Search Results for author:
Found 79 papers, 47 papers with code
Revisiting Pivot-Based Paraphrase Generation: Language Is Not the Only Optional Pivot
Concretely, we transform a sentence into a variety of different semantic or syntactic representations (including AMR, UD, and latent semantic representation), and then decode the sentence back from the semantic representations.
On the Robustness of Segment Anything
Second, we extend representative adversarial attacks against SAM and study the influence of different prompts on robustness.
A robust design of time-varying internal model principle-based control for ultra-precision tracking in a direct-drive servo stage
By means of the ESO feedback, the plant model is kept as nominal, and hence the structural robustness is achieved for the time-varying internal model.
SegGPT: Segmenting Everything In Context
We unify various segmentation tasks into a generalist in-context learning framework that accommodates different kinds of segmentation data by transforming them into the same format of images.
Ranked #1 on
Few-Shot Semantic Segmentation
on PASCAL-5i (5-Shot)
Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models
Our vid2vid-zero leverages off-the-shelf image diffusion models, and doesn't require training on any video.
EVA-CLIP: Improved Training Techniques for CLIP at Scale
Our approach incorporates new techniques for representation learning, optimization, and augmentation, enabling EVA-CLIP to achieve superior performance compared to previous CLIP models with the same number of parameters but significantly smaller training costs.
Ranked #4 on
Image Classification
on ObjectNet
(using extra training data)
EVA-02: A Visual Representation for Neon Genesis
We launch EVA-02, a next-generation Transformer-based visual representation pre-trained to reconstruct strong and robust language-aligned vision features via masked image modeling.
One Transformer Fits All Distributions in Multi-Modal Diffusion at Scale
Inspired by the unified view, UniDiffuser learns all distributions simultaneously with a minimal modification to the original diffusion model -- perturbs data in all modalities instead of a single modality, inputs individual timesteps in different modalities, and predicts the noise of all modalities instead of a single modality.
Robot Behavior-Tree-Based Task Generation with Large Language Models
To cope with this issue, we propose a novel behavior-tree-based task generation approach that utilizes state-of-the-art large language models.
Revisiting Discriminative vs. Generative Classifiers: Theory and Implications
Theoretically, the paper considers the surrogate loss instead of the zero-one loss in analyses and generalizes the classical results from binary cases to multiclass ones.
iCLIP: Bridging Image Classification and Contrastive Language-Image Pre-Training for Visual Recognition
This paper presents a method that effectively combines two prevalent visual recognition methods, i. e., image classification and contrastive language-image pre-training, dubbed iCLIP.
Physics-Guided ISO-Dependent Sensor Noise Modeling for Extreme Low-Light Photography
Although deep neural networks have achieved astonishing performance in many vision tasks, existing learning-based methods are far inferior to the physical model-based solutions in extreme low-light sensor noise modeling.
Deep Incubation: Training Large Models by Divide-and-Conquering
In this paper, we present Deep Incubation, a novel approach that enables the efficient and effective training of large models by dividing them into smaller sub-modules that can be trained separately and assembled seamlessly.
Images Speak in Images: A Generalist Painter for In-Context Visual Learning
In this work, we present Painter, a generalist model which addresses these obstacles with an "image"-centric solution, that is, to redefine the output of core vision tasks as images, and specify task prompts as also images.
Ranked #6 on
Personalized Segmentation
on PerSeg
EVA: Exploring the Limits of Masked Visual Representation Learning at Scale
We launch EVA, a vision-centric foundation model to explore the limits of visual representation at scale using only publicly accessible data.
Could Giant Pretrained Image Models Extract Universal Representations?
In this paper, we present a study of frozen pretrained models when applied to diverse and representative computer vision tasks, including object detection, semantic segmentation and video action recognition.
Ranked #3 on
Action Recognition In Videos
on Kinetics-400
All are Worth Words: A ViT Backbone for Diffusion Models
We evaluate U-ViT in unconditional and class-conditional image generation, as well as text-to-image generation tasks, where U-ViT is comparable if not superior to a CNN-based U-Net of a similar size.
Geo-Spatio-Temporal Information Based 3D Cooperative Positioning in LOS/NLOS Mixed Environments
We propose a geographic and spatio-temporal information based distributed cooperative positioning (GSTICP) algorithm for wireless networks that require three-dimensional (3D) coordinates and operate in the line-of-sight (LOS) and nonline-of-sight (NLOS) mixed environments.
Distributed Spatio-Temporal Information Based Cooperative 3D Positioning in GNSS-Denied Environments
A distributed spatio-temporal information based cooperative positioning (STICP) algorithm is proposed for wireless networks that require three-dimensional (3D) coordinates and operate in the global navigation satellite system (GNSS) denied environments.
Contrastive Information Transfer for Pre-Ranking Systems
In this paper, we focus on the information transfer from ranking to pre-ranking stage.
On Data Scaling in Masked Image Modeling
Our study reveals that: (i) Masked image modeling is also demanding on larger data.
Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation
These properties, which we aggregately refer to as optimization friendliness, are identified and analyzed by a set of attention- and optimization-related diagnosis tools.
Ranked #3 on
Instance Segmentation
on COCO test-dev
(using extra training data)
Revealing the Dark Secrets of Masked Image Modeling
In this paper, we compare MIM with the long-dominant supervised pre-trained models from two perspectives, the visualizations and the experiments, to uncover their key representational differences.
Ranked #1 on
Monocular Depth Estimation
on KITTI Eigen split
Sampling Is All You Need on Modeling Long-Term User Behaviors for CTR Prediction
However, the retrieval-based methods are sub-optimal and would cause more or less information losses, and it's difficult to balance the effectiveness and efficiency of the retrieval algorithm.
iCAR: Bridging Image Classification and Image-text Alignment for Visual Recognition
Second, we convert the image classification problem from learning parametric category classifier weights to learning a text encoder as a meta network to generate category classifier weights.
Incorporating Semi-Supervised and Positive-Unlabeled Learning for Boosting Full Reference Image Quality Assessment
Particularly, by treating all labeled data as positive samples, PU learning is leveraged to identify negative samples (i. e., outliers) from unlabeled data.
Enhanced Contour Tracking: a Time-Varying Internal Model Principle-Based Approach
Among the existing contouring control methods, the cross coupled control (CCC) lacks of an asymptotical tracking performance for general contours, and the task coordinate frame (TCF) control usually leads to system nonlinearity, and by design is not well-suited for multi-axis contour tracking.
Decipher soil organic carbon dynamics and driving forces across China using machine learning
Additionally, the national cropland topsoil organic carbon increased with a rate of 23. 6 ± 7. 6 g C m−2 yr−1since the 1980s, and the widely applied nitrogenous fertilizer was a key stimulus.
Correlation-Aware Deep Tracking
In contrast to the Siamese-like feature extraction, our network deeply embeds cross-image feature correlation in multiple layers of the feature network.
Pre-Trained Neural Language Models for Automatic Mobile App User Feedback Answer Generation
In this paper, we evaluate PTMs to generate replies to the mobile app user feedbacks.
Self-supervised Learning from 100 Million Medical Images
Building accurate and robust artificial intelligence systems for medical image assessment requires not only the research and design of advanced deep learning models but also the creation of large and curated sets of annotated training examples.
A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Model
However, semantic segmentation and the CLIP model perform on different visual granularity, that semantic segmentation processes on pixels while CLIP performs on images.
Ranked #1 on
Open Vocabulary Semantic Segmentation
on Cityscapes
Swin Transformer V2: Scaling Up Capacity and Resolution
Three main techniques are proposed: 1) a residual-post-norm method combined with cosine attention to improve training stability; 2) A log-spaced continuous position bias method to effectively transfer models pre-trained using low-resolution images to downstream tasks with high-resolution inputs; 3) A self-supervised pre-training method, SimMIM, to reduce the needs of vast labeled images.
Ranked #4 on
Image Classification
on ImageNet V2
(using extra training data)
SimMIM: A Simple Framework for Masked Image Modeling
We also leverage this approach to facilitate the training of a 3B model (SwinV2-G), that by $40\times$ less data than that in previous practice, we achieve the state-of-the-art on four representative vision benchmarks.
Representation Learning
Self-Supervised Image Classification
Bootstrap Your Object Detector via Mixed Training
We introduce MixTraining, a new training paradigm for object detection that can improve the performance of existing detectors for free.
Bayesian Modeling and Uncertainty Quantification for Learning to Optimize: What, Why, and How
Optimizing an objective function with uncertainty awareness is well-known to improve the accuracy and confidence of optimization solutions.
Deep Reinforcement Learning-Based Long-Range Autonomous Valet Parking for Smart Cities
In this paper, to reduce the congestion rate at the city center and increase the quality of experience (QoE) of each user, the framework of long-range autonomous valet parking (LAVP) is presented, where an Autonomous Vehicle (AV) is deployed in the city, which can pick up, drop off users at their required spots, and then drive to the car park out of city center autonomously.
Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design
Designing novel protein sequences for a desired 3D topological fold is a fundamental yet non-trivial task in protein engineering.
Video Swin Transformer
The vision community is witnessing a modeling shift from CNNs to Transformers, where pure Transformer architectures have attained top accuracy on the major video recognition benchmarks.
Ranked #25 on
Action Classification
on Kinetics-600
(using extra training data)
Continual Learning for Neural Machine Translation
In practical applications, NMT models are usually trained on a general domain corpus and then fine-tuned by continuing training on the in-domain corpus.
Breaking Shortcut: Exploring Fully Convolutional Cycle-Consistency for Video Correspondence Learning
Previous cycle-consistency correspondence learning methods usually leverage image patches for training.
Self-Supervised Learning with Swin Transformers
We are witnessing a modeling shift from CNN to Transformers in computer vision.
Ranked #62 on
Self-Supervised Image Classification
on ImageNet
Prediction of Prognosis and Survival of Patients with Gastric Cancer by Weighted Improved Random Forest Model
Among the 10 public datasets, the Random Forest weighted in accuracy has the best performance on 6 datasets, with an average increase of 1. 44% in accuracy and an average increase of 1. 2% in AUC.
Group-Free 3D Object Detection via Transformers
Instead of grouping local points to each object candidate, our method computes the feature of an object from all the points in the point cloud with the help of an attention mechanism in the Transformers \cite{vaswani2017attention}, where the contribution of each point is automatically learned in the network training.
Ranked #3 on
3D Object Detection
on SUN-RGBD
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a general-purpose backbone for computer vision.
Ranked #2 on
Image Classification
on OmniBenchmark
Pseudo-ISP: Learning Pseudo In-camera Signal Processing Pipeline from A Color Image Denoiser
To begin with, the pre-trained denoiser is used to generate the pseudo clean images for the test images.
ParaSCI: A Large Scientific Paraphrase Dataset for Longer Paraphrase Generation
We propose ParaSCI, the first large-scale paraphrase dataset in the scientific field, including 33, 981 paraphrase pairs from ACL (ParaSCI-ACL) and 316, 063 pairs from arXiv (ParaSCI-arXiv).
Bayesian Learning to Optimize: Quantifying the Optimizer Uncertainty
Optimizing an objective function with uncertainty awareness is well-known to improve the accuracy and confidence of optimization solutions.
Leveraging Batch Normalization for Vision Transformers
Transformer-based vision architectures have attracted great attention because of the strong performance over the convolutional neural networks (CNNs).
Global Context Networks
The Non-Local Network (NLNet) presents a pioneering approach for capturing long-range dependencies within an image, via aggregating query-specific global context to each query position.
Ranked #37 on
Instance Segmentation
on COCO test-dev
DR 21 South Filament: a Parsec-sized Dense Gas Accretion Flow onto the DR 21 Massive Young Cluster
DR21 south filament (DR21SF) is a unique component of the giant network of filamentary molecular clouds in the north region of Cygnus X complex.
Astrophysics of Galaxies
Propagate Yourself: Exploring Pixel-Level Consistency for Unsupervised Visual Representation Learning
We argue that the power of contrastive learning has yet to be fully unleashed, as current methods are trained only on instance-level pretext tasks, leading to representations that may be sub-optimal for downstream tasks requiring dense pixel predictions.
DivGAN: Towards Diverse Paraphrase Generation via Diversified Generative Adversarial Network
In this paper, we propose a deep generative model to generate diverse paraphrases.
Progressive Training of Multi-level Wavelet Residual Networks for Image Denoising
To cope with this issue, this paper presents a multi-level wavelet residual network (MWRN) architecture as well as a progressive training (PTMWRN) scheme to improve image denoising performance.
Unpaired Learning of Deep Image Denoising
As for knowledge distillation, we first apply the learned noise models to clean images to synthesize a paired set of training images, and use the real noisy images and the corresponding denoising results in the first stage to form another paired set.
RepPoints V2: Verification Meets Regression for Object Detection
Though RepPoints provides high performance, we find that its heavy reliance on regression for object localization leaves room for improvement.
Ranked #70 on
Object Detection
on COCO test-dev
Quantifying and Leveraging Predictive Uncertainty for Medical Image Assessment
In our experiments we demonstrate that sample rejection based on the predicted uncertainty can significantly improve the ROC-AUC for various tasks, e. g., by 8% to 0. 91 with an expected rejection rate of under 25% for the classification of different abnormalities in chest radiographs.
A Closer Look at Local Aggregation Operators in Point Cloud Analysis
Our investigation reveals that despite the different designs of these operators, all of these operators make surprisingly similar contributions to the network performance under the same network input and feature numbers and result in the state-of-the-art accuracy on standard benchmarks.
Ranked #4 on
3D Semantic Segmentation
on PartNet
Jointly Learning to Align and Summarize for Neural Cross-Lingual Summarization
However, it is a big challenge for the model to directly learn cross-lingual summarization as it requires learning to understand different languages and learning how to summarize at the same time.
Parametric Instance Classification for Unsupervised Visual Feature Learning
This paper presents parametric instance classification (PIC) for unsupervised visual feature learning.
Disentangled Non-Local Neural Networks
This paper first studies the non-local block in depth, where we find that its attention computation can be split into two terms, a whitened pairwise term accounting for the relationship between two pixels and a unary term representing the saliency of every pixel.
Ranked #14 on
Semantic Segmentation
on Cityscapes test
NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results
This challenge is based on a newly collected validation and testing image datasets, and hence, named SIDD+.
Memory Enhanced Global-Local Aggregation for Video Object Detection
We argue that there are two important cues for humans to recognize objects in videos: the global semantic information and the local localization information.
Ranked #7 on
Video Object Detection
on ImageNet VID
Negative Margin Matters: Understanding Margin in Few-shot Classification
This paper introduces a negative margin loss to metric learning based few-shot learning methods.
Cross-Iteration Batch Normalization
We thus compensate for the network weight changes via a proposed technique based on Taylor polynomials, so that the statistics can be accurately estimated and batch normalization can be effectively applied.
Ranked #193 on
Object Detection
on COCO test-dev
Energy-based Graph Convolutional Networks for Scoring Protein Docking Models
Moreover, estimating model quality, also known as the quality assessment problem, is rarely addressed in protein docking.
Learning to Optimize in Swarms
Learning to optimize has emerged as a powerful framework for various optimization and machine learning tasks.
VL-BERT: Pre-training of Generic Visual-Linguistic Representations
We introduce a new pre-trainable generic representation for visual-linguistic tasks, called Visual-Linguistic BERT (VL-BERT for short).
Ranked #1 on
Visual Question Answering (VQA)
on VCR (Q-A) dev
GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond
In this paper, we take advantage of this finding to create a simplified network based on a query-independent formulation, which maintains the accuracy of NLNet but with significantly less computation.
Ranked #55 on
Instance Segmentation
on COCO test-dev
Spatial-Temporal Relation Networks for Multi-Object Tracking
Recent progress in multiple object tracking (MOT) has shown that a robust similarity score is key to the success of trackers.
Jointly Learning Explainable Rules for Recommendation with Knowledge Graph
The framework encourages two modules to complement each other in generating effective and explainable recommendation: 1) inductive rules, mined from item-centric knowledge graphs, summarize common multi-hop relational patterns for inferring different item associations and provide human-readable explanation for model prediction; 2) recommendation module can be augmented by induced rules and thus have better generalization ability dealing with the cold-start issue.
Deep Triplet Quantization
We propose Deep Triplet Quantization (DTQ), a novel approach to learning deep quantization models from the similarity triplets.
Ranked #1 on
Image Retrieval
on NUS-WIDE
Bayesian active learning for optimization and uncertainty quantification in protein docking
To the best of our knowledge, this study represents the first uncertainty quantification solution for protein docking, with theoretical rigor and comprehensive assessment.
HashGAN: Deep Learning to Hash With Pair Conditional Wasserstein GAN
The main idea is to augment the training data with nearly real images synthesized from a new Pair Conditional Wasserstein GAN (PC-WGAN) conditioned on the pairwise similarity information.
Deep Cauchy Hashing for Hamming Space Retrieval
Due to its computation efficiency and retrieval quality, hashing has been widely applied to approximate nearest neighbor search for large-scale image retrieval, while deep hashing further improves the retrieval quality by end-to-end representation learning and hash coding.
Deep Visual-Semantic Quantization for Efficient Image Retrieval
This paper presents a compact coding solution with a focus on the deep learning to quantization approach, which improves retrieval quality by end-to-end representation learning and compact encoding and has already shown the superior performance over the hashing solutions for similarity retrieval.
Correlation Hashing Network for Efficient Cross-Modal Retrieval
This paper presents a Correlation Hashing Network (CHN) approach to cross-modal hashing, which jointly learns good data representation tailored to hash coding and formally controls the quantization error.
Learning Transferable Features with Deep Adaptation Networks
Recent studies reveal that a deep neural network can learn transferable features which generalize well to novel tasks for domain adaptation.
Ranked #3 on
Domain Adaptation
on Synth Digits-to-SVHN
