Search Results for author:
Found 55 papers, 21 papers with code
Unified Entropy Optimization for Open-Set Test-Time Adaptation
To address these issues, we propose a simple but effective framework called unified entropy optimization (UniEnt), which is capable of simultaneously adapting to covariate-shifted in-distribution (csID) data and detecting covariate-shifted out-of-distribution (csOOD) data.
Branch-Tuning: Balancing Stability and Plasticity for Continual Self-Supervised Learning
Self-supervised learning (SSL) has emerged as an effective paradigm for deriving general representations from vast amounts of unlabeled data.
Towards Non-Exemplar Semi-Supervised Class-Incremental Learning
On the other hand, Semi-IPC learns a prototype for each class with unsupervised regularization, enabling the model to incrementally learn from partially labeled new data while maintaining the knowledge of old classes.
Multi-scale Unified Network for Image Classification
Convolutional Neural Networks (CNNs) have advanced significantly in visual representation learning and recognition.
Ensemble Quadratic Assignment Network for Graph Matching
In this paper, we propose a graph neural network (GNN) based approach to combine the advantages of data-driven and traditional methods.
Active Generalized Category Discovery
Generalized Category Discovery (GCD) is a pragmatic and challenging open-world task, which endeavors to cluster unlabeled samples from both novel and old classes, leveraging some labeled data of old classes.
Revisiting Confidence Estimation: Towards Reliable Failure Prediction
Reliable confidence estimation is a challenging yet fundamental requirement in many risk-sensitive applications.
Open-world Machine Learning: A Review and New Outlooks
This paper aims to provide a comprehensive introduction to the emerging open-world machine learning paradigm, to help researchers build more powerful AI systems in their respective fields, and to promote the development of artificial general intelligence.
Federated Class-Incremental Learning with Prototype Guided Transformer
On the other hand, our approach utilizes a pre-trained model as the backbone and utilizes LoRA to fine-tune with a tiny amount of parameters when learning new classes.
LANS: A Layout-Aware Neural Solver for Plane Geometry Problem
Existing neural solvers take GPS as a vision-language task but are short in the representation of geometry diagrams that carry rich and complex layout information.
Unified Classification and Rejection: A One-versus-All Framework
Previous methods mostly take post-training score transformation or hybrid models to ensure low scores on OOD inputs while separating known classes.
Towards Reliable Domain Generalization: A New Dataset and Evaluations
We advocate that researchers in the DG community refer to dynamic performance of methods for more comprehensive and reliable evaluation.
Class Incremental Learning with Self-Supervised Pre-Training and Prototype Learning
This is hard for DNN because it tends to focus on fitting to new classes while ignoring old classes, a phenomenon known as catastrophic forgetting.
ICDAR 2023 Competition on Structured Text Extraction from Visually-Rich Document Images
It is hoped that this competition will attract many researchers in the field of CV and NLP, and bring some new thoughts to the field of Document AI.
On the Hidden Mystery of OCR in Large Multimodal Models
In this paper, we conducted a comprehensive evaluation of Large Multimodal Models, such as GPT4V and Gemini, in various text-related visual tasks including Text Recognition, Scene Text-Centric Visual Question Answering (VQA), Document-Oriented VQA, Key Information Extraction (KIE), and Handwritten Mathematical Expression Recognition (HMER).
OpenMix: Exploring Outlier Samples for Misclassification Detection
Reliable confidence estimation for deep neural classifiers is a challenging yet fundamental requirement in high-stakes applications.
Dynamics-Aware Loss for Learning with Label Noise
Label noise poses a serious threat to deep neural networks (DNNs).
Cross-Modal Causal Intervention for Medical Report Generation
Medical report generation (MRG) is essential for computer-aided diagnosis and medication guidance, which can relieve the heavy burden of radiologists by automatically generating the corresponding medical reports according to the given radiology image.
Rethinking Confidence Calibration for Failure Prediction
We investigate this problem and reveal that popular confidence calibration methods often lead to worse confidence separation between correct and incorrect samples, making it more difficult to decide whether to trust a prediction or not.
Average of Pruning: Improving Performance and Stability of Out-of-Distribution Detection
Detecting Out-of-distribution (OOD) inputs have been a critical issue for neural networks in the open world.
A Multi-Modal Neural Geometric Solver with Textual Clauses Parsed from Diagram
Geometry problem solving (GPS) is a high-level mathematical reasoning requiring the capacities of multi-modal fusion and geometric knowledge application.
Ranked #1 on
Mathematical Reasoning
on PGPS9K
Visual Traffic Knowledge Graph Generation from Scene Images
Although previous works on traffic scene understanding have achieved great success, most of them stop at a lowlevel perception stage, such as road segmentation and lane detection, and few concern high-level understanding.
Biologically Plausible Training of Deep Neural Networks Using a Top-down Credit Assignment Network
We further introduce a brain-inspired credit diffusion mechanism, significantly reducing the TDCA-network's parameter complexity, thereby greatly accelerating training without compromising the network's performance. Our experiments involving non-convex function optimization, supervised learning, and reinforcement learning reveal that a well-trained TDCA-network outperforms back-propagation across various settings.
Plane Geometry Diagram Parsing
Geometry diagram parsing plays a key role in geometry problem solving, wherein the primitive extraction and relation parsing remain challenging due to the complex layout and between-primitive relationship.
Ranked #1 on
Scene Parsing
on PGDP5K
Unsupervised Structure-Texture Separation Network for Oracle Character Recognition
Second, transformation is achieved via swapping the learned textures across domains and a classifier for final classification is trained to predict the labels of the transformed scanned characters.
Document Dewarping with Control Points
In this paper, we propose a simple yet effective approach to rectify distorted document image by estimating control points and reference points.
Towards Open-Set Text Recognition via Label-to-Prototype Learning
Scene text recognition is a popular topic and extensively used in the industry.
Emergence of Machine Language: Towards Symbolic Intelligence with Neural Networks
Moreover, through experiments we show that discrete language representation has several advantages compared with continuous feature representation, from the aspects of interpretability, generalization, and robustness.
Class-Incremental Learning via Dual Augmentation
Deep learning systems typically suffer from catastrophic forgetting of past knowledge when acquiring new skills continually.
Proxy Graph Matching with Proximal Matching Networks
It consists of three parts: a graph neural network to generate a high-level local feature, an attention-based module to normalize the rotational transform, and a global feature matching module based on proximal optimization.
Delving into Feature Space: Improving Adversarial Robustness by Feature Spectral Regularization
Comprehensive experiments demonstrate that FSR is effective to alleviate the dominance of larger eigenvalues and improve adversarial robustness on different datasets.
Prototype Augmentation and Self-Supervision for Incremental Learning
Despite the impressive performance in many individual tasks, deep neural networks suffer from catastrophic forgetting when learning new tasks incrementally.
Semantic-Aware Video Text Detection
To overcome the lack of character-level annotations, we propose a novel weakly-supervised character center detection module, which only uses word-level annotated real images to generate character-level labels.
Dewarping Document Image By Displacement Flow Estimation with Fully Convolutional Network
As camera-based documents are increasingly used, the rectification of distorted document images becomes a need to improve the recognition performance.
Misclassification Detection via Class Augmentation
In spite of the simplicity, extensive experiments demonstrate that the misclassification detection performance of DNNs can be significantly improved by seeing more generated pseudo-classes during training.
Weakly-Supervised Arbitrary-Shaped Text Detection with Expectation-Maximization Algorithm
We propose an Expectation-Maximization (EM) based weakly-supervised learning framework to train an accurate arbitrary-shaped text detector using only a small amount of polygon-level annotated data combined with a large amount of weakly annotated data.
Towards Robust Pattern Recognition: A Review
The accuracies for many pattern recognition tasks have increased rapidly year by year, achieving or even outperforming human performance.
ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition -- RRC-MLT-2019
With the growing cosmopolitan culture of modern cities, the need of robust Multi-Lingual scene Text (MLT) detection and recognition systems has never been more immense.
Cultural Vocal Bursts Intensity Prediction
General Classification
+2
Arbitrary Shape Scene Text Detection with Adaptive Text Region Representation
Here, recurrent neural network based adaptive text region representation is proposed for text region refinement, where a pair of boundary points are predicted each time step until no new points are found.
BlockQNN: Efficient Block-wise Neural Network Architecture Generation
The block-wise generation brings unique advantages: (1) it yields state-of-the-art results in comparison to the hand-crafted networks on image classification, particularly, the best network generated by BlockQNN achieves 2. 35% top-1 error rate on CIFAR-10.
Anomaly Detection via Minimum Likelihood Generative Adversarial Networks
Anomaly detection aims to detect abnormal events by a model of normality.
Multi-task Layout Analysis for Historical Handwritten Documents Using Fully Convolutional Networks
Layout analysis is a fundamental process in document image analysis and understanding.
SCAN: Sliding Convolutional Attention Network for Scene Text Recognition
Scene text recognition has drawn great attentions in the community of computer vision and artificial intelligence due to its challenges and wide applications.
Robust Classification with Convolutional Prototype Learning
To improve the robustness, we propose a novel learning framework called convolutional prototype learning (CPL).
Scene Text Recognition with Sliding Convolutional Character Models
In this paper, we investigate the intrinsic characteristics of text recognition, and inspired by human cognition mechanisms in reading texts, we propose a scene text recognition method with character models on convolutional feature map.
Practical Block-wise Neural Network Architecture Generation
Convolutional neural networks have gained a remarkable success in computer vision.
Deep Direct Regression for Multi-Oriented Scene Text Detection
To verify this point of view, we propose a deep direct regression based method for multi-oriented scene text detection.
Drawing and Recognizing Chinese Characters with Recurrent Neural Network
In this paper, we propose a framework by using the recurrent neural network (RNN) as both a discriminative model for recognizing Chinese characters and a generative model for drawing (generating) Chinese characters.
Online and Offline Handwritten Chinese Character Recognition: A Comprehensive Study and New Benchmark
Furthermore, although directMap+convNet can achieve the best results and surpass human-level performance, we show that writer adaptation in this case is still effective.
Data Augmentation
Offline Handwritten Chinese Character Recognition
Natural Scene Character Recognition Using Robust PCA and Sparse Representation
Natural scene character recognition is challenging due to the cluttered background, which is hard to separate from text.
Hybrid CNN and Dictionary-Based Models for Scene Recognition and Domain Adaptation
Learned from a large-scale training dataset, CNN features are much more discriminative and accurate than the hand-crafted features.
Task-Driven Feature Pooling for Image Classification
Feature pooling is an important strategy to achieve high performance in image classification.
A Fast Projected Fixed-Point Algorithm for Large Graph Matching
In particular, with high accuracy, our algorithm takes only a few seconds (in a PC) to match two graphs of 1, 000 nodes.
Robust Metric Learning by Smooth Optimization
Most existing distance metric learning methods assume perfect side information that is usually given in pairwise or triplet constraints.
