access to features at multiple network layers, (2) a foveal structure to exploit object context at multiple object resolutions, and (3) an integral loss function and corresponding network adjustment that improve localization.
Ranked #104 on
Instance Segmentation
on COCO test-dev
Unsupervised Learning of Edges
In this work we present a simple yet effective approach for training edge detectors without human supervision.
Semantic Amodal Segmentation
Specifically, we create an amodal segmentation of each image: the full extent of each region is marked, not just the visible pixels.
What makes for effective detection proposals?
Current top performing object detectors employ detection proposals to guide the search for objects, thereby avoiding exhaustive sliding window search across images.
From Captions to Visual Concepts and Back
The language model learns from a set of over 400, 000 image descriptions to capture the statistics of word usage.
Ranked #1 on
Image Captioning
on COCO Captions test
Fast Edge Detection Using Structured Forests
We formulate the problem of predicting local edge masks in a structured learning framework applied to random decision forests.
Local Decorrelation For Improved Detection
In fact, orthogonal trees with our locally decorrelated features outperform oblique trees trained over the original features at a fraction of the computational cost.
Microsoft COCO: Common Objects in Context
We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding.
