Search Results
MaskConver: Revisiting Pure Convolution Model for Panoptic Segmentation
With ResNet50 backbone, our MaskConver achieves 53. 6% PQ on the COCO panoptic val set, outperforming the modern convolution-based model, Panoptic FCN, by 9. 3% as well as transformer-based models such as Mask2Former (+1. 7% PQ) and kMaX-DeepLab (+0. 6% PQ).
Ranked #8 on
Panoptic Segmentation
on COCO test-dev
A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation
In this paper, we comprehensively study three architecture design choices on ViT -- spatial reduction, doubled channels, and multiscale features -- and demonstrate that a vanilla ViT architecture can fulfill this goal without handcrafting multiscale features, maintaining the original ViT design philosophy.
Towards End-to-End Unified Scene Text Detection and Layout Analysis
tensorflow/models
•
•
CVPR 2022
In this paper, we bring them together and introduce the task of unified scene text detection and layout analysis.
Contextualized Spatio-Temporal Contrastive Learning with Self-Supervision
tensorflow/models
•
•
CVPR 2022
Modern self-supervised learning algorithms typically enforce persistency of instance representations across views.
Proper Reuse of Image Classification Features Improves Object Detection
tensorflow/models
•
•
CVPR 2022
A common practice in transfer learning is to initialize the downstream model weights by pre-training on a data-abundant upstream task.
Adversarial Training Methods for Semi-Supervised Text Classification
We extend adversarial and virtual adversarial training to the text domain by applying perturbations to the word embeddings in a recurrent neural network rather than to the original input itself.
Ranked #22 on
Sentiment Analysis
on IMDb
General Classification
Semi-Supervised Text Classification
+2
MobileNetV2: Inverted Residuals and Linear Bottlenecks
tensorflow/models
•
•
CVPR 2018
In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes.
Ranked #7 on
Retinal OCT Disease Classification
on OCT2017
AutoAugment: Learning Augmentation Policies from Data
In our implementation, we have designed a search space where a policy consists of many sub-policies, one of which is randomly chosen for each image in each mini-batch.
Ranked #6 on
Data Augmentation
on ImageNet
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 #20 on
Image Classification
on Kuzushiji-MNIST
Cognitive Mapping and Planning for Visual Navigation
tensorflow/models
•
•
CVPR 2017
The accumulated belief of the world enables the agent to track visited regions of the environment.
