Search Results for author:
Found 167 papers, 52 papers with code
Semantic Aligned Multi-modal Transformer for Vision-LanguageUnderstanding: A Preliminary Study on Visual QA
Recent vision-language understanding approaches adopt a multi-modal transformer pre-training and finetuning paradigm.
Monocular 3D Object Detection via Feature Domain Adaptation
Monocular 3D object detection is a challenging task due to unreliable depth, resulting in a distinct performance gap between monocular and LiDAR-based approaches.
Asynchronous Convergence in Multi-Task Learning via Knowledge Distillation from Converged Tasks
However, one issue that often arises in MTL is the convergence speed between tasks varies due to differences in task difficulty, so it can be a challenge to simultaneously achieve the best performance on all tasks with a single model checkpoint.
PointDifformer: Robust Point Cloud Registration With Neural Diffusion and Transformer
Point cloud registration is a fundamental technique in 3-D computer vision with applications in graphics, autonomous driving, and robotics.
Learning to Rebalance Multi-Modal Optimization by Adaptively Masking Subnetworks
According to the findings, we further propose a novel importance sampling-based, element-wise joint optimization method, called Adaptively Mask Subnetworks Considering Modal Significance(AMSS).
OOSTraj: Out-of-Sight Trajectory Prediction With Vision-Positioning Denoising
By enhancing trajectory prediction accuracy and addressing the challenges of out-of-sight objects, our work significantly contributes to improving the safety and reliability of autonomous driving in complex environments.
Machine Unlearning for Traditional Models and Large Language Models: A Short Survey
With the implementation of personal data privacy regulations, the field of machine learning (ML) faces the challenge of the "right to be forgotten".
Adapting to Length Shift: FlexiLength Network for Trajectory Prediction
Trajectory prediction plays an important role in various applications, including autonomous driving, robotics, and scene understanding.
ParCo: Part-Coordinating Text-to-Motion Synthesis
However, these methods encounter challenges such as the lack of coordination between different part motions and difficulties for networks to understand part concepts.
Ranked #8 on
Motion Synthesis
on HumanML3D
Solution for Point Tracking Task of ICCV 1st Perception Test Challenge 2023
To address this issue, we propose a simple yet effective approach called TAP with confident static points (TAPIR+), which focuses on rectifying the tracking of the static point in the videos shot by a static camera.
The Solution for the CVPR 2023 1st foundation model challenge-Track2
For the vehicle retrieval task, we use BLIP as the base model.
IBCB: Efficient Inverse Batched Contextual Bandit for Behavioral Evolution History
This poses a new challenge for existing imitation learning approaches that can only utilize data from experienced experts.
Is Reference Necessary in the Evaluation of NLG Systems? When and Where?
The majority of automatic metrics for evaluating NLG systems are reference-based.
Skeleton-Based Human Action Recognition with Noisy Labels
In this study, we bridge this gap by implementing a framework that augments well-established skeleton-based human action recognition methods with label-denoising strategies from various research areas to serve as the initial benchmark.
AceMap: Knowledge Discovery through Academic Graph
The exponential growth of scientific literature requires effective management and extraction of valuable insights.
Spectrum AUC Difference (SAUCD): Human-aligned 3D Shape Evaluation
Then, we calculate the Area Under the Curve (AUC) difference between the two spectrums, so that each frequency band that captures either the overall or detailed shape is equitably considered.
NARUTO: Neural Active Reconstruction from Uncertain Target Observations
We present NARUTO, a neural active reconstruction system that combines a hybrid neural representation with uncertainty learning, enabling high-fidelity surface reconstruction.
Robust Multi-Task Learning with Excess Risks
To overcome this limitation, we propose Multi-Task Learning with Excess Risks (ExcessMTL), an excess risk-based task balancing method that updates the task weights by their distances to convergence instead.
Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective
Pre-training is known to generate universal representations for downstream tasks in large-scale deep learning such as large language models.
GeoGalactica: A Scientific Large Language Model in Geoscience
To our best knowledge, it is the largest language model for the geoscience domain.
PlanarNeRF: Online Learning of Planar Primitives with Neural Radiance Fields
Through extensive experiments, we demonstrate the effectiveness of PlanarNeRF in various scenarios and remarkable improvement over existing works.
Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis
Novel view synthesis of dynamic scenes has been an intriguing yet challenging problem.
Learn to Optimize Denoising Scores for 3D Generation: A Unified and Improved Diffusion Prior on NeRF and 3D Gaussian Splatting
We propose a unified framework aimed at enhancing the diffusion priors for 3D generation tasks.
Background Clustering Pre-training for Few-shot Segmentation
In this paper, we propose a new pre-training scheme for FSS via decoupling the novel classes from background, called Background Clustering Pre-Training (BCPT).
Supported Trust Region Optimization for Offline Reinforcement Learning
Offline reinforcement learning suffers from the out-of-distribution issue and extrapolation error.
Relit-NeuLF: Efficient Relighting and Novel View Synthesis via Neural 4D Light Field
A DecomposeNet learns to map each ray to its SVBRDF components: albedo, normal, and roughness.
Layout Sequence Prediction From Noisy Mobile Modality
In summary, our approach offers a promising solution to the challenges faced by layout sequence and trajectory prediction models in real-world settings, paving the way for utilizing sensor data from mobile phones to accurately predict pedestrian bounding box trajectories.
ForeSeer: Product Aspect Forecasting Using Temporal Graph Embedding
ForeSeer transfers reviews from similar products on a large product graph and exploits these reviews to predict aspects that might emerge in future reviews.
Latent Graph Inference with Limited Supervision
We begin by defining the pivotal nodes as $k$-hop starved nodes, which can be identified based on a given adjacency matrix.
NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functions
The spatial positions of their neural features are fixed on grid nodes and cannot well adapt to target signals.
Multi-turn Dialogue Comprehension from a Topic-aware Perspective
On the other hand, the split segments are an appropriate element of multi-turn dialogue response selection.
OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects
We introduce OpenIllumination, a real-world dataset containing over 108K images of 64 objects with diverse materials, captured under 72 camera views and a large number of different illuminations.
Context-Aware Prompt Tuning for Vision-Language Model with Dual-Alignment
To achieve this, we introduce a pre-trained LLM to generate context descriptions, and we encourage the prompts to learn from the LLM's knowledge by alignment, as well as the alignment between prompts and local image features.
Exploring the Limits of Historical Information for Temporal Knowledge Graph Extrapolation
To this end, we investigate the limits of historical information for temporal knowledge graph extrapolation and propose a new event forecasting model called Contrastive Event Network (CENET) based on a novel training framework of historical contrastive learning.
Breast Lesion Diagnosis Using Static Images and Dynamic Video
In this work, we propose a multi-modality breast tumor diagnosis model to imitate the diagnosing process of radiologists, which learns the features of both static images and dynamic video and explores the potential relationship between the two modalities.
WeaverBird: Empowering Financial Decision-Making with Large Language Model, Knowledge Base, and Search Engine
We present WeaverBird, an intelligent dialogue system designed specifically for the finance domain.
Relational Contrastive Learning for Scene Text Recognition
We argue that such prior contextual information can be interpreted as the relations of textual primitives due to the heterogeneous text and background, which can provide effective self-supervised labels for representation learning.
HiREN: Towards Higher Supervision Quality for Better Scene Text Image Super-Resolution
Observing the quality issue of HR images, in this paper we propose a novel idea to boost STISR by first enhancing the quality of HR images and then using the enhanced HR images as supervision to do STISR.
SLPD: Slide-level Prototypical Distillation for WSIs
Specifically, we iteratively perform intra-slide clustering for the regions (4096x4096 patches) within each WSI to yield the prototypes and encourage the region representations to be closer to the assigned prototypes.
Uncertainty-aware State Space Transformer for Egocentric 3D Hand Trajectory Forecasting
In this paper, we set up an egocentric 3D hand trajectory forecasting task that aims to predict hand trajectories in a 3D space from early observed RGB videos in a first-person view.
High Fidelity 3D Hand Shape Reconstruction via Scalable Graph Frequency Decomposition
To capture high-frequency personalized details, we transform the 3D mesh into the frequency domain, and propose a novel frequency decomposition loss to supervise each frequency component.
K2: A Foundation Language Model for Geoscience Knowledge Understanding and Utilization
Large language models (LLMs) have achieved great success in general domains of natural language processing.
MyStyle++: A Controllable Personalized Generative Prior
In this paper, we propose an approach to obtain a personalized generative prior with explicit control over a set of attributes.
Graph-Aware Language Model Pre-Training on a Large Graph Corpus Can Help Multiple Graph Applications
Model pre-training on large text corpora has been demonstrated effective for various downstream applications in the NLP domain.
Exploring and Verbalizing Academic Ideas by Concept Co-occurrence
The results demonstrate that our system has broad prospects and can assist researchers in expediting the process of discovering new ideas.
Dynamic Voxel Grid Optimization for High-Fidelity RGB-D Supervised Surface Reconstruction
Direct optimization of interpolated features on multi-resolution voxel grids has emerged as a more efficient alternative to MLP-like modules.
Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction
As far as we know, this is the first work to address the lack of benchmarks and techniques for trajectory imputation and prediction in a unified manner.
TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization
To better exploit the potential of pre-trained models in adversarial robustness, this paper focuses on the fine-tuning of an adversarially pre-trained model in various classification tasks.
Harnessing Low-Frequency Neural Fields for Few-Shot View Synthesis
We further propose a simple-yet-effective strategy for tuning the frequency to avoid overfitting few-shot inputs: enforcing consistency among the frequency domain of rendered 2D images.
EgoViT: Pyramid Video Transformer for Egocentric Action Recognition
Different from previous video transformers, which use the same static embedding as the class token for diverse inputs, we propose a dynamic class token generator that produces a class token for each input video by analyzing the hand-object interaction and the related motion information.
Interventional Bag Multi-Instance Learning On Whole-Slide Pathological Images
This deficiency is a confounder that limits the performance of existing MIL methods.
Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning
Hence we advocate that the key of better performance lies in meaningful latent modality structures instead of perfect modality alignment.
Few-Shot Image Classification
Open-Ended Question Answering
+6
Making Reconstruction-based Method Great Again for Video Anomaly Detection
With the same perturbation magnitude, the testing reconstruction error of the normal frames lowers more than that of the abnormal frames, which contributes to mitigating the overfitting problem of reconstruction.
AdamsFormer for Spatial Action Localization in the Future
SALF is challenging because it requires understanding the underlying physics of video observations to predict future action locations accurately.
3D-Aware Facial Landmark Detection via Multi-View Consistent Training on Synthetic Data
Accurate facial landmark detection on wild images plays an essential role in human-computer interaction, entertainment, and medical applications.
EurNet: Efficient Multi-Range Relational Modeling of Spatial Multi-Relational Data
We study EurNets in two important domains for image and protein structure modeling.
ActiveRMAP: Radiance Field for Active Mapping And Planning
We, for the first time, present an RGB-only active vision framework using radiance field representation for active 3D reconstruction and planning in an online manner.
Temporal Knowledge Graph Reasoning with Historical Contrastive Learning
Simultaneously, it trains representations of queries to investigate whether the current moment depends more on historical or non-historical events by launching contrastive learning.
Look More but Care Less in Video Recognition
To tackle this problem, we propose Ample and Focal Network (AFNet), which is composed of two branches to utilize more frames but with less computation.
NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fields
Visually exploring in a real-world 4D spatiotemporal space freely in VR has been a long-term quest.
CLIP-FLow: Contrastive Learning by semi-supervised Iterative Pseudo labeling for Optical Flow Estimation
To this end, we propose CLIP-FLow, a semi-supervised iterative pseudo-labeling framework to transfer the pretraining knowledge to the target real domain.
Fairness via Adversarial Attribute Neighbourhood Robust Learning
Improving fairness between privileged and less-privileged sensitive attribute groups (e. g, {race, gender}) has attracted lots of attention.
OmniNeRF: Hybriding Omnidirectional Distance and Radiance fields for Neural Surface Reconstruction
3D reconstruction from images has wide applications in Virtual Reality and Automatic Driving, where the precision requirement is very high.
INFINITY: A Simple Yet Effective Unsupervised Framework for Graph-Text Mutual Conversion
As a fully unsupervised framework, INFINITY is empirically verified to outperform state-of-the-art baselines for G2T and T2G tasks.
MonoIndoor++:Towards Better Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments
As compared to outdoor environments, estimating depth of monocular videos for indoor environments, using self-supervised methods, results in two additional challenges: (i) the depth range of indoor video sequences varies a lot across different frames, making it difficult for the depth network to induce consistent depth cues for training; (ii) the indoor sequences recorded with handheld devices often contain much more rotational motions, which cause difficulties for the pose network to predict accurate relative camera poses.
SepLUT: Separable Image-adaptive Lookup Tables for Real-time Image Enhancement
Image-adaptive lookup tables (LUTs) have achieved great success in real-time image enhancement tasks due to their high efficiency for modeling color transforms.
Ranked #5 on
Image Enhancement
on MIT-Adobe 5k
(PSNR on proRGB metric)
Efficient and effective training of language and graph neural network models
The effectiveness in our framework is achieved by applying stage-wise fine-tuning of the BERT model first with heterogenous graph information and then with a GNN model.
Semantics-Depth-Symbiosis: Deeply Coupled Semi-Supervised Learning of Semantics and Depth
Multi-task learning (MTL) paradigm focuses on jointly learning two or more tasks, aiming for significant improvement w. r. t model's generalizability, performance, and training/inference memory footprint.
DynaMaR: Dynamic Prompt with Mask Token Representation
In this paper, we propose an improvement to prompt-based fine-tuning that addresses these two issues.
RIAV-MVS: Recurrent-Indexing an Asymmetric Volume for Multi-View Stereo
At the pixel level, we propose to break the symmetry of the Siamese network (which is typically used in MVS to extract image features) by introducing a transformer block to the reference image (but not to the source images).
HIRL: A General Framework for Hierarchical Image Representation Learning
This framework aims to learn multiple semantic representations for each image, and these representations are structured to encode image semantics from fine-grained to coarse-grained.
An Empirical Study on Distribution Shift Robustness From the Perspective of Pre-Training and Data Augmentation
With our empirical result obtained from 1, 330 models, we provide the following main observations: 1) ERM combined with data augmentation can achieve state-of-the-art performance if we choose a proper pre-trained model respecting the data property; 2) specialized algorithms further improve the robustness on top of ERM when handling a specific type of distribution shift, e. g., GroupDRO for spurious correlation and CORAL for large-scale out-of-distribution data; 3) Comparing different pre-training modes, architectures and data sizes, we provide novel observations about pre-training on distribution shift, which sheds light on designing or selecting pre-training strategy for different kinds of distribution shifts.
FisheyeDistill: Self-Supervised Monocular Depth Estimation with Ordinal Distillation for Fisheye Cameras
In this paper, we deal with the problem of monocular depth estimation for fisheye cameras in a self-supervised manner.
CNN-Augmented Visual-Inertial SLAM with Planar Constraints
The CNN depth effectively bootstraps the back-end optimization of SLAM and meanwhile the CNN uncertainty adaptively weighs the contribution of each feature point to the back-end optimization.
GeoRefine: Self-Supervised Online Depth Refinement for Accurate Dense Mapping
We present a robust and accurate depth refinement system, named GeoRefine, for geometrically-consistent dense mapping from monocular sequences.
AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-time Image Enhancement
They adopt a sub-optimal uniform sampling point allocation, limiting the expressiveness of the learned LUTs since the (tri-)linear interpolation between uniform sampling points in the LUT transform might fail to model local non-linearities of the color transform.
Ranked #2 on
Photo Retouching
on MIT-Adobe 5k
EPiDA: An Easy Plug-in Data Augmentation Framework for High Performance Text Classification
However, to the best of our knowledge, most existing methods consider only either the diversity or the quality of augmented data, thus cannot fully mine the potential of DA for NLP.
Interventional Multi-Instance Learning with Deconfounded Instance-Level Prediction
When applying multi-instance learning (MIL) to make predictions for bags of instances, the prediction accuracy of an instance often depends on not only the instance itself but also its context in the corresponding bag.
Solving The Long-Tailed Problem via Intra- and Inter-Category Balance
Benchmark datasets for visual recognition assume that data is uniformly distributed, while real-world datasets obey long-tailed distribution.
Exploration strategies for articulatory synthesis of complex syllable onsets
High-quality articulatory speech synthesis has many potential applications in speech science and technology.
Enhancing Non-mass Breast Ultrasound Cancer Classification With Knowledge Transfer
Based on the insight that mass data is sufficient and shares the same knowledge structure with non-mass data of identifying the malignancy of a lesion based on the ultrasound image, we propose a novel transfer learning framework to enhance the generalizability of the DNN model for non-mass BUS with the help of mass BUS.
Self Supervised Lesion Recognition For Breast Ultrasound Diagnosis
Since an ultrasound image only describes a partial 2D projection of a 3D lesion, such paradigm ignores the semantic relationship between different views of a lesion, which is inconsistent with the traditional diagnosis where sonographers analyze a lesion from at least two views.
Learning from Untrimmed Videos: Self-Supervised Video Representation Learning with Hierarchical Consistency
In this work, we aim to learn representations by leveraging more abundant information in untrimmed videos.
CHEX: CHannel EXploration for CNN Model Compression
However, conventional pruning methods have limitations in that: they are restricted to pruning process only, and they require a fully pre-trained large model.
Efficient Few-Shot Object Detection via Knowledge Inheritance
Upon this baseline, we devise an initializer named knowledge inheritance (KI) to reliably initialize the novel weights for the box classifier, which effectively facilitates the knowledge transfer process and boosts the adaptation speed.
PlaneMVS: 3D Plane Reconstruction from Multi-View Stereo
The semantic plane detection branch is based on a single-view plane detection framework but with differences.
Deformable VisTR: Spatio temporal deformable attention for video instance segmentation
To improve the training efficiency, we propose Deformable VisTR, leveraging spatio-temporal deformable attention module that only attends to a small fixed set of key spatio-temporal sampling points around a reference point.
Adaptive Trajectory Prediction via Transferable GNN
To the best of our knowledge, our work is the pioneer which fills the gap in benchmarks and techniques for practical pedestrian trajectory prediction across different domains.
Multi-modal Alignment using Representation Codebook
Aligning signals from different modalities is an important step in vision-language representation learning as it affects the performance of later stages such as cross-modality fusion.
Vision-Language Pre-Training with Triple Contrastive Learning
Besides CMA, TCL introduces an intra-modal contrastive objective to provide complementary benefits in representation learning.
Ranked #3 on
Zero-Shot Cross-Modal Retrieval
on COCO 2014
HCSC: Hierarchical Contrastive Selective Coding
In this framework, a set of hierarchical prototypes are constructed and also dynamically updated to represent the hierarchical semantic structures underlying the data in the latent space.
A Novel Convergence Analysis for Algorithms of the Adam Family
Although rigorous convergence analysis exists for Adam, they impose specific requirements on the update of the adaptive step size, which are not generic enough to cover many other variants of Adam.
Boosting Unsupervised Domain Adaptation with Soft Pseudo-label and Curriculum Learning
To avoid overfitting on source domain, at the second stage, we propose a curriculum learning strategy to adaptively control the weighting between losses from the two domains so that the focus of the training stage is gradually shifted from source distribution to target distribution with prediction confidence boosted on the target domain.
SLA$^2$P: Self-supervised Anomaly Detection with Adversarial Perturbation
Next we add adversarial perturbation to the transformed features to decrease their softmax scores of the predicted labels and design anomaly scores based on the predictive uncertainties of the classifier on these perturbed features.
Improved Fine-Tuning by Better Leveraging Pre-Training Data
The generalization result of using pre-training data shows that the excess risk bound on a target task can be improved when the appropriate pre-training data is included in fine-tuning.
Self-Supervised Pre-Training for Transformer-Based Person Re-Identification
We first investigate self-supervised learning (SSL) methods with Vision Transformer (ViT) pretrained on unlabelled person images (the LUPerson dataset), and empirically find it significantly surpasses ImageNet supervised pre-training models on ReID tasks.
Ranked #1 on
Unsupervised Person Re-Identification
on Market-1501
(using extra training data)
Magic Pyramid: Accelerating Inference with Early Exiting and Token Pruning
To achieve this, we propose a novel idea, Magic Pyramid (MP), to reduce both width-wise and depth-wise computation via token pruning and early exiting for Transformer-based models, particularly BERT.
DP-SSL: Towards Robust Semi-supervised Learning with A Few Labeled Samples
Extensive experiments on four standard SSL benchmarks show that DP-SSL can provide reliable labels for unlabeled data and achieve better classification performance on test sets than existing SSL methods, especially when only a small number of labeled samples are available.
Weakly-supervised Text Classification Based on Keyword Graph
Among them, keyword-driven methods are the mainstream where user-provided keywords are exploited to generate pseudo-labels for unlabeled texts.
MemREIN: Rein the Domain Shift for Cross-Domain Few-Shot Learning
In this paper, we propose a novel framework, MemREIN, which considers Memorized, Restitution, and Instance Normalization for cross-domain few-shot learning.
Causal Triple Attention Time Series Forecasting
Time series forecasting has historically been a key area of academic research and industrial applications.
Distribution-sensitive Information Retention for Accurate Binary Neural Network
We present a novel Distribution-sensitive Information Retention Network (DIR-Net) that retains the information in the forward and backward propagation by improving internal propagation and introducing external representations.
MLIM: Vision-and-Language Model Pre-training with Masked Language and Image Modeling
Vision-and-Language Pre-training (VLP) improves model performance for downstream tasks that require image and text inputs.
Dash: Semi-Supervised Learning with Dynamic Thresholding
In this work we develop a simple yet powerful framework, whose key idea is to select a subset of training examples from the unlabeled data when performing existing SSL methods so that only the unlabeled examples with pseudo labels related to the labeled data will be used to train models.
Recursive Fusion and Deformable Spatiotemporal Attention for Video Compression Artifact Reduction
A number of deep learning based algorithms have been proposed to recover high-quality videos from low-quality compressed ones.
MonoIndoor: Towards Good Practice of Self-Supervised Monocular Depth Estimation for Indoor Environments
The effectiveness of each module is shown through a carefully conducted ablation study and the demonstration of the state-of-the-art performance on three indoor datasets, \ie, EuRoC, NYUv2, and 7-scenes.
Simpler, Faster, Stronger: Breaking The log-K Curse On Contrastive Learners With FlatNCE
InfoNCE-based contrastive representation learners, such as SimCLR, have been tremendously successful in recent years.
Rethinking Adam: A Twofold Exponential Moving Average Approach
The intuition is that gradient with momentum contains more accurate directional information and therefore its second moment estimation is a more favorable option for learning rate scaling than that of the raw gradient.
Effective Model Sparsification by Scheduled Grow-and-Prune Methods
It addresses the shortcomings of the previous works by repeatedly growing a subset of layers to dense and then pruning them back to sparse after some training.
Dialogue-oriented Pre-training
Pre-trained language models (PrLM) has been shown powerful in enhancing a broad range of downstream tasks including various dialogue related ones.
Boosting the Performance of Video Compression Artifact Reduction with Reference Frame Proposals and Frequency Domain Information
Many deep learning based video compression artifact removal algorithms have been proposed to recover high-quality videos from low-quality compressed videos.
Dynamic Dual Sampling Module for Fine-Grained Semantic Segmentation
Representation of semantic context and local details is the essential issue for building modern semantic segmentation models.
NeuLF: Efficient Novel View Synthesis with Neural 4D Light Field
In this paper, we present an efficient and robust deep learning solution for novel view synthesis of complex scenes.
Why Does Multi-Epoch Training Help?
Stochastic gradient descent (SGD) has become the most attractive optimization method in training large-scale deep neural networks due to its simplicity, low computational cost in each updating step, and good performance.
A Novel Convergence Analysis for Algorithms of the Adam Family and Beyond
Our analysis exhibits that an increasing or large enough "momentum" parameter for the first-order moment used in practice is sufficient to ensure Adam and its many variants converge under a mild boundness condition on the adaptive scaling factor of the step size.
NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results
This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with a focus on the proposed methods and results.
A Theoretical Analysis of Learning with Noisily Labeled Data
Noisy labels are very common in deep supervised learning.
Federated Deep AUC Maximization for Heterogeneous Data with a Constant Communication Complexity
Deep AUC (area under the ROC curve) Maximization (DAM) has attracted much attention recently due to its great potential for imbalanced data classification.
A Convergence Theory Towards Practical Over-parameterized Deep Neural Networks
We show that convergence to a global minimum is guaranteed for networks with widths quadratic in the sample size and linear in their depth at a time logarithmic in both.
Attentional-Biased Stochastic Gradient Descent
In this paper, we present a simple yet effective provable method (named ABSGD) for addressing the data imbalance or label noise problem in deep learning.
PoP-Net: Pose over Parts Network for Multi-Person 3D Pose Estimation from a Depth Image
In this paper, a real-time method called PoP-Net is proposed to predict multi-person 3D poses from a depth image.
WeMix: How to Better Utilize Data Augmentation
To this end, we develop two novel algorithms, termed "AugDrop" and "MixLoss", to correct the data bias in the data augmentation.
Topic-Aware Multi-turn Dialogue Modeling
In the retrieval-based multi-turn dialogue modeling, it remains a challenge to select the most appropriate response according to extracting salient features in context utterances.
Object Detection in the Context of Mobile Augmented Reality
Ordinary object detection approaches process information from the images only, and they are oblivious to the camera pose with regard to the environment and the scale of the environment.
Talking-head Generation with Rhythmic Head Motion
When people deliver a speech, they naturally move heads, and this rhythmic head motion conveys prosodic information.
Learning Tumor Growth via Follow-Up Volume Prediction for Lung Nodules
It is achieved by predicting future displacement field of each voxel with a WarpNet.
Towards Understanding Label Smoothing
Label smoothing regularization (LSR) has a great success in training deep neural networks by stochastic algorithms such as stochastic gradient descent and its variants.
An Online Method for A Class of Distributionally Robust Optimization with Non-Convex Objectives
In this paper, we propose a practical online method for solving a class of distributionally robust optimization (DRO) with non-convex objectives, which has important applications in machine learning for improving the robustness of neural networks.
Evaluating Features and Metrics for High-Quality Simulation of Early Vocal Learning of Vowels
One of the crucial parameters in these simulations is the choice of features and a metric to evaluate the acoustic error between the synthesised sound and the reference target.
Relational Learning between Multiple Pulmonary Nodules via Deep Set Attention Transformers
In this study, we propose a multiple instance learning (MIL) approach and empirically prove the benefit to learn the relations between multiple nodules.
Decoupled Gradient Harmonized Detector for Partial Annotation: Application to Signet Ring Cell Detection
Early diagnosis of signet ring cell carcinoma dramatically improves the survival rate of patients.
Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment
Specifically, the fractional dilated kernel is adaptively constructed according to the image aspect ratios, where the interpolation of nearest two integers dilated kernels is used to cope with the misalignment of fractional sampling.
Optimal Epoch Stochastic Gradient Descent Ascent Methods for Min-Max Optimization
In this paper, we bridge this gap by providing a sharp analysis of epoch-wise stochastic gradient descent ascent method (referred to as Epoch-GDA) for solving strongly convex strongly concave (SCSC) min-max problems, without imposing any additional assumption about smoothness or the function's structure.
2.75D: Boosting learning by representing 3D Medical imaging to 2D features for small data
Such performance gain is more pronounced with transfer learning or in the case of limited training data.
Occlum: Secure and Efficient Multitasking Inside a Single Enclave of Intel SGX
SFI is a software instrumentation technique for sandboxing untrusted modules (called domains).
Operating Systems Hardware Architecture Cryptography and Security
Quaternion Product Units for Deep Learning on 3D Rotation Groups
We propose a novel quaternion product unit (QPU) to represent data on 3D rotation groups.
Non-Local ConvLSTM for Video Compression Artifact Reduction
Video compression artifact reduction aims to recover high-quality videos from low-quality compressed videos.
Probabilistic Radiomics: Ambiguous Diagnosis with Controllable Shape Analysis
The final diagnosis is obtained by combining the ambiguity prior sample and lesion representation, and the whole network named $DenseSharp^{+}$ is end-to-end trainable.
On Leveraging the Visual Modality for Neural Machine Translation
Leveraging the visual modality effectively for Neural Machine Translation (NMT) remains an open problem in computational linguistics.
Evaluating and Boosting Uncertainty Quantification in Classification
Emergence of artificial intelligence techniques in biomedical applications urges the researchers to pay more attention on the uncertainty quantification (UQ) in machine-assisted medical decision making.
Stochastic Optimization for Non-convex Inf-Projection Problems
In this paper, we study a family of non-convex and possibly non-smooth inf-projection minimization problems, where the target objective function is equal to minimization of a joint function over another variable.
3D Virtual Garment Modeling from RGB Images
The predicted landmarks are used for estimating sizing information of the garment.
Pose Guided Fashion Image Synthesis Using Deep Generative Model
In order to formulate the framework, we employ one generator and two discriminators for image synthesis.
Optimizing Interim Analysis Timing for Bayesian Adaptive Commensurate Designs
In developing products for rare diseases, statistical challenges arise due to the limited number of patients available for participation in drug trials and other clinical research.
Applications Computation Methodology
Stochastic Primal-Dual Algorithms with Faster Convergence than $O(1/\sqrt{T})$ for Problems without Bilinear Structure
The main contribution of this paper is the design and analysis of new stochastic primal-dual algorithms that use a mixture of stochastic gradient updates and a logarithmic number of deterministic dual updates for solving a family of convex-concave problems with no bilinear structure assumed.
Quaternion Convolutional Neural Networks
Neural networks in the real domain have been studied for a long time and achieved promising results in many vision tasks for recent years.
Disentangled Deep Autoencoding Regularization for Robust Image Classification
In spite of achieving revolutionary successes in machine learning, deep convolutional neural networks have been recently found to be vulnerable to adversarial attacks and difficult to generalize to novel test images with reasonably large geometric transformations.
Analogy Search Engine: Finding Analogies in Cross-Domain Research Papers
ASE combines recent theories and methods from Computational Analogy and Natural Language Processing to go beyond keyword-based lexical search and discover the deeper analogical relationships among research paper abstracts.
Stochastic Optimization for DC Functions and Non-smooth Non-convex Regularizers with Non-asymptotic Convergence
In this paper, we propose new stochastic optimization algorithms and study their first-order convergence theories for solving a broad family of DC functions.
Geometric Constrained Joint Lane Segmentation and Lane Boundary Detection
The main contributions of the proposed frame- work are highlighted in two facets: (1) We put forward a multiple-task learning framework with mutually interlinked sub-structures between lane segmentation and lane boundary detection to improve overall performance.
SADAGRAD: Strongly Adaptive Stochastic Gradient Methods
Although the convergence rates of existing variants of ADAGRAD have a better dependence on the number of iterations under the strong convexity condition, their iteration complexities have a explicitly linear dependence on the dimensionality of the problem.
A Variational Prosody Model for the decomposition and synthesis of speech prosody
Our work bridges between a comprehensive generative model of intonation and state-of-the-art AI techniques.
Crowd Counting via Adversarial Cross-Scale Consistency Pursuit
Crowd counting or density estimation is a challenging task in computer vision due to large scale variations, perspective distortions and serious occlusions, etc.
Ranked #4 on
Crowd Counting
on WorldExpo’10
Learning with Non-Convex Truncated Losses by SGD
Learning with a {\it convex loss} function has been a dominating paradigm for many years.
NEON+: Accelerated Gradient Methods for Extracting Negative Curvature for Non-Convex Optimization
Accelerated gradient (AG) methods are breakthroughs in convex optimization, improving the convergence rate of the gradient descent method for optimization with smooth functions.
ADMM without a Fixed Penalty Parameter: Faster Convergence with New Adaptive Penalization
The novelty of the proposed scheme lies at that it is adaptive to a local sharpness property of the objective function, which marks the key difference from previous adaptive scheme that adjusts the penalty parameter per-iteration based on certain conditions on iterates.
Adaptive SVRG Methods under Error Bound Conditions with Unknown Growth Parameter
The most studied error bound is the quadratic error bound, which generalizes strong convexity and is satisfied by a large family of machine learning problems.
First-order Stochastic Algorithms for Escaping From Saddle Points in Almost Linear Time
Two classes of methods have been proposed for escaping from saddle points with one using the second-order information carried by the Hessian and the other adding the noise into the first-order information.
Flexible Network Binarization with Layer-wise Priority
In this work, we reveal an important fact that binarizing different layers has a widely-varied effect on the compression ratio of network and the loss of performance.
Stochastic Convex Optimization: Faster Local Growth Implies Faster Global Convergence
In this paper, a new theory is developed for first-order stochastic convex optimization, showing that the global convergence rate is sufficiently quantified by a local growth rate of the objective function in a neighborhood of the optimal solutions.
Video Segmentation via Multiple Granularity Analysis
We introduce a Multiple Granularity Analysis framework for video segmentation in a coarse-to-fine manner.
Efficient Non-oblivious Randomized Reduction for Risk Minimization with Improved Excess Risk Guarantee
Previously, oblivious random projection based approaches that project high dimensional features onto a random subspace have been used in practice for tackling high-dimensionality challenge in machine learning.
Homotopy Smoothing for Non-Smooth Problems with Lower Complexity than O(1/\epsilon)
To the best of our knowledge, this is the lowest iteration complexity achieved so far for the considered non-smooth optimization problems without strong convexity assumption.
Homotopy Smoothing for Non-Smooth Problems with Lower Complexity than $O(1/ε)$
In this work, we will show that the proposed HOPS achieved a lower iteration complexity of $\widetilde O(1/\epsilon^{1-\theta})$\footnote{$\widetilde O()$ suppresses a logarithmic factor.}
Accelerate Stochastic Subgradient Method by Leveraging Local Growth Condition
In particular, if the objective function $F(\mathbf w)$ in the $\epsilon$-sublevel set grows as fast as $\|\mathbf w - \mathbf w_*\|_2^{1/\theta}$, where $\mathbf w_*$ represents the closest optimal solution to $\mathbf w$ and $\theta\in(0, 1]$ quantifies the local growth rate, the iteration complexity of first-order stochastic optimization for achieving an $\epsilon$-optimal solution can be $\widetilde O(1/\epsilon^{2(1-\theta)})$, which is optimal at most up to a logarithmic factor.
Feature Selection Based on Confidence Machine
We propose a filter method for unsupervised feature selection which is based on the Confidence Machine.
