Search Results for author:
Found 31 papers, 19 papers with code
GPT-4o System Card
We also include third-party assessments on dangerous capabilities, as well as discussion of potential societal impacts of GPT-4o's text and vision capabilities.
Ranked #2 on
Multiple-choice
on Neptune-Full
R-MAE: Regions Meet Masked Autoencoders
In this work, we explore regions as a potential visual analogue of words for self-supervised image representation learning.
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
Point-Level Region Contrast for Object Detection Pre-Training
In this work we present point-level region contrast, a self-supervised pre-training approach for the task of object detection.
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.
Mask2Former for Video Instance Segmentation
We find Mask2Former also achieves state-of-the-art performance on video instance segmentation without modifying the architecture, the loss or even the training pipeline.
Ranked #16 on
Video Instance Segmentation
on YouTube-VIS validation
Masked-attention Mask Transformer for Universal Image Segmentation
While only the semantics of each task differ, current research focuses on designing specialized architectures for each task.
Ranked #3 on
Semantic Segmentation
on Mapillary val
Recognizing Scenes from Novel Viewpoints
Humans can perceive scenes in 3D from a handful of 2D views.
Per-Pixel Classification is Not All You Need for Semantic Segmentation
Overall, the proposed mask classification-based method simplifies the landscape of effective approaches to semantic and panoptic segmentation tasks and shows excellent empirical results.
Ranked #4 on
Semantic Segmentation
on Mapillary val
Pointly-Supervised Instance Segmentation
Our experiments show that the new module is more suitable for the point-based supervision.
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.
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.
Evaluating Large-Vocabulary Object Detectors: The Devil is in the Details
On one hand, this is desirable as it treats all classes equally.
TrackFormer: Multi-Object Tracking with Transformers
The challenging task of multi-object tracking (MOT) requires simultaneous reasoning about track initialization, identity, and spatio-temporal trajectories.
Ranked #1 on
Multi-Object Tracking
on MOT17
(e2e-MOT metric)
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.
End-to-End Object Detection with Transformers
We present a new method that views object detection as a direct set prediction problem.
Ranked #22 on
Panoptic Segmentation
on COCO minival
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
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
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
WSD algorithm based on a new method of vector-word contexts proximity calculation via epsilon-filtration
It is necessary to select the meaning of the word in the sentence automatically.
Calculated attributes of synonym sets
Several geometric characteristics of the synset words are introduced: the interior of synset, the synset word rank and centrality.
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)
Joint Graph Decomposition & Node Labeling: Problem, Algorithms, Applications
In order to find feasible solutions efficiently, we define two local search algorithms that converge monotonously to a local optimum, offering a feasible solution at any time.
Analyzing Modular CNN Architectures for Joint Depth Prediction and Semantic Segmentation
Towards this end we propose a Convolutional Neural Network (CNN) architecture that fuses the state of the state-of-the-art results for depth estimation and semantic labeling.
Global Hypothesis Generation for 6D Object Pose Estimation
Most modern approaches solve this task in three steps: i) Compute local features; ii) Generate a pool of pose-hypotheses; iii) Select and refine a pose from the pool.
InstanceCut: from Edges to Instances with MultiCut
This work addresses the task of instance-aware semantic segmentation.
Joint Graph Decomposition and Node Labeling: Problem, Algorithms, Applications
In order to find feasible solutions efficiently, we define two local search algorithms that converge monotonously to a local optimum, offering a feasible solution at any time.
Joint M-Best-Diverse Labelings as a Parametric Submodular Minimization
In particular, the joint M-best diverse labelings can be obtained by running a non-parametric submodular minimization (in the special case - max-flow) solver for M different values of $\gamma$ in parallel, for certain diversity measures.
Inferring M-Best Diverse Labelings in a Single One
We consider the task of finding M-best diverse solutions in a graphical model.
M-Best-Diverse Labelings for Submodular Energies and Beyond
In this work we show that the joint inference of $M$ best diverse solutions can be formulated as a submodular energy minimization if the original MAP-inference problem is submodular, hence fast inference techniques can be used.
Joint Training of Generic CNN-CRF Models with Stochastic Optimization
We propose a new CNN-CRF end-to-end learning framework, which is based on joint stochastic optimization with respect to both Convolutional Neural Network (CNN) and Conditional Random Field (CRF) parameters.
