Search Results for author:
Found 17 papers, 5 papers with code
DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models
In contrast, synthetic data can be freely available using a generative model (e. g., DALL-E, Stable Diffusion).
GoSum: Extractive Summarization of Long Documents by Reinforcement Learning and Graph Organized discourse state
In this paper, we propose GoSum, a novel graph and reinforcement learning based extractive model for long-paper summarization.
Ranked #4 on
Text Summarization
on Pubmed
BiViT: Extremely Compressed Binary Vision Transformer
To solve this, we propose Softmax-aware Binarization, which dynamically adapts to the data distribution and reduces the error caused by binarization.
Real-time End-to-End Video Text Spotter with Contrastive Representation Learning
Our contributions are three-fold: 1) CoText simultaneously address the three tasks (e. g., text detection, tracking, recognition) in a real-time end-to-end trainable framework.
Binarizing by Classification: Is soft function really necessary?
Binary neural network leverages the $Sign$ function to binarize real values, and its non-derivative property inevitably brings huge gradient errors during backpropagation.
Ranked #1 on
Binarization
on ImageNet
(Top 1 Accuracy metric)
Data-Free Quantization with Accurate Activation Clipping and Adaptive Batch Normalization
In this paper, we present a simple yet effective data-free quantization method with accurate activation clipping and adaptive batch normalization.
End-to-End Video Text Spotting with Transformer
Recent video text spotting methods usually require the three-staged pipeline, i. e., detecting text in individual images, recognizing localized text, tracking text streams with post-processing to generate final results.
The Observability in Unobservable Systems
In this paper, we introduce the concept of observability of targeted state variables for systems that may not be fully observable.
Contrastive Learning of Semantic and Visual Representations for Text Tracking
Semantic representation is of great benefit to the video text tracking(VTT) task that requires simultaneously classifying, detecting, and tracking texts in the video.
A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer
Most existing video text spotting benchmarks focus on evaluating a single language and scenario with limited data.
Divide-and-Assemble: Learning Block-wise Memory for Unsupervised Anomaly Detection
Surprisingly, by varying the granularity of division on feature maps, we are able to modulate the reconstruction capability of the model for both normal and abnormal samples.
Polygon-free: Unconstrained Scene Text Detection with Box Annotations
For example, without using polygon annotations, PSENet achieves an 80. 5% F-score on TotalText [3] (vs. 80. 9% of fully supervised counterpart), 31. 1% better than training directly with upright bounding box annotations, and saves 80%+ labeling costs.
A Local Search Framework for Experimental Design
We present a local search framework to design and analyze both combinatorial algorithms and rounding algorithms for experimental design problems.
TextCohesion: Detecting Text for Arbitrary Shapes
In this paper, we propose a pixel-wise method named TextCohesion for scene text detection, which splits a text instance into five key components: a Text Skeleton and four Directional Pixel Regions.
Ranked #1 on
Curved Text Detection
on SCUT-CTW1500
Brain Tumor Segmentation Based on Refined Fully Convolutional Neural Networks with A Hierarchical Dice Loss
Since the proposal of fully convolutional neural network (FCNN), it has been widely used in semantic segmentation because of its high accuracy of pixel-wise classification as well as high precision of localization.
An Automatic Diagnosis Method of Facial Acne Vulgaris Based on Convolutional Neural Network
The core of our method is to extract features of images based on convolutional neural network and achieve classification by classifier.
