Search Results for author:
Found 19 papers, 12 papers with code
Revisiting Multi-Scale Feature Fusion for Semantic Segmentation
It is commonly believed that high internal resolution combined with expensive operations (e. g. atrous convolutions) are necessary for accurate semantic segmentation, resulting in slow speed and large memory usage.
Open-Vocabulary Image Segmentation
First, it learns to propose segmentation masks for possible organizations.
Combined Scaling for Open-Vocabulary Image Classification
Second, while increasing the dataset size and the model size has been the defacto method to improve the performance of deep learning models like BASIC, the effect of a large contrastive batch size on such contrastive-trained image-text models is not well-understood.
Ranked #2 on
Zero-Shot Transfer Image Classification
on ImageNet
(using extra training data)
Gradual Domain Adaptation in the Wild: When Intermediate Distributions are Absent
It is shown that under the following two assumptions: (a) access to samples from intermediate distributions, and (b) samples being annotated with the amount of change from the source distribution; self-training can be successfully applied on gradually shifted samples to adapt the model toward the target distribution.
Multi-Task Self-Training for Learning General Representations
The results suggest self-training is a promising direction to aggregate labeled and unlabeled training data for learning general feature representations.
Gradual Domain Adaptation in the Wild:When Intermediate Distributions are Absent
It has been shown that under the following two assumptions: (a) access to samples from intermediate distributions, and (b) samples being annotated with the amount of change from the source distribution, self-training can be successfully applied on gradually shifted samples to adapt the model toward the target distribution.
Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation
Our baseline model outperforms the LVIS 2020 Challenge winning entry by +3. 6 mask AP on rare categories.
Ranked #1 on
Instance Segmentation
on LVIS v1.0 val
Rethinking Pre-training and Self-training
For example, on the COCO object detection dataset, pre-training benefits when we use one fifth of the labeled data, and hurts accuracy when we use all labeled data.
Ranked #1 on
Semantic Segmentation
on PASCAL VOC 2012 test
(using extra training data)
SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization
We propose SpineNet, a backbone with scale-permuted intermediate features and cross-scale connections that is learned on an object detection task by Neural Architecture Search.
Ranked #7 on
Image Classification
on iNaturalist
MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devices
We propose MnasFPN, a mobile-friendly search space for the detection head, and combine it with latency-aware architecture search to produce efficient object detection models.
Ranked #198 on
Object Detection
on COCO test-dev
Learning Data Augmentation Strategies for Object Detection
Importantly, the best policy found on COCO may be transferred unchanged to other detection datasets and models to improve predictive accuracy.
Ranked #54 on
Object Detection
on COCO test-dev
NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection
Here we aim to learn a better architecture of feature pyramid network for object detection.
Ranked #7 on
Real-Time Object Detection
on COCO
Adjustable Real-time Style Transfer
Artistic style transfer is the problem of synthesizing an image with content similar to a given image and style similar to another.
DropBlock: A regularization method for convolutional networks
This lack of success of dropout for convolutional layers is perhaps due to the fact that activation units in convolutional layers are spatially correlated so information can still flow through convolutional networks despite dropout.
Ranked #452 on
Image Classification
on ImageNet
Exploring the structure of a real-time, arbitrary neural artistic stylization network
In this paper, we present a method which combines the flexibility of the neural algorithm of artistic style with the speed of fast style transfer networks to allow real-time stylization using any content/style image pair.
Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation
CNN architectures have terrific recognition performance but rely on spatial pooling which makes it difficult to adapt them to tasks that require dense, pixel-accurate labeling.
Ranked #61 on
Semantic Segmentation
on Cityscapes test
Occlusion Coherence: Detecting and Localizing Occluded Faces
The presence of occluders significantly impacts object recognition accuracy.
Occlusion Coherence: Localizing Occluded Faces with a Hierarchical Deformable Part Model
The presence of occluders significantly impacts performance of systems for object recognition.
Parsing Occluded People
Occlusion poses a significant difficulty for object recognition due to the combinatorial diversity of possible occlusion patterns.
