Search Results for author:
Found 267 papers, 100 papers with code
Gradient Harmonized Single-stage Detector
Despite the great success of two-stage detectors, single-stage detector is still a more elegant and efficient way, yet suffers from the two well-known disharmonies during training, i. e. the huge difference in quantity between positive and negative examples as well as between easy and hard examples.
Ranked #165 on
Object Detection
on COCO test-dev
DETRs with Collaborative Hybrid Assignments Training
This new training scheme can easily enhance the encoder's learning ability in end-to-end detectors by training the multiple parallel auxiliary heads supervised by one-to-many label assignments such as ATSS and Faster RCNN.
Ranked #1 on
Object Detection
on LVIS v1.0 val
(using extra training data)
Composer: Creative and Controllable Image Synthesis with Composable Conditions
Recent large-scale generative models learned on big data are capable of synthesizing incredible images yet suffer from limited controllability.
Cones: Concept Neurons in Diffusion Models for Customized Generation
Concatenating multiple clusters of concept neurons can vividly generate all related concepts in a single image.
AnyDoor: Zero-shot Object-level Image Customization
This work presents AnyDoor, a diffusion-based image generator with the power to teleport target objects to new scenes at user-specified locations in a harmonious way.
Temporal Interlacing Network
In this way, a heavy temporal model is replaced by a simple interlacing operator.
Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization
We propose to explicitly model the Actor-Context-Actor Relation, which is the relation between two actors based on their interactions with the context.
Ranked #2 on
Action Recognition
on AVA v2.1
UniFormer: Unified Transformer for Efficient Spatial-Temporal Representation Learning
For Something-Something V1 and V2, our UniFormer achieves new state-of-the-art performances of 60. 8% and 71. 4% top-1 accuracy respectively.
Ranked #8 on
Action Recognition
on Something-Something V1
UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning
For Something-Something V1 and V2, our UniFormer achieves new state-of-the-art performances of 60. 9% and 71. 2% top-1 accuracy respectively.
DreamVideo: Composing Your Dream Videos with Customized Subject and Motion
In motion learning, we architect a motion adapter and fine-tune it on the given videos to effectively model the target motion pattern.
VideoLCM: Video Latent Consistency Model
Consistency models have demonstrated powerful capability in efficient image generation and allowed synthesis within a few sampling steps, alleviating the high computational cost in diffusion models.
A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning
In this paper, from a novel perspective, we systematically study the challenges that remain in O2O RL and identify that the reason behind the slow improvement of the performance and the instability of online finetuning lies in the inaccurate Q-value estimation inherited from offline pretraining.
T-GCN: A Temporal Graph ConvolutionalNetwork for Traffic Prediction
However, traffic forecasting has always been considered an open scientific issue, owing to the constraints of urban road network topological structure and the law of dynamic change with time, namely, spatial dependence and temporal dependence.
Ranked #4 on
Traffic Prediction
on SZ-Taxi
Correlation Congruence for Knowledge Distillation
Most teacher-student frameworks based on knowledge distillation (KD) depend on a strong congruent constraint on instance level.
LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios
Building agents based on tree-search planning capabilities with learned models has achieved remarkable success in classic decision-making problems, such as Go and Atari.
Talking Face Generation by Adversarially Disentangled Audio-Visual Representation
Talking face generation aims to synthesize a sequence of face images that correspond to a clip of speech.
UniFormer: Unifying Convolution and Self-attention for Visual Recognition
Different from the typical transformer blocks, the relation aggregators in our UniFormer block are equipped with local and global token affinity respectively in shallow and deep layers, allowing to tackle both redundancy and dependency for efficient and effective representation learning.
Ranked #153 on
Image Classification
on ImageNet
Knowledge Distillation via Route Constrained Optimization
However, we find that the representation of a converged heavy model is still a strong constraint for training a small student model, which leads to a high lower bound of congruence loss.
Cones 2: Customizable Image Synthesis with Multiple Subjects
Synthesizing images with user-specified subjects has received growing attention due to its practical applications.
Rotate-and-Render: Unsupervised Photorealistic Face Rotation from Single-View Images
Though face rotation has achieved rapid progress in recent years, the lack of high-quality paired training data remains a great hurdle for existing methods.
Top-1 Solution of Multi-Moments in Time Challenge 2019
In this technical report, we briefly introduce the solutions of our team 'Efficient' for the Multi-Moments in Time challenge in ICCV 2019.
Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformer
Large-scale deployment of autonomous vehicles has been continually delayed due to safety concerns.
Ranked #2 on
Autonomous Driving
on CARLA Leaderboard
1st Place Solutions for OpenImage2019 -- Object Detection and Instance Segmentation
Given such good instance bounding box, we further design a simple instance-level semantic segmentation pipeline and achieve the 1st place on the segmentation challenge.
Revisiting the Sibling Head in Object Detector
The ``shared head for classification and localization'' (sibling head), firstly denominated in Fast RCNN~\cite{girshick2015fast}, has been leading the fashion of the object detection community in the past five years.
Ranked #67 on
Object Detection
on COCO test-dev
GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest
Before sending to LLM, the reference is replaced by RoI features and interleaved with language embeddings as a sequence.
Ranked #1 on
Visual Question Answering (VQA)
on VCR (Q-AR) test
LMDrive: Closed-Loop End-to-End Driving with Large Language Models
On the other hand, previous autonomous driving methods tend to rely on limited-format inputs (e. g. sensor data and navigation waypoints), restricting the vehicle's ability to understand language information and interact with humans.
AnimateLCM: Accelerating the Animation of Personalized Diffusion Models and Adapters with Decoupled Consistency Learning
We validate the proposed strategy in image-conditioned video generation and layout-conditioned video generation, all achieving top-performing results.
Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising
To address this challenge, we introduce a novel paradigm dubbed as Gen-L-Video, capable of extending off-the-shelf short video diffusion models for generating and editing videos comprising hundreds of frames with diverse semantic segments without introducing additional training, all while preserving content consistency.
Recurrent Scale Approximation for Object Detection in CNN
To further increase efficiency and accuracy, we (a): design a scale-forecast network to globally predict potential scales in the image since there is no need to compute maps on all levels of the pyramid.
Ranked #3 on
Face Detection
on Annotated Faces in the Wild
Learning to Measure Change: Fully Convolutional Siamese Metric Networks for Scene Change Detection
A critical challenge problem of scene change detection is that noisy changes generated by varying illumination, shadows and camera viewpoint make variances of a scene difficult to define and measure since the noisy changes and semantic ones are entangled.
1st place solution for AVA-Kinetics Crossover in AcitivityNet Challenge 2020
This technical report introduces our winning solution to the spatio-temporal action localization track, AVA-Kinetics Crossover, in ActivityNet Challenge 2020.
Crafting GBD-Net for Object Detection
The effectiveness of GBD-Net is shown through experiments on three object detection datasets, ImageNet, Pascal VOC2007 and Microsoft COCO.
ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency
In the learning phase, each agent minimizes the TD error that is dependent on how the subsequent agents have reacted to their chosen action.
Ranked #1 on
SMAC
on SMAC 3s5z_vs_3s6z
Learning Deep Features via Congenerous Cosine Loss for Person Recognition
Person recognition aims at recognizing the same identity across time and space with complicated scenes and similar appearance.
DPGN: Distribution Propagation Graph Network for Few-shot Learning
To combine the distribution-level relations and instance-level relations for all examples, we construct a dual complete graph network which consists of a point graph and a distribution graph with each node standing for an example.
Ranked #2 on
Few-Shot Learning
on Mini-ImageNet - 1-Shot Learning
Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction
The HoP approach is straightforward: given the current timestamp t, we generate a pseudo Bird's-Eye View (BEV) feature of timestamp t-k from its adjacent frames and utilize this feature to predict the object set at timestamp t-k. Our approach is motivated by the observation that enforcing the detector to capture both the spatial location and temporal motion of objects occurring at historical timestamps can lead to more accurate BEV feature learning.
Ranked #3 on
3D Object Detection
on nuScenes Camera Only
Rethinking the Spatial Inconsistency in Classifier-Free Diffusion Guidance
Classifier-Free Guidance (CFG) has been widely used in text-to-image diffusion models, where the CFG scale is introduced to control the strength of text guidance on the whole image space.
CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching
We further attribute this phenomenon to the diffusion model's insufficient condition utilization, which is caused by its training paradigm.
DASNet: Dual attentive fully convolutional siamese networks for change detection of high resolution satellite images
However, the available methods focus mainly on the difference information between multitemporal remote sensing images and lack robustness to pseudo-change information.
Towards Flops-constrained Face Recognition
Large scale face recognition is challenging especially when the computational budget is limited.
MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers
In this paper, we propose Mixed and Masked AutoEncoder (MixMAE), a simple but efficient pretraining method that is applicable to various hierarchical Vision Transformers.
Ranked #2 on
Image Classification
on Places205
Anisotropic Convolutional Networks for 3D Semantic Scene Completion
In contrast to the standard 3D convolution that is limited to a fixed 3D receptive field, our module is capable of modeling the dimensional anisotropy voxel-wisely.
FouriScale: A Frequency Perspective on Training-Free High-Resolution Image Synthesis
In this study, we delve into the generation of high-resolution images from pre-trained diffusion models, addressing persistent challenges, such as repetitive patterns and structural distortions, that emerge when models are applied beyond their trained resolutions.
Quality Aware Network for Set to Set Recognition
In this paper, the quality aware network (QAN) is proposed to confront this problem, where the quality of each sample can be automatically learned although such information is not explicitly provided in the training stage.
Ranked #6 on
Face Verification
on YouTube Faces DB
HDGT: Heterogeneous Driving Graph Transformer for Multi-Agent Trajectory Prediction via Scene Encoding
Based on these observations, we propose Heterogeneous Driving Graph Transformer (HDGT), a backbone modelling the driving scene as a heterogeneous graph with different types of nodes and edges.
UniNet: Unified Architecture Search with Convolution, Transformer, and MLP
Finally, we integrate configurable operators and DSMs into a unified search space and search with a Reinforcement Learning-based search algorithm to fully explore the optimal combination of the operators.
Ranked #12 on
Neural Architecture Search
on ImageNet
TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers
In this paper, we propose a novel data augmentation technique TokenMix to improve the performance of vision transformers.
Learning Where to Focus for Efficient Video Object Detection
Transferring existing image-based detectors to the video is non-trivial since the quality of frames is always deteriorated by part occlusion, rare pose, and motion blur.
Ranked #22 on
Video Object Detection
on ImageNet VID
Lifelong Person Re-Identification via Adaptive Knowledge Accumulation
In this work we explore a new and challenging ReID task, namely lifelong person re-identification (LReID), which enables to learn continuously across multiple domains and even generalise on new and unseen domains.
Mapping evolving population geography in China
China's demographic changes have important global economic and geopolitical implications.
Self-slimmed Vision Transformer
Specifically, we first design a novel Token Slimming Module (TSM), which can boost the inference efficiency of ViTs by dynamic token aggregation.
3D Semantic Subspace Traverser: Empowering 3D Generative Model with Shape Editing Capability
Our method utilizes implicit functions as the 3D shape representation and combines a novel latent-space GAN with a linear subspace model to discover semantic dimensions in the local latent space of 3D shapes.
UV-SAM: Adapting Segment Anything Model for Urban Village Identification
Urban villages, defined as informal residential areas in or around urban centers, are characterized by inadequate infrastructures and poor living conditions, closely related to the Sustainable Development Goals (SDGs) on poverty, adequate housing, and sustainable cities.
Large-batch Optimization for Dense Visual Predictions
To address this challenge, we propose a simple yet effective algorithm, named Adaptive Gradient Variance Modulator (AGVM), which can train dense visual predictors with very large batch size, enabling several benefits more appealing than prior arts.
MoVA: Adapting Mixture of Vision Experts to Multimodal Context
Although some large-scale pretrained vision encoders such as vision encoders in CLIP and DINOv2 have brought promising performance, we found that there is still no single vision encoder that can dominate various image content understanding, e. g., the CLIP vision encoder leads to outstanding results on general image understanding but poor performance on document or chart content.
Unifying Visual Perception by Dispersible Points Learning
The method, called UniHead, views different visual perception tasks as the dispersible points learning via the transformer encoder architecture.
Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priors
Inspired by this, we propose ASAP-RL, an efficient reinforcement learning algorithm for autonomous driving that simultaneously leverages motion skills and expert priors.
Improving Object-centric Learning with Query Optimization
The ability to decompose complex natural scenes into meaningful object-centric abstractions lies at the core of human perception and reasoning.
Improved Techniques for Learning to Dehaze and Beyond: A Collective Study
Here we explore two related but important tasks based on the recently released REalistic Single Image DEhazing (RESIDE) benchmark dataset: (i) single image dehazing as a low-level image restoration problem; and (ii) high-level visual understanding (e. g., object detection) of hazy images.
Depth Based Semantic Scene Completion with Position Importance Aware Loss
We propose PALNet, a novel hybrid network for SSC based on single depth.
GeoMIM: Towards Better 3D Knowledge Transfer via Masked Image Modeling for Multi-view 3D Understanding
In this paper, we propose Geometry Enhanced Masked Image Modeling (GeoMIM) to transfer the knowledge of the LiDAR model in a pretrain-finetune paradigm for improving the multi-view camera-based 3D detection.
SmartRefine: A Scenario-Adaptive Refinement Framework for Efficient Motion Prediction
Context information, such as road maps and surrounding agents' states, provides crucial geometric and semantic information for motion behavior prediction.
Visual CoT: Unleashing Chain-of-Thought Reasoning in Multi-Modal Language Models
This paper presents Visual CoT, a novel pipeline that leverages the reasoning capabilities of multi-modal large language models (MLLMs) by incorporating visual Chain-of-Thought (CoT) reasoning.
Self-supervised Video Representation Learning by Context and Motion Decoupling
A key challenge in self-supervised video representation learning is how to effectively capture motion information besides context bias.
Video Diffusion Models with Local-Global Context Guidance
We construct a local-global context guidance strategy to capture the multi-perceptual embedding of the past fragment to boost the consistency of future prediction.
TagAlign: Improving Vision-Language Alignment with Multi-Tag Classification
The crux of learning vision-language models is to extract semantically aligned information from visual and linguistic data.
Be-Your-Outpainter: Mastering Video Outpainting through Input-Specific Adaptation
We introduce MOTIA Mastering Video Outpainting Through Input-Specific Adaptation, a diffusion-based pipeline that leverages both the intrinsic data-specific patterns of the source video and the image/video generative prior for effective outpainting.
Exploiting temporal consistency for real-time video depth estimation
The temporal consistency loss is combined with the spatial loss to update the model in an end-to-end fashion.
Ranked #5 on
Monocular Depth Estimation
on Mid-Air Dataset
Teach-DETR: Better Training DETR with Teachers
In this paper, we present a novel training scheme, namely Teach-DETR, to learn better DETR-based detectors from versatile teacher detectors.
Zoom Out-and-In Network with Map Attention Decision for Region Proposal and Object Detection
A key observation is that it is difficult to classify anchors of different sizes with the same set of features.
Ranked #2 on
Region Proposal
on COCO test-dev
Zoom Out-and-In Network with Recursive Training for Object Proposal
In this paper, we propose a zoom-out-and-in network for generating object proposals.
Visual Localization Under Appearance Change: Filtering Approaches
Our approaches rely on local features with an encoding technique to represent an image as a single vector.
PAD-Net: A Perception-Aided Single Image Dehazing Network
In this work, we investigate the possibility of replacing the $\ell_2$ loss with perceptually derived loss functions (SSIM, MS-SSIM, etc.)
Segment, Magnify and Reiterate: Detecting Camouflaged Objects the Hard Way
To tackle camouflaged object detection (COD), we are inspired by humans attention coupled with the coarse-to-fine detection strategy, and thereby propose an iterative refinement framework, coined SegMaR, which integrates Segment, Magnify and Reiterate in a multi-stage detection fashion.
Generating Dynamic Kernels via Transformers for Lane Detection
While such methods reduce the reliance on specific knowledge, the kernels computed from the key locations fail to capture the lane line's global structure due to its long and thin structure, leading to inaccurate detection of lane lines with complex topologies.
Ranked #1 on
Lane Detection
on CurveLanes
Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization
A single language model (LM), despite aligning well with an average labeler through reinforcement learning from human feedback (RLHF), may not universally suit diverse human preferences.
On the Exploration of Incremental Learning for Fine-grained Image Retrieval
On the other hand, fine-tuning the learned representation only with the new classes leads to catastrophic forgetting.
Knowledge-infused Contrastive Learning for Urban Imagery-based Socioeconomic Prediction
To address such issues, in this paper, we propose a Knowledge-infused Contrastive Learning (KnowCL) model for urban imagery-based socioeconomic prediction.
Towards Generative Modeling of Urban Flow through Knowledge-enhanced Denoising Diffusion
To capture the effect of multiple factors on urban flow, such as region features and urban environment, we employ diffusion model to generate urban flow for regions under different conditions.
Generalizing Tensor Decomposition for N-ary Relational Knowledge Bases
With the rapid development of knowledge bases (KBs), link prediction task, which completes KBs with missing facts, has been broadly studied in especially binary relational KBs (a. k. a knowledge graph) with powerful tensor decomposition related methods.
More Classifiers, Less Forgetting: A Generic Multi-classifier Paradigm for Incremental Learning
Since those regularization strategies are mostly associated with classifier outputs, we propose a MUlti-Classifier (MUC) incremental learning paradigm that integrates an ensemble of auxiliary classifiers to estimate more effective regularization constraints.
A novel multimodal approach for hybrid brain-computer interface
It has been already shown in literature that the hybrid of EEG and NIRS has better results than their respective individual signals.
Human-Computer Interaction Signal Processing
Hyperspectral Classification Based on 3D Asymmetric Inception Network with Data Fusion Transfer Learning
Hyperspectral image(HSI) classification has been improved with convolutional neural network(CNN) in very recent years.
Extending regionalization algorithms to explore spatial process heterogeneity
In spatial regression models, spatial heterogeneity may be considered with either continuous or discrete specifications.
Single-Stage Open-world Instance Segmentation with Cross-task Consistency Regularization
Based on the single-stage instance segmentation framework, we propose a regularization model to predict foreground pixels and use its relation to instance segmentation to construct a cross-task consistency loss.
A Satellite Imagery Dataset for Long-Term Sustainable Development in United States Cities
Especially satellite imagery is a potential data source for studying sustainable urban development.
Genetic Quantization-Aware Approximation for Non-Linear Operations in Transformers
Non-linear functions are prevalent in Transformers and their lightweight variants, incurring substantial and frequently underestimated hardware costs.
Cooperative Multi-Agent Reinforcement Learning with Hypergraph Convolution
HGCN-MIX models agents as well as their relationships as a hypergraph, where agents are nodes and hyperedges among nodes indicate that the corresponding agents can coordinate to achieve larger rewards.
Privacy-Preserving Personalized Fitness Recommender System (P3FitRec): A Multi-level Deep Learning Approach
Recommender systems have been successfully used in many domains with the help of machine learning algorithms.
Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identification
To solve the problem, we present a carefully designed dual Gaussian-based variational auto-encoder (DG-VAE), which disentangles an identity-discriminable and an identity-ambiguous cross-modality feature subspace, following a mixture-of-Gaussians (MoG) prior and a standard Gaussian distribution prior, respectively.
Understanding the mesoscopic scaling patterns within cities
Understanding quantitative relationships between urban elements is crucial for a wide range of applications.
Physics and Society
Extensible Multi-Granularity Fusion Network for Aspect-based Sentiment Analysis
This paper presents the Extensible Multi-Granularity Fusion (EMGF) network, which integrates information from dependency and constituent syntactic, attention semantic , and external knowledge graphs.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
Role-Aware Modeling for N-ary Relational Knowledge Bases
N-ary relational knowledge bases (KBs) represent knowledge with binary and beyond-binary relational facts.
Centralized Cooperative Exploration Policy for Continuous Control Tasks
To explicitly encourage exploration in continuous control tasks, we propose CCEP (Centralized Cooperative Exploration Policy), which utilizes underestimation and overestimation of value functions to maintain the capacity of exploration.
ACDnet: An action detection network for real-time edge computing based on flow-guided feature approximation and memory aggregation
Interpreting human actions requires understanding the spatial and temporal context of the scenes.
Snow Removal for LiDAR Point Clouds with Spatio-temporal Conditional Random Fields
The proposed approach first constructs the CRF based on k-nearest neighbors with the snow confidence derived from the physical priors of snow, such as intensity and distribution.
Estimating On-road Transportation Carbon Emissions from Open Data of Road Network and Origin-destination Flow Data
To relieve this issue by utilizing the strong pattern recognition of artificial intelligence, we incorporate two sources of open data representative of the transportation demand and capacity factors, the origin-destination (OD) flow data and the road network data, to build a hierarchical heterogeneous graph learning method for on-road carbon emission estimation (HENCE).
Beyond Trade-off: Accelerate FCN-based Face Detector with Higher Accuracy
Fully convolutional neural network (FCN) has been dominating the game of face detection task for a few years with its congenital capability of sliding-window-searching with shared kernels, which boiled down all the redundant calculation, and most recent state-of-the-art methods such as Faster-RCNN, SSD, YOLO and FPN use FCN as their backbone.
Transferable Semi-supervised Semantic Segmentation
The performance of deep learning based semantic segmentation models heavily depends on sufficient data with careful annotations.
Exploring Disentangled Feature Representation Beyond Face Identification
This paper proposes learning disentangled but complementary face features with minimal supervision by face identification.
Region-based Quality Estimation Network for Large-scale Person Re-identification
One of the major restrictions on the performance of video-based person re-id is partial noise caused by occlusion, blur and illumination.
MLBench: How Good Are Machine Learning Clouds for Binary Classification Tasks on Structured Data?
We then compare the performance of the top winning code available from Kaggle with that of running machine learning clouds from both Azure and Amazon on mlbench.
Unsupervised Sequence Classification using Sequential Output Statistics
Although it is harder to optimize in its functional form, a stochastic primal-dual gradient method is developed to effectively solve the problem.
Combinatorial Multi-Armed Bandit with General Reward Functions
Our framework enables a much larger class of reward functions such as the $\max()$ function and nonlinear utility functions.
On the Exploration of Convolutional Fusion Networks for Visual Recognition
Despite recent advances in multi-scale deep representations, their limitations are attributed to expensive parameters and weak fusion modules.
POI: Multiple Object Tracking with High Performance Detection and Appearance Feature
In this paper, we explore the high-performance detection and deep learning based appearance feature, and show that they lead to significantly better MOT results in both online and offline setting.
Storytelling of Photo Stream with Bidirectional Multi-thread Recurrent Neural Network
Second, by using sGRU as basic units, the BMRNN is trained to align the local storylines into the global sequential timeline.
Modulation Classification via Gibbs Sampling Based on a Latent Dirichlet Bayesian Network
A novel Bayesian modulation classification scheme is proposed for a single-antenna system over frequency-selective fading channels.
Knowledge Graph Embedding with Entity Neighbors and Deep Memory Network
Knowledge Graph Embedding (KGE) aims to represent entities and relations of knowledge graph in a low-dimensional continuous vector space.
How far from automatically interpreting deep learning
In other words, there is a gap between the deep learning model and the cognitive mode.
RGB-D Based Action Recognition with Light-weight 3D Convolutional Networks
Different from RGB videos, depth data in RGB-D videos provide key complementary information for tristimulus visual data which potentially could achieve accuracy improvement for action recognition.
How to improve the interpretability of kernel learning
In this paper, a quantitative index of the interpretability is proposed and its rationality is proved, and equilibrium problem between the interpretability and the generalization performance is analyzed.
Derivative Estimation in Random Design
We propose a nonparametric derivative estimation method for random design without having to estimate the regression function.
Hyperparameter Optimization for Tracking With Continuous Deep Q-Learning
Hyperparameters are numerical presets whose values are assigned prior to the commencement of the learning process.
MoNet: Deep Motion Exploitation for Video Object Segmentation
In this paper, we propose a novel MoNet model to deeply exploit motion cues for boosting video object segmentation performance from two aspects, i. e., frame representation learning and segmentation refinement.
Transductive Centroid Projection for Semi-supervised Large-scale Recognition
It is inspired by the observation of the weights in classification layer (called extit{anchors}) converge to the central direction of each class in hyperspace.
Learning Pairwise Relationship for Multi-object Detection in Crowded Scenes
As the post-processing step for object detection, non-maximum suppression (GreedyNMS) is widely used in most of the detectors for many years.
Learning Relaxed Deep Supervision for Better Edge Detection
We consider these false positives in the supervision, and are able to achieve high performance for better edge detection.
Learning a Recurrent Residual Fusion Network for Multimodal Matching
A major challenge in matching between vision and language is that they typically have completely different features and representations.
RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion
RGB images differentiate from depth images as they carry more details about the color and texture information, which can be utilized as a vital complementary to depth for boosting the performance of 3D semantic scene completion (SSC).
Ranked #19 on
3D Semantic Scene Completion
on NYUv2
Conditional Adversarial Generative Flow for Controllable Image Synthesis
Flow-based generative models show great potential in image synthesis due to its reversible pipeline and exact log-likelihood target, yet it suffers from weak ability for conditional image synthesis, especially for multi-label or unaware conditions.
Extracting human emotions at different places based on facial expressions and spatial clustering analysis
In this study, a novel framework for extracting human emotions from large-scale georeferenced photos at different places is proposed.
From Caesar Cipher to Unsupervised Learning: A New Method for Classifier Parameter Estimation
To remove the need for the parallel training corpora has practical significance for real-world applications, and it is one of the main goals of unsupervised learning.
Use of OWL and Semantic Web Technologies at Pinterest
In this paper, we present the engineering of an OWL ontology---the Pinterest Taxonomy---that forms the core of Pinterest's knowledge graph, the Pinterest Taste Graph.
Scalable Place Recognition Under Appearance Change for Autonomous Driving
Our experiments show that, compared to state-of-the-art techniques, our method has much greater potential for large-scale place recognition for autonomous driving.
Modeling Event Propagation via Graph Biased Temporal Point Process
Temporal point process is widely used for sequential data modeling.
In defense of OSVOS
Through adding a common module, video loss, which we formulate with various forms of constraints (including weighted BCE loss, high-dimensional triplet loss, as well as a novel mixed instance-aware video loss), to train the parent network in the step (2), the network is then better prepared for the step (3), i. e. online fine-tuning on the target instance.
Boosting Throughput and Efficiency of Hardware Spiking Neural Accelerators using Time Compression Supporting Multiple Spike Codes
Using spiking speech and image recognition datasets, we demonstrate the feasibility of supporting large time compression ratios of up to 16x, delivering up to 15. 93x, 13. 88x, and 86. 21x improvements in throughput, energy dissipation, the tradeoffs between hardware area, runtime, energy, and classification accuracy, respectively based on different spike codes on a Xilinx Zynq-7000 FPGA.
Meta Learning with Differentiable Closed-form Solver for Fast Video Object Segmentation
This paper tackles the problem of video object segmentation.
Gradient Information Guided Deraining with A Novel Network and Adversarial Training
However, the existing methods usually do not have good generalization ability, which leads to the fact that almost all of existing methods have a satisfied performance on removing a specific type of rain streaks, but may have a relatively poor performance on other types of rain streaks.
A game method for improving the interpretability of convolution neural network
The reason is, we believe that: the network is essentially a perceptual model.
Differentiable Kernel Evolution
This paper proposes a differentiable kernel evolution (DKE) algorithm to find a better layer-operator for the convolutional neural network.
Search to Distill: Pearls are Everywhere but not the Eyes
Standard Knowledge Distillation (KD) approaches distill the knowledge of a cumbersome teacher model into the parameters of a student model with a pre-defined architecture.
3D Gated Recurrent Fusion for Semantic Scene Completion
This paper tackles the problem of data fusion in the semantic scene completion (SSC) task, which can simultaneously deal with semantic labeling and scene completion.
Ranked #14 on
3D Semantic Scene Completion
on NYUv2
KPNet: Towards Minimal Face Detector
The small receptive field and capacity of minimal neural networks limit their performance when using them to be the backbone of detectors.
Change Detection in Heterogeneous Optical and SAR Remote Sensing Images via Deep Homogeneous Feature Fusion
To solve this problem, this paper presents a new homogeneous transformation model termed deep homogeneous feature fusion (DHFF) based on image style transfer (IST).
Complementary Boundary Generator with Scale-Invariant Relation Modeling for Temporal Action Localization: Submission to ActivityNet Challenge 2020
Specifically, in order to generate high-quality proposals, we consider several factors including the video feature encoder, the proposal generator, the proposal-proposal relations, the scale imbalance, and ensemble strategy.
Discriminability Distillation in Group Representation Learning
We show the discrimiability knowledge has good properties that can be distilled by a light-weight distillation network and can be generalized on the unseen target set.
Image Retrieval for Structure-from-Motion via Graph Convolutional Network
Conventional image retrieval techniques for Structure-from-Motion (SfM) suffer from the limit of effectively recognizing repetitive patterns and cannot guarantee to create just enough match pairs with high precision and high recall.
Commands 4 Autonomous Vehicles (C4AV) Workshop Summary
In this work, we deviate from recent, popular task settings and consider the problem under an autonomous vehicle scenario.
Ranked #3 on
Referring Expression Comprehension
on Talk2Car
Fast MNAS: Uncertainty-aware Neural Architecture Search with Lifelong Learning
Further, a life-long knowledge pool together with a block similarity function is proposed to utilize the lifelong parameter knowledge and reduces the searching time by 2 times.
Self-supervised Temporal Learning
Inspired by spatial-based contrastive SSL, we show that significant improvement can be achieved by a proposed temporal-based contrastive learning approach, which includes three novel and efficient modules: temporal augmentations, temporal memory bank and SSTL loss.
Delineating Intra-Urban Spatial Connectivity Patterns by Travel-Activities: A Case Study of Beijing, China
Travel activities have been widely applied to quantify spatial interactions between places, regions and nations.
Physics and Society Social and Information Networks
MulDE: Multi-teacher Knowledge Distillation for Low-dimensional Knowledge Graph Embeddings
Link prediction based on knowledge graph embeddings (KGE) aims to predict new triples to automatically construct knowledge graphs (KGs).
The artificial ecosystem: number soup (part II)
This paper is a follow-up work about the artificial ecosystem model: number soup (Liu and Sumpter, J. Royal Soc.
Electronic properties of InAs/EuS/Al hybrid nanowires
We study the electronic properties of InAs/EuS/Al heterostructures as explored in a recent experiment [S. Vaitiekenas \emph{et al.}, Nat.
Mesoscale and Nanoscale Physics
Deep Reinforcement Learning for Dynamic Spectrum Sensing and Aggregation in Multi-Channel Wireless Networks
Then, the vacant channels in the selected segment will be aggregated for satisfying the user requirement.
High Fermi velocities and small cyclotron masses in LaAlGe
We report quantum oscillation measurements of LaAlGe, a Lorentz-violating type-II Weyl semimetal with tilted Weyl cones.
Mesoscale and Nanoscale Physics Materials Science
Precision test of statistical dynamics with state-to-state ultracold chemistry
Chemical reactions represent a class of quantum problems that challenge both the current theoretical understanding and computational capabilities.
Chemical Physics Atomic Physics Quantum Physics
Deep Learning for Instance Retrieval: A Survey
In recent years a vast amount of visual content has been generated and shared from many fields, such as social media platforms, medical imaging, and robotics.
Train a One-Million-Way Instance Classifier for Unsupervised Visual Representation Learning
However, scaling up the classification task from thousands of semantic labels to millions of instance labels brings specific challenges including 1) the large-scale softmax computation; 2) the slow convergence due to the infrequent visiting of instance samples; and 3) the massive number of negative classes that can be noisy.
Hyperbolic Geometry is Not Necessary: Lightweight Euclidean-Based Models for Low-Dimensional Knowledge Graph Embeddings
Recent knowledge graph embedding (KGE) models based on hyperbolic geometry have shown great potential in a low-dimensional embedding space.
Single Cell Transcriptome Research in Human Placenta
Human placenta is a complex and heterogeneous organ interfacing between the mother and the fetus that supports fetal development.
Integrating Information Theory and Adversarial Learning for Cross-modal Retrieval
Moreover, feature encoders (as a generator) project uni-modal features into a commonly shared space and attempt to fool the discriminator by maximizing its output information entropy.
A Novel Binocular Eye-Tracking SystemWith Stereo Stimuli for 3D Gaze Estimation
However, most current eye trackers focus on 2D point of gaze (PoG) estimation and cannot provide accurate gaze depth. Concerning future applications such as HCI with 3D displays, we propose a novel binocular eye tracking device with stereo stimuli to provide highly accurate 3D PoG estimation.
FNAS: Uncertainty-Aware Fast Neural Architecture Search
Further, an architecture knowledge pool together with a block similarity function is proposed to utilize parameter knowledge and reduces the searching time by 2 times.
Curvature Graph Neural Network
And we propose Curvature Graph Neural Network (CGNN), which effectively improves the adaptive locality ability of GNNs by leveraging the structural property of graph curvature.
Communication Efficient SGD via Gradient Sampling With Bayes Prior
Different from all of them, we regard large and small gradients selection as the exploitation and exploration of gradient information, respectively.
Real-time Keypoints Detection for Autonomous Recovery of the Unmanned Ground Vehicle
UGV-KPNet is computationally efficient with a small number of parameters and provides pixel-level accurate keypoints detection results in real-time.
Unified Regularity Measures for Sample-wise Learning and Generalization
Fundamental machine learning theory shows that different samples contribute unequally both in learning and testing processes.
Iterative Self-consistent Parallel Magnetic Resonance Imaging Reconstruction based on Nonlocal Low-Rank Regularization
Recent methods have exploited the nonlocal self-similarity (NSS) of images by imposing nonlocal low-rankness of similar patches to achieve a superior performance.
Spatio-temporal Parking Behaviour Forecasting and Analysis Before and During COVID-19
Parking demand forecasting and behaviour analysis have received increasing attention in recent years because of their critical role in mitigating traffic congestion and understanding travel behaviours.
LDC-VAE: A Latent Distribution Consistency Approach to Variational AutoEncoders
Variational autoencoders (VAEs), as an important aspect of generative models, have received a lot of research interests and reached many successful applications.
The $f$-Divergence Reinforcement Learning Framework
In FRL, the policy evaluation and policy improvement phases are simultaneously performed by minimizing the $f$-divergence between the learning policy and sampling policy, which is distinct from conventional DRL algorithms that aim to maximize the expected cumulative rewards.
Switchable K-Class Hyperplanes for Noise-Robust Representation Learning
When collaborated with the popular ArcFace on million-level data representation learning, we found that the switchable manner in SKH can effectively eliminate the gradient conflict generated by real-world label noise on a single K-class hyperplane.
UniNet: Unified Architecture Search with Convolution, Transformer, and MLP
Recently, transformer and multi-layer perceptron (MLP) architectures have achieved impressive results on various vision tasks.
Ranked #239 on
Image Classification
on ImageNet
Self-Slimming Vision Transformer
Specifically, we first design a novel Token Slimming Module (TSM), which can boost the inference efficiency of ViTs by dynamic token aggregation.
RelationRS: Relationship Representation Network for Object Detection in Aerial Images
To address these issues, we propose a relationship representation network for object detection in aerial images (RelationRS): 1) Firstly, multi-scale features are fused and enhanced by a dual relationship module (DRM) with conditional convolution.
Knowledge-driven Site Selection via Urban Knowledge Graph
Specifically, motivated by distilled knowledge and rich semantics in KG, we firstly construct an urban KG (UrbanKG) with cities' key elements and semantic relationships captured.
SOM-NCSCM : An Efficient Neural Chinese Sentence Compression Model Enhanced with Self-Organizing Map
Sentence Compression (SC), which aims to shorten sentences while retaining important words that express the essential meanings, has been studied for many years in many languages, especially in English.
Spatio-Temporal Urban Knowledge Graph Enabled Mobility Prediction
Further, a complex embedding model with elaborately designed scoring functions is proposed to measure the plausibility of facts in STKG to solve the knowledge graph completion problem, which considers temporal dynamics of the mobility patterns and utilizes PoI categories as the auxiliary information and background knowledge.
INTERN: A New Learning Paradigm Towards General Vision
Enormous waves of technological innovations over the past several years, marked by the advances in AI technologies, are profoundly reshaping the industry and the society.
Learning by Active Forgetting for Neural Networks
This paper presents a learning model by active forgetting mechanism with artificial neural networks.
Reviewing continual learning from the perspective of human-level intelligence
Different from previous reviews that mainly focus on the catastrophic forgetting phenomenon in CL, this paper surveys CL from a more macroscopic perspective based on the Stability Versus Plasticity mechanism.
Arbitrary Virtual Try-On Network: Characteristics Preservation and Trade-off between Body and Clothing
Based on this dataset, we then propose the Arbitrary Virtual Try-On Network (AVTON) that is utilized for all-type clothes, which can synthesize realistic try-on images by preserving and trading off characteristics of the target clothes and the reference person.
A Bayesian Model for Online Activity Sample Sizes
Given observations on the number of unique users participating in an initial period, we present a simple but novel Bayesian method for predicting the number of additional individuals who will participate during a subsequent period.
Optimization of RIS Configurations for Multiple-RIS-Aided mmWave Positioning Systems based on CRLB Analysis
Reconfigurable intelligent surface (RIS) is a promising technology for future millimeter-wave (mmWave) communication systems.
Overcome Anterograde Forgetting with Cycled Memory Networks
This work proposes a general framework named Cycled Memory Networks (CMN) to address the anterograde forgetting in neural networks for lifelong learning.
Ghost-dil-NetVLAD: A Lightweight Neural Network for Visual Place Recognition
Visual place recognition (VPR) is a challenging task with the unbalance between enormous computational cost and high recognition performance.
Swift and Sure: Hardness-aware Contrastive Learning for Low-dimensional Knowledge Graph Embeddings
Knowledge graph embedding (KGE) has shown great potential in automatic knowledge graph (KG) completion and knowledge-driven tasks.
Pedestrian Dead Reckoning System using Quasi-static Magnetic Field Detection
Kalman filter-based Inertial Navigation System (INS) is a reliable and efficient method to estimate the position of a pedestrian indoors.
Rectifying the Data Bias in Knowledge Distillation
In this paper, we first quantitatively define the uniformity of the sampled data for training, providing a unified view for methods that learn from biased data.
Ranked #1 on
Face Verification
on IJB-C
(training dataset metric)
Meta Knowledge Distillation
Recent studies pointed out that knowledge distillation (KD) suffers from two degradation problems, the teacher-student gap and the incompatibility with strong data augmentations, making it not applicable to training state-of-the-art models, which are trained with advanced augmentations.
Ranked #135 on
Image Classification
on ImageNet
Dual-Domain Reconstruction Networks with V-Net and K-Net for fast MRI
Purpose: To introduce a dual-domain reconstruction network with V-Net and K-Net for accurate MR image reconstruction from undersampled k-space data.
HoVer-Trans: Anatomy-aware HoVer-Transformer for ROI-free Breast Cancer Diagnosis in Ultrasound Images
In this study, we propose a novel ROI-free model for breast cancer diagnosis in ultrasound images with interpretable feature representations.
Enhancing Quality of Pose-varied Face Restoration with Local Weak Feature Sensing and GAN Prior
In the asymmetric codec, we adopt a mixed multi-path residual block (MMRB) to gradually extract weak texture features of input images, which can better preserve the original facial features and avoid excessive fantasy.
DeStripe: A Self2Self Spatio-Spectral Graph Neural Network with Unfolded Hessian for Stripe Artifact Removal in Light-sheet Microscopy
Light-sheet fluorescence microscopy (LSFM) is a cutting-edge volumetric imaging technique that allows for three-dimensional imaging of mesoscopic samples with decoupled illumination and detection paths.
Rethinking Robust Representation Learning Under Fine-grained Noisy Faces
To better understand this, we reformulate the noise type of each class in a more fine-grained manner as N-identities|K^C-clusters.
Towards Robust Face Recognition with Comprehensive Search
To eliminate the bias of single-aspect research and provide an overall understanding of the face recognition model design, we first carefully design the search space for each aspect, then a comprehensive search method is introduced to jointly search optimal data cleaning, architecture, and loss function design.
SOM-Net: Unrolling the Subspace-based Optimization for Solving Full-wave Inverse Scattering Problems
The final output of the SOM-Net is the full predicted induced current, from which the scattered field and the permittivity image can also be deduced analytically.
EEG-based Emotion Recognition via Efficient Convolutional Neural Network and Contrastive Learning
To achieve a simple and effective model with supervised learning, we propose an efficient CNN and contrastive learning (ECNN-C) method for EEG-based emotion recognition.
DiffGAR: Model-Agnostic Restoration from Generative Artifacts Using Image-to-Image Diffusion Models
In this work, we first design a group of mechanisms to simulate generative artifacts of popular generators (i. e., GANs, autoregressive models, and diffusion models), given real images.
PolyBuilding: Polygon Transformer for End-to-End Building Extraction
Given a set of polygon queries, the model learns the relations among them and encodes context information from the image to predict the final set of building polygons with fixed vertex numbers.
Channel Tracking for RIS-aided mmWave Communications Under High Mobility Scenarios
The emerging reconfigurable intelligent surface (RIS) technology is promising for applications in the millimeter wave (mmWave) communication systems to effectively compensate for propagation loss or tackle the blockage issue.
Real-World Image Super Resolution via Unsupervised Bi-directional Cycle Domain Transfer Learning based Generative Adversarial Network
First, the UBCDTN is able to produce an approximated real-like LR image through transferring the LR image from an artificially degraded domain to the real-world LR image domain.
Semantic Encoder Guided Generative Adversarial Face Ultra-Resolution Network
In this paper, we propose a novel face super-resolution method, namely Semantic Encoder guided Generative Adversarial Face Ultra-Resolution Network (SEGA-FURN) to ultra-resolve an unaligned tiny LR face image to its HR counterpart with multiple ultra-upscaling factors (e. g., 4x and 8x).
Unsupervised Domain Adaptation GAN Inversion for Image Editing
In this paper, we resolve this problem by introducing Unsupervised Domain Adaptation (UDA) into the Inversion process, namely UDA-Inversion, for both high-quality and low-quality image inversion and editing.
