Search Results for author:
Found 92 papers, 31 papers with code
Transfer Learning and Prediction Consistency for Detecting Offensive Spans of Text
Toxic span detection is the task of recognizing offensive spans in a text snippet.
Variational Label Enhancement
Label distribution covers a certain number of labels, representing the degree to which each label describes the instance.
Self-Attention Graph Residual Convolutional Networks for Event Detection with dependency relations
While existing GCN-based methods explore latent node-to-node dependency relations according to a stationary adjacency tensor, an attention-based dynamic tensor, which can pay much attention to the key node like event trigger or its neighboring nodes, has not been developed.
Reduction-based Pseudo-label Generation for Instance-dependent Partial Label Learning
However, these methods overlook a critical aspect of ID-PLL: the training model is prone to overfitting on incorrect candidate labels, thereby providing poor supervision information and creating a bottleneck in training.
LSVOS Challenge Report: Large-scale Complex and Long Video Object Segmentation
Despite the promising performance of current video segmentation models on existing benchmarks, these models still struggle with complex scenes.
Progressively Label Enhancement for Large Language Model Alignment
Due to challenges in stability and scalability with RLHF stages, which arise from the complex interactions between multiple models, researchers are exploring alternative methods to achieve effects comparable to those of RLHF.
ChipExpert: The Open-Source Integrated-Circuit-Design-Specific Large Language Model
Finally, to mitigate the hallucinations of ChipExpert, we have developed a Retrieval-Augmented Generation (RAG) system, based on the IC design knowledge base.
ISPO: An Integrated Ontology of Symptom Phenotypes for Semantic Integration of Traditional Chinese Medical Data
Methods: To construct an integrated ontology of symptom phenotypes (ISPO), we manually annotated classical TCM textbooks and large-scale Chinese electronic medical records (EMRs) to collect symptom terms with support from a medical text annotation system.
Exploring Real World Map Change Generalization of Prior-Informed HD Map Prediction Models
Recent work on these models proposes training robust online mapping systems using low quality map priors with synthetic perturbations in an attempt to simulate out-of-date HD map priors.
How to Understand Named Entities: Using Common Sense for News Captioning
Our approach consists of three modules: (a) Filter Module aims to clarify the common sense concerning a named entity from two aspects: what does it mean?
Rule-driven News Captioning
News captioning task aims to generate sentences by describing named entities or concrete events for an image with its news article.
Causality is all you need
In this paper, we propose the Causal Graph Routing (CGR) framework, an integrated causal scheme relying entirely on the intervention mechanisms to reveal the cause-effect forces hidden in data.
Can Class-Priors Help Single-Positive Multi-Label Learning?
Single-positive multi-label learning (SPMLL) is a typical weakly supervised multi-label learning problem, where each training example is annotated with only one positive label.
T2IW: Joint Text to Image & Watermark Generation
Furthermore, we strengthen the watermark robustness of our approach by subjecting the compound image to various post-processing attacks, with minimal pixel distortion observed in the revealed watermark.
Variational Label-Correlation Enhancement for Congestion Prediction
In order to fully exploit the inherent spatial label-correlation between neighboring grids, we propose a novel approach, {\ours}, i. e., VAriational Label-Correlation Enhancement for Congestion Prediction, which considers the local label-correlation in the congestion map, associating the estimated congestion value of each grid with a local label-correlation weight influenced by its surrounding grids.
Towards Effective Visual Representations for Partial-Label Learning
Under partial-label learning (PLL) where, for each training instance, only a set of ambiguous candidate labels containing the unknown true label is accessible, contrastive learning has recently boosted the performance of PLL on vision tasks, attributed to representations learned by contrasting the same/different classes of entities.
Scalable Multiple Patterning Layout Decomposition Implemented by a Distribution Evolutionary Algorithm
As the feature size of semiconductor technology shrinks to 10 nm and beyond, the multiple patterning lithography (MPL) attracts more attention from the industry.
Unreliable Partial Label Learning with Recursive Separation
Therefore, a generalized PLL named Unreliable Partial Label Learning (UPLL) is proposed, in which the true label may not be in the candidate label set.
CVM-Cervix: A Hybrid Cervical Pap-Smear Image Classification Framework Using CNN, Visual Transformer and Multilayer Perceptron
Cervical cytopathology image classification is an important method to diagnose cervical cancer.
Progressive Purification for Instance-Dependent Partial Label Learning
Partial label learning (PLL) aims to train multiclass classifiers from the examples each annotated with a set of candidate labels where a fixed but unknown candidate label is correct.
One Positive Label is Sufficient: Single-Positive Multi-Label Learning with Label Enhancement
To cope with the challenge, we investigate single-positive multi-label learning (SPMLL) where each example is annotated with only one relevant label, and show that one can successfully learn a theoretically grounded multi-label classifier for the problem.
Decompositional Generation Process for Instance-Dependent Partial Label Learning
Most existing PLL approaches assume that the incorrect labels in each training example are randomly picked as the candidate labels and model the generation process of the candidate labels in a simple way.
A Distribution Evolutionary Algorithm for the Graph Coloring Problem
Unlike existing estimation of distribution algorithms where a probability model is updated by generated solutions, DEA-PPM employs a distribution population based on a novel probability model, and an orthogonal exploration strategy is introduced to search the distribution space with the assistance of an refinement strategy.
CM-GAN: Image Inpainting with Cascaded Modulation GAN and Object-Aware Training
We propose cascaded modulation GAN (CM-GAN), a new network design consisting of an encoder with Fourier convolution blocks that extract multi-scale feature representations from the input image with holes and a dual-stream decoder with a novel cascaded global-spatial modulation block at each scale level.
Ranked #3 on
Image Inpainting
on Places2
Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation
Instead of directly distilling the generated images of teachers, wavelet knowledge distillation first decomposes the images into different frequency bands with discrete wavelet transformation and then only distills the high frequency bands.
End-to-end video instance segmentation via spatial-temporal graph neural networks
Specifically, graph nodes representing instance features are used for detection and segmentation while graph edges representing instance relations are used for tracking.
Adaptive Cross-Layer Attention for Image Restoration
Non-local attention module has been proven to be crucial for image restoration.
EBHI:A New Enteroscope Biopsy Histopathological H&E Image Dataset for Image Classification Evaluation
Traditional machine learning methods achieve maximum accuracy of 76. 02% and deep learning method achieves a maximum accuracy of 95. 37%.
SpaceEdit: Learning a Unified Editing Space for Open-Domain Image Color Editing
Recently, large pretrained models (e. g., BERT, StyleGAN, CLIP) show great knowledge transfer and generalization capability on various downstream tasks within their domains.
EMDS-6: Environmental Microorganism Image Dataset Sixth Version for Image Denoising, Segmentation, Feature Extraction, Classification and Detection Methods Evaluation
Each type of EM contains 40 original and 40 GT images, in total 1680 EM images.
SpaceEdit: Learning a Unified Editing Space for Open-Domain Image Editing
Recently, large pretrained models (e. g., BERT, StyleGAN, CLIP) have shown great knowledge transfer and generalization capability on various downstream tasks within their domains.
Exploring the Semi-supervised Video Object Segmentation Problem from a Cyclic Perspective
We conduct comprehensive comparison and detailed analysis on challenging benchmarks of DAVIS16, DAVIS17 and Youtube-VOS, demonstrating that the cyclic mechanism is helpful to enhance segmentation quality, improve the robustness of VOS systems, and further provide qualitative comparison and interpretation on how different VOS algorithms work.
Instance-Dependent Partial Label Learning
In this paper, we consider instance-dependent PLL and assume that each example is associated with a latent label distribution constituted by the real number of each label, representing the degree to each label describing the feature.
TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation
With the recent exponential increase in applying Vision Transformer (ViT) to vision tasks, the capability of ViT in adapting cross-domain knowledge, however, remains unexplored in the literature.
Learning by Planning: Language-Guided Global Image Editing
Recently, language-guided global image editing draws increasing attention with growing application potentials.
Learngene: From Open-World to Your Learning Task
Moreover, the learngene, i. e., the gene for learning initialization rules of the target model, is proposed to inherit the meta-knowledge from the collective model and reconstruct a lightweight individual model on the target task.
On the Robustness of Average Losses for Partial-Label Learning
Partial-label learning (PLL) utilizes instances with PLs, where a PL includes several candidate labels but only one is the true label (TL).
A Simple Baseline for Weakly-Supervised Scene Graph Generation
We investigate the weakly-supervised scene graph generation, which is a challenging task since no correspondence of label and object is provided.
Language-Guided Global Image Editing via Cross-Modal Cyclic Mechanism
Given the cycle, we propose several free augmentation strategies to help our model understand various editing requests given the imbalanced dataset.
Semantic Layout Manipulation with High-Resolution Sparse Attention
A core problem of this task is how to transfer visual details from the input images to the new semantic layout while making the resulting image visually realistic.
Mask Guided Matting via Progressive Refinement Network
We propose Mask Guided (MG) Matting, a robust matting framework that takes a general coarse mask as guidance.
Delving into the Cyclic Mechanism in Semi-supervised Video Object Segmentation
In this paper, we address several inadequacies of current video object segmentation pipelines.
A Benchmark and Baseline for Language-Driven Image Editing
To solve this new task, we first present a new language-driven image editing dataset that supports both local and global editing with editing operation and mask annotations.
Compact Learning for Multi-Label Classification
In this paper, we present a compact learning (CL) framework to embed the features and labels simultaneously and with mutual guidance.
High-Resolution Deep Image Matting
Image matting is a key technique for image and video editing and composition.
Finding Action Tubes with a Sparse-to-Dense Framework
The task of spatial-temporal action detection has attracted increasing attention among researchers.
Ranked #3 on
Action Detection
on UCF Sports
(Video-mAP 0.2 metric)
CFAD: Coarse-to-Fine Action Detector for Spatiotemporal Action Localization
Most current pipelines for spatio-temporal action localization connect frame-wise or clip-wise detection results to generate action proposals, where only local information is exploited and the efficiency is hindered by dense per-frame localization.
Video Question Answering on Screencast Tutorials
This paper presents a new video question answering task on screencast tutorials.
Rademacher upper bounds for cross-validation errors with an application to the lasso
We establish a general upper bound for $K$-fold cross-validation ($K$-CV) errors that can be adapted to many $K$-CV-based estimators and learning algorithms.
Solar: $L_0$ solution path averaging for fast and accurate variable selection in high-dimensional data
We propose a new variable selection algorithm, subsample-ordered least-angle regression (solar), and its coordinate descent generalization, solar-cd.
Accuracy and stability of solar variable selection comparison under complicated dependence structures
In this paper we focus on the empirical variable-selection peformance of subsample-ordered least angle regression (Solar) -- a novel ultrahigh dimensional redesign of lasso -- on the empirical data with complicated dependence structures and, hence, severe multicollinearity and grouping effect issues.
Instrument variable detection with graph learning : an application to high dimensional GIS-census data for house pricing
In this paper, we merge two well-known tools from machine learning and biostatistics---variable selection algorithms and probablistic graphs---to estimate house prices and the corresponding causal structure using 2010 data on Sydney.
Incorporating Reinforced Adversarial Learning in Autoregressive Image Generation
To our best knowledge, the proposed method is first to enable adversarial learning in autoregressive models for image generation.
Multiple Sound Sources Localization from Coarse to Fine
How to visually localize multiple sound sources in unconstrained videos is a formidable problem, especially when lack of the pairwise sound-object annotations.
AOWS: Adaptive and optimal network width search with latency constraints
We introduce a novel efficient one-shot NAS approach to optimally search for channel numbers, given latency constraints on a specific hardware.
Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events
To this end, we present a new large-scale dataset with comprehensive annotations, named Human-in-Events or HiEve (Human-centric video analysis in complex Events), for the understanding of human motions, poses, and actions in a variety of realistic events, especially in crowd & complex events.
Minimizing FLOPs to Learn Efficient Sparse Representations
Deep representation learning has become one of the most widely adopted approaches for visual search, recommendation, and identification.
Channel Attention Is All You Need for Video Frame Interpolation
Prevailing video frame interpolation techniques rely heavily on optical flow estimation and require additional model complexity and computational cost; it is also susceptible to error propagation in challenging scenarios with large motion and heavy occlusion.
Getting to 99% Accuracy in Interactive Segmentation
We propose a novel interactive architecture and a novel training scheme that are both tailored to better exploit the user workflow.
MILA: Multi-Task Learning from Videos via Efficient Inter-Frame Attention
We embed the attention module in a ``slow-fast'' architecture, where the slower network runs on sparsely sampled keyframes and the light-weight shallow network runs on non-keyframes at a high frame rate.
Training a Constrained Natural Media Painting Agent using Reinforcement Learning
We present a novel approach to train a natural media painting using reinforcement learning.
An Internal Learning Approach to Video Inpainting
We propose a novel video inpainting algorithm that simultaneously hallucinates missing appearance and motion (optical flow) information, building upon the recent 'Deep Image Prior' (DIP) that exploits convolutional network architectures to enforce plausible texture in static images.
Large-scale Tag-based Font Retrieval with Generative Feature Learning
In this paper, we address the problem of large-scale tag-based font retrieval which aims to bring semantics to the font selection process and enable people without expert knowledge to use fonts effectively.
Adversarial Attacks in Sound Event Classification
In addition, we show that the adversarial attacks are very effective across the different models.
Video Instance Segmentation
The goal of this new task is simultaneous detection, segmentation and tracking of instances in videos.
Ranked #51 on
Video Instance Segmentation
on YouTube-VIS validation
Controllable Artistic Text Style Transfer via Shape-Matching GAN
In this paper, we present the first text style transfer network that allows for real-time control of the crucial stylistic degree of the glyph through an adjustable parameter.
Fast User-Guided Video Object Segmentation by Interaction-and-Propagation Networks
We propose a new multi-round training scheme for the interactive video object segmentation so that the networks can learn how to understand the user's intention and update incorrect estimations during the training.
Ranked #6 on
Interactive Video Object Segmentation
on DAVIS 2017
(AUC-J metric)
Streamlined Dense Video Captioning
Dense video captioning is an extremely challenging task since accurate and coherent description of events in a video requires holistic understanding of video contents as well as contextual reasoning of individual events.
M2KD: Multi-model and Multi-level Knowledge Distillation for Incremental Learning
Instead of sequentially distilling knowledge only from the last model, we directly leverage all previous model snapshots.
Video Object Segmentation using Space-Time Memory Networks
In our framework, the past frames with object masks form an external memory, and the current frame as the query is segmented using the mask information in the memory.
Ranked #4 on
Interactive Video Object Segmentation
on DAVIS 2017
(using extra training data)
End-to-End Time-Lapse Video Synthesis from a Single Outdoor Image
Time-lapse videos usually contain visually appealing content but are often difficult and costly to create.
Singing voice conversion with non-parallel data
F0 and aperiodic are obtained through the original singing voice, and used with acoustic features to reconstruct the target singing voice through a vocoder.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Slimmable Neural Networks
Instead of training individual networks with different width configurations, we train a shared network with switchable batch normalization.
Deep neural network based i-vector mapping for speaker verification using short utterances
Experimental results using the NIST SRE 2010 dataset show that both methods provide significant improvement and result in a max of 28. 43% relative improvement in Equal Error Rates from a baseline system, when using deep encoder with residual blocks and adding an additional phoneme vector.
YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark
End-to-end sequential learning to explore spatialtemporal features for video segmentation is largely limited by the scale of available video segmentation datasets, i. e., even the largest video segmentation dataset only contains 90 short video clips.
YouTube-VOS: Sequence-to-Sequence Video Object Segmentation
End-to-end sequential learning to explore spatial-temporal features for video segmentation is largely limited by the scale of available video segmentation datasets, i. e., even the largest video segmentation dataset only contains 90 short video clips.
Ranked #12 on
Video Object Segmentation
on YouTube-VOS 2018
(F-Measure (Unseen) metric)
Wide Activation for Efficient and Accurate Image Super-Resolution
Keras-based implementation of WDSR, EDSR and SRGAN for single image super-resolution
Ranked #4 on
Multi-Frame Super-Resolution
on PROBA-V
EIGEN: Ecologically-Inspired GENetic Approach for Neural Network Structure Searching from Scratch
In this paper, we propose an Ecologically-Inspired GENetic (EIGEN) approach that uses the concept of succession, extinction, mimicry, and gene duplication to search neural network structure from scratch with poorly initialized simple network and few constraints forced during the evolution, as we assume no prior knowledge about the task domain.
Factorized Adversarial Networks for Unsupervised Domain Adaptation
In this paper, we propose Factorized Adversarial Networks (FAN) to solve unsupervised domain adaptation problems for image classification tasks.
Learn to Combine Modalities in Multimodal Deep Learning
Combining complementary information from multiple modalities is intuitively appealing for improving the performance of learning-based approaches.
Learning $3$D-FilterMap for Deep Convolutional Neural Networks
Due to the weight sharing scheme, the parameter size of the $3$D-FilterMap is much smaller than that of the filters to be learned in the conventional convolution layer when $3$D-FilterMap generates the same number of filters.
WSNet: Learning Compact and Efficient Networks with Weight Sampling
We present a new approach and a novel architecture, termed WSNet, for learning compact and efficient deep neural networks.
WSNet: Compact and Efficient Networks Through Weight Sampling
We present a new approach and a novel architecture, termed WSNet, for learning compact and efficient deep neural networks.
Deep GrabCut for Object Selection
In this paper, we propose a novel segmentation approach that uses a rectangle as a soft constraint by transforming it into an Euclidean distance map.
Multi-Label Learning with Label Enhancement
To solve this problem, we assume that each multi-label instance is described by a vector of latent real-valued labels, which can reflect the importance of the corresponding labels.
$\left( β, \varpi \right)$-stability for cross-validation and the choice of the number of folds
The $\left( \beta, \varpi \right)$-stability mathematically connects the generalization ability and the stability of the cross-validated model via the Rademacher complexity.
Deep Image Matting
We evaluate our algorithm on the image matting benchmark, our testing set, and a wide variety of real images.
Generalization error minimization: a new approach to model evaluation and selection with an application to penalized regression
We propose using generalization error minimization (GEM) as a framework for model selection.
Finite-sample and asymptotic analysis of generalization ability with an application to penalized regression
We show that the error bounds may be used for tuning key estimation hyper-parameters, such as the number of folds $K$ in cross-validation.
Model selection consistency from the perspective of generalization ability and VC theory with an application to Lasso
In this paper, we study model selection from the perspective of generalization ability, under the framework of structural risk minimization (SRM) and Vapnik-Chervonenkis (VC) theory.
Deep Interactive Object Selection
Interactive object selection is a very important research problem and has many applications.
Ranked #11 on
Interactive Segmentation
on SBD
Intra-and-Inter-Constraint-based Video Enhancement based on Piecewise Tone Mapping
In this paper, we propose a new intra-and-inter-constraint-based video enhancement approach aiming to 1) achieve high intra-frame quality of the entire picture where multiple region-of-interests (ROIs) can be adaptively and simultaneously enhanced, and 2) guarantee the inter-frame quality consistencies among video frames.
