Search Results for author:
Found 149 papers, 81 papers with code
FAF: A Feature-Adaptive Framework for Few-Shot Time Series Forecasting
Meanwhile, the TSM is trained to capture diverse local dynamics through multiple functional regions, each of which learns specific features from individual tasks.
FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistency
To effectively exploit temporal information in robotic manipulation, we propose FreqPolicy, a novel approach that first imposes frequency consistency constraints on flow-based visuomotor policies.
RoboSwap: A GAN-driven Video Diffusion Framework For Unsupervised Robot Arm Swapping
Our experiments demonstrate that RoboSwap outperforms state-of-the-art video and image editing models on three benchmarks in terms of both structural coherence and motion consistency, thereby offering a robust solution for generating reliable, cross-embodiment data in robotic learning.
FreeScene: Mixed Graph Diffusion for 3D Scene Synthesis from Free Prompts
Controllability plays a crucial role in the practical applications of 3D indoor scene synthesis.
A Survey on 3D Reconstruction Techniques in Plant Phenotyping: From Classical Methods to Neural Radiance Fields (NeRF), 3D Gaussian Splatting (3DGS), and Beyond
Through this review, we aim to provide insights into how these diverse 3D reconstruction techniques can be effectively leveraged for automated and high-throughput plant phenotyping, contributing to the next generation of agricultural technology.
Fast Autoregressive Models for Continuous Latent Generation
Autoregressive models have demonstrated remarkable success in sequential data generation, particularly in NLP, but their extension to continuous-domain image generation presents significant challenges.
VLLFL: A Vision-Language Model Based Lightweight Federated Learning Framework for Smart Agriculture
By training a compact prompt generator to boost the performance of the VLM deployed across different farms, VLLFL preserves privacy while reducing communication overhead.
Real-Time Roadway Obstacle Detection for Electric Scooters Using Deep Learning and Multi-Sensor Fusion
This study introduces a novel ground obstacle detection system for e-scooters, integrating an RGB camera, and a depth camera to enhance real-time road hazard detection.
Detecting Plant VOC Traces Using Indoor Air Quality Sensors
In the era of growing interest in healthy buildings and smart homes, the importance of sustainable, health conscious indoor environments is paramount.
Multimodal Data Integration for Sustainable Indoor Gardening: Tracking Anyplant with Time Series Foundation Model
Unlike previous approaches, this framework combines RGB imagery, plant phenotyping data, and environmental factors such as temperature and humidity, to predict plant water stress in a controlled growth environment.
Selective Complementary Feature Fusion and Modal Feature Compression Interaction for Brain Tumor Segmentation
In order to solve the above problems, we propose a noval complementary feature compression interaction network (CFCI-Net), which realizes the complementary fusion and compression interaction of multi-modal feature information with an efficient mode fusion strategy.
DesignDiffusion: High-Quality Text-to-Design Image Generation with Diffusion Models
In this paper, we present DesignDiffusion, a simple yet effective framework for the novel task of synthesizing design images from textual descriptions.
ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation
In this paper, we introduce the Anonymous Region Transformer (ART), which facilitates the direct generation of variable multi-layer transparent images based on a global text prompt and an anonymous region layout.
Diffusion Models without Classifier-free Guidance
This paper presents Model-guidance (MG), a novel objective for training diffusion model that addresses and removes of the commonly used Classifier-free guidance (CFG).
Ranked #12 on
Image Generation
on ImageNet 256x256
Improved YOLOv7 model for insulator defect detection
Specifically, there is a 1. 6% advancement in mAP_0. 5, a corresponding 1. 6% enhancement in mAP_0. 5:0. 95, a 1. 3% elevation in precision, and a 1% increase in recall.
Artificial Intelligence Approaches for Anti-Addiction Drug Discovery
Drug addiction is a complex and pervasive global challenge that continues to pose significant public health concerns.
TeLL-Drive: Enhancing Autonomous Driving with Teacher LLM-Guided Deep Reinforcement Learning
To address these limitations, we propose TeLL-Drive, a hybrid framework that integrates a Teacher LLM to guide an attention-based Student DRL policy.
A Simple Aerial Detection Baseline of Multimodal Language Models
In this paper, we present a simple baseline for applying MLMs to aerial detection for the first time, named LMMRotate.
SmartEraser: Remove Anything from Images using Masked-Region Guidance
This paradigm retains the masked region in the input, using it as guidance for the removal process.
Wavelet and Prototype Augmented Query-based Transformer for Pixel-level Surface Defect Detection
Specifically, a set of dynamic queries for mask prediction is updated through the dual-domain transformer decoder.
Experimental Study of RCS Diversity with Novel No-divergent OAM Beams
The findings reveal that the novel OAM beams produce significant azimuthal RCS diversity, providing a new approach for the detection of weak and small targets. This study not only reveals the RCS diversity phenomenon based on novel OAM beams of different modes but also addresses the issue of energy divergence that hinders traditional OAM beams in long-range detection applications.
CodeV: Issue Resolving with Visual Data
Large Language Models (LLMs) have advanced rapidly in recent years, with their applications in software engineering expanding to more complex repository-level tasks.
Category-Specific Topological Learning of Metal-Organic Frameworks
Metal-organic frameworks (MOFs) are porous, crystalline materials with high surface area, adjustable porosity, and structural tunability, making them ideal for diverse applications.
Protecting Confidentiality, Privacy and Integrity in Collaborative Learning
During this collaboration, however, dataset owners and model owners want to protect the confidentiality of their respective assets (i. e., datasets, models and training code), with the dataset owners also caring about the privacy of individual users whose data is in their datasets.
Structured 3D Latents for Scalable and Versatile 3D Generation
We introduce a novel 3D generation method for versatile and high-quality 3D asset creation.
CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
Unlike previous works that directly repurpose VLM for action prediction by simple action quantization, we propose a omponentized VLA architecture that has a specialized action module conditioned on VLM output.
A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics
Despite the many challenges associated with combining machine learning technology with robotics, robot learning remains one of the most promising directions for enhancing the capabilities of robots.
A Comparative Study of Deep Reinforcement Learning for Crop Production Management
Our results indicate that PPO outperforms DQN in fertilization and irrigation tasks, while DQN excels in the mixed management task.
Integrating Reinforcement Learning and Large Language Models for Crop Production Process Management Optimization and Control through A New Knowledge-Based Deep Learning Paradigm
This paper systematically examines how the integration of RL and LLMs into crop management decision support systems (DSSs) can drive advancements in agricultural practice.
SynChart: Synthesizing Charts from Language Models
With the release of GPT-4V(O), its use in generating pseudo labels for multi-modality tasks has gained significant popularity.
SWE-bench-java: A GitHub Issue Resolving Benchmark for Java
GitHub issue resolving is a critical task in software engineering, recently gaining significant attention in both industry and academia.
Logic Distillation: Learning from Code Function by Function for Planning and Decision-making
Subsequently, based on the function base, LD fine-tunes S-LLMs to learn the logic employed by L-LLMs in planning and decision-making.
DepGAN: Leveraging Depth Maps for Handling Occlusions and Transparency in Image Composition
In this work, we propose DepGAN, a Generative Adversarial Network that utilizes depth maps and alpha channels to rectify inaccurate occlusions and enhance transparency effects in image composition.
RodinHD: High-Fidelity 3D Avatar Generation with Diffusion Models
We present RodinHD, which can generate high-fidelity 3D avatars from a portrait image.
Communication-Efficient MARL for Platoon Stability and Energy-efficiency Co-optimization in Cooperative Adaptive Cruise Control of CAVs
Cooperative adaptive cruise control (CACC) has been recognized as a fundamental function of autonomous driving, in which platoon stability and energy efficiency are outstanding challenges that are difficult to accommodate in real-world operations.
Scaling the Codebook Size of VQGAN to 100,000 with a Utilization Rate of 99%
We demonstrate the superior performance of our model over its counterparts across a variety of tasks, including image reconstruction, image classification, auto-regressive image generation using GPT, and image creation with diffusion- and flow-based generative models.
Ranked #12 on
Image Reconstruction
on ImageNet
Improving Large Models with Small models: Lower Costs and Better Performance
On the other hand, certain tasks can be broken down into multiple subtasks, some of which can be completed without powerful capabilities.
FontStudio: Shape-Adaptive Diffusion Model for Coherent and Consistent Font Effect Generation
This task essentially requires generating coherent and consistent visual content within the confines of a font-shaped canvas, as opposed to a traditional rectangular canvas.
CodeR: Issue Resolving with Multi-Agent and Task Graphs
GitHub issue resolving recently has attracted significant attention from academia and industry.
Ranked #1 on
Bug fixing
on SWE-bench-lite
Performance Evaluation of Real-Time Object Detection for Electric Scooters
Electric scooters (e-scooters) have rapidly emerged as a popular mode of transportation in urban areas, yet they pose significant safety challenges.
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
We introduce phi-3-mini, a 3. 8 billion parameter language model trained on 3. 3 trillion tokens, whose overall performance, as measured by both academic benchmarks and internal testing, rivals that of models such as Mixtral 8x7B and GPT-3. 5 (e. g., phi-3-mini achieves 69% on MMLU and 8. 38 on MT-bench), despite being small enough to be deployed on a phone.
Ranked #5 on
MMR total
on MRR-Benchmark
(using extra training data)
WcDT: World-centric Diffusion Transformer for Traffic Scene Generation
To enhance the scene diversity and stochasticity, the historical trajectory data is first preprocessed into "Agent Move Statement" and encoded into latent space using Denoising Diffusion Probabilistic Models (DDPM) enhanced with Diffusion with Transformer (DiT) blocks.
GaussianCube: A Structured and Explicit Radiance Representation for 3D Generative Modeling
We introduce a radiance representation that is both structured and fully explicit and thus greatly facilitates 3D generative modeling.
CodeS: Natural Language to Code Repository via Multi-Layer Sketch
For feedback-based evaluation, we develop a VSCode plugin for CodeS and engage 30 participants in conducting empirical studies.
Simplified Diffusion Schrödinger Bridge
This paper introduces a novel theoretical simplification of the Diffusion Schr\"odinger Bridge (DSB) that facilitates its unification with Score-based Generative Models (SGMs), addressing the limitations of DSB in complex data generation and enabling faster convergence and enhanced performance.
SiGNN: A Spike-induced Graph Neural Network for Dynamic Graph Representation Learning
In the domain of dynamic graph representation learning (DGRL), the efficient and comprehensive capture of temporal evolution within real-world networks is crucial.
Performance Evaluation of Semi-supervised Learning Frameworks for Multi-Class Weed Detection
In this study, we assess the effectiveness of a semi-supervised learning framework for multi-class weed detection, employing two well-known object detection frameworks, namely FCOS and Faster-RCNN.
Drug Resistance Predictions Based on a Directed Flag Transformer
CAPTURE combines a comprehensive mutation analysis with a resistance prediction module based on DFFormer-seq, which is a novel ensemble model that leverages a new Directed Flag Transformer and sequence embeddings from the protein and small-molecule-large-language models.
EPSD: Early Pruning with Self-Distillation for Efficient Model Compression
Instead of a simple combination of pruning and SD, EPSD enables the pruned network to favor SD by keeping more distillable weights before training to ensure better distillation of the pruned network.
CCA: Collaborative Competitive Agents for Image Editing
This paper presents a novel generative model, Collaborative Competitive Agents (CCA), which leverages the capabilities of multiple Large Language Models (LLMs) based agents to execute complex tasks.
Back-stepping Experience Replay with Application to Model-free Reinforcement Learning for a Soft Snake Robot
In this paper, we propose a novel technique, Back-stepping Experience Replay (BER), that is compatible with arbitrary off-policy reinforcement learning (RL) algorithms.
VolumeDiffusion: Flexible Text-to-3D Generation with Efficient Volumetric Encoder
The 3D volumes are then trained on a diffusion model for text-to-3D generation using a 3D U-Net.
Customize-It-3D: High-Quality 3D Creation from A Single Image Using Subject-Specific Knowledge Prior
In this paper, we present a novel two-stage approach that fully utilizes the information provided by the reference image to establish a customized knowledge prior for image-to-3D generation.
COLE: A Hierarchical Generation Framework for Multi-Layered and Editable Graphic Design
Our COLE system comprises multiple fine-tuned Large Language Models (LLMs), Large Multimodal Models (LMMs), and Diffusion Models (DMs), each specifically tailored for design-aware layer-wise captioning, layout planning, reasoning, and the task of generating images and text.
PersonMAE: Person Re-Identification Pre-Training with Masked AutoEncoders
Pre-training is playing an increasingly important role in learning generic feature representation for Person Re-identification (ReID).
SoybeanNet: Transformer-Based Convolutional Neural Network for Soybean Pod Counting from Unmanned Aerial Vehicle (UAV) Images
Soybeans are a critical source of food, protein and oil, and thus have received extensive research aimed at enhancing their yield, refining cultivation practices, and advancing soybean breeding techniques.
Improving Vision Anomaly Detection with the Guidance of Language Modality
To learn a more compact latent space for the vision anomaly detector, CMLE learns a correlation structure matrix from the language modality, and then the latent space of vision modality will be learned with the guidance of the matrix.
InstructDiffusion: A Generalist Modeling Interface for Vision Tasks
We present InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions.
Large Language Models and Foundation Models in Smart Agriculture: Basics, Opportunities, and Challenges
These models are trained on a large amount of data from multiple domains and modalities.
Communication-Efficient Decentralized Multi-Agent Reinforcement Learning for Cooperative Adaptive Cruise Control
Connected and autonomous vehicles (CAVs) promise next-gen transportation systems with enhanced safety, energy efficiency, and sustainability.
Label-Efficient Learning in Agriculture: A Comprehensive Review
In addition, a systematic review of various agricultural applications exploiting these label-efficient algorithms, such as precision agriculture, plant phenotyping, and postharvest quality assessment, is presented.
Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior
In this work, we investigate the problem of creating high-fidelity 3D content from only a single image.
CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive Learning
Our framework, termed as domain-aware sign language retrieval via Cross-lingual Contrastive learning or CiCo for short, outperforms the pioneering method by large margins on various datasets, e. g., +22. 4 T2V and +28. 0 V2T R@1 improvements on How2Sign dataset, and +13. 7 T2V and +17. 1 V2T R@1 improvements on PHOENIX-2014T dataset.
Ranked #1 on
Sign Language Retrieval
on CSL-Daily
IRGen: Generative Modeling for Image Retrieval
While generative modeling has become prevalent across numerous research fields, its integration into the realm of image retrieval remains largely unexplored and underjustified.
Efficient Diffusion Training via Min-SNR Weighting Strategy
Denoising diffusion models have been a mainstream approach for image generation, however, training these models often suffers from slow convergence.
Ranked #26 on
Image Generation
on ImageNet 256x256
O2RNet: Occluder-Occludee Relational Network for Robust Apple Detection in Clustered Orchard Environments
One key technology to fully enable efficient automated harvesting is accurate and robust apple detection, which is challenging due to complex orchard environments that involve varying lighting conditions and foliage/branch occlusions.
Hyneter: Hybrid Network Transformer for Object Detection
In this paper, we point out that the essential differences between CNN-based and Transformer-based detectors, which cause the worse performance of small objects in Transformer-based methods, are the gap between local information and global dependencies in feature extraction and propagation.
Improving CLIP Fine-tuning Performance
Experiments suggest that the feature map distillation approach significantly boosts the fine-tuning performance of CLIP models on several typical downstream vision tasks.
FreeEnricher: Enriching Face Landmarks without Additional Cost
To evaluate our method, we manually label the dense landmarks on 300W testset.
Ranked #1 on
Face Alignment
on 300W
MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptation
In this work, we propose an ID-preserving talking head generation framework, which advances previous methods in two aspects.
Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion
This paper presents a 3D generative model that uses diffusion models to automatically generate 3D digital avatars represented as neural radiance fields.
CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet
Recent studies have shown that CLIP has achieved remarkable success in performing zero-shot inference while its fine-tuning performance is not satisfactory.
X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion
We demonstrate for the first time that using a text2image model to generate images or zero-shot recognition model to filter noisily crawled images for different object categories is a feasible way to make Copy-Paste truly scalable.
Ranked #8 on
Instance Segmentation
on LVIS v1.0 val
Paint by Example: Exemplar-based Image Editing with Diffusion Models
Language-guided image editing has achieved great success recently.
SinDiffusion: Learning a Diffusion Model from a Single Natural Image
We present SinDiffusion, leveraging denoising diffusion models to capture internal distribution of patches from a single natural image.
Ranked #1 on
Image Generation
on Places50
Deep Data Augmentation for Weed Recognition Enhancement: A Diffusion Probabilistic Model and Transfer Learning Based Approach
In this paper, we present the first work of applying diffusion probabilistic models (also known as diffusion models) to generate high-quality synthetic weed images based on transfer learning.
DigiFace-1M: 1 Million Digital Face Images for Face Recognition
Such models are trained on large-scale datasets that contain millions of real human face images collected from the internet.
Ranked #2 on
Synthetic Face Recognition
on CPLFW
(Accuracy metric)
3DFaceShop: Explicitly Controllable 3D-Aware Portrait Generation
In contrast to the traditional avatar creation pipeline which is a costly process, contemporary generative approaches directly learn the data distribution from photographs.
MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining
Second, masked self-distillation is also consistent with vision-language contrastive from the perspective of training objective as both utilize the visual encoder for feature aligning, and thus is able to learn local semantics getting indirect supervision from the language.
Bootstrapped Masked Autoencoders for Vision BERT Pretraining
The first design is motivated by the observation that using a pretrained MAE to extract the features as the BERT prediction target for masked tokens can achieve better pretraining performance.
I^2R-Net: Intra- and Inter-Human Relation Network for Multi-Person Pose Estimation
In this paper, we present the Intra- and Inter-Human Relation Networks (I^2R-Net) for Multi-Person Pose Estimation.
Ranked #2 on
Multi-Person Pose Estimation
on OCHuman
Robust Meta-learning with Sampling Noise and Label Noise via Eigen-Reptile
Moreover, when handling the data with noisy labels, the meta-learner could be extremely sensitive to label noise on a corrupted dataset.
Improved Vector Quantized Diffusion Models
When trained on ImageNet, we dramatically improve the FID score from 11. 89 to 4. 83, demonstrating the superiority of our proposed techniques.
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 #4 on
Instance Segmentation
on COCO test-dev
(using extra training data)
Pretraining is All You Need for Image-to-Image Translation
We propose to use pretraining to boost general image-to-image translation.
Ranked #1 on
Sketch-to-Image Translation
on COCO-Stuff
Real-Time Neural Character Rendering with Pose-Guided Multiplane Images
We propose pose-guided multiplane image (MPI) synthesis which can render an animatable character in real scenes with photorealistic quality.
Generative Adversarial Networks for Image Augmentation in Agriculture: A Systematic Review
In agricultural image analysis, optimal model performance is keenly pursued for better fulfilling visual recognition tasks (e. g., image classification, segmentation, object detection and localization), in the presence of challenges with biological variability and unstructured environments.
Large-Scale Pre-training for Person Re-identification with Noisy Labels
Since theses ID labels automatically derived from tracklets inevitably contain noises, we develop a large-scale Pre-training framework utilizing Noisy Labels (PNL), which consists of three learning modules: supervised Re-ID learning, prototype-based contrastive learning, and label-guided contrastive learning.
Ranked #8 on
Person Re-Identification
on CUHK03
Semi-Supervised Image-to-Image Translation using Latent Space Mapping
Thanks to the low dimensional feature space, it is easier to find the desired mapping function, resulting in improved quality of translation results as well as the stability of the translation model.
Protecting Celebrities from DeepFake with Identity Consistency Transformer
In this work we propose Identity Consistency Transformer, a novel face forgery detection method that focuses on high-level semantics, specifically identity information, and detecting a suspect face by finding identity inconsistency in inner and outer face regions.
Machine learning analysis of cocaine addiction informed by DAT, SERT, and NET-based interactome networks
Cocaine dependence is neurological and involves many interacting proteins in the interactome.
StyleSwin: Transformer-based GAN for High-resolution Image Generation
To this end, we believe that local attention is crucial to strike the balance between computational efficiency and modeling capacity.
Ranked #1 on
Image Generation
on CelebA 256x256
(FID metric)
General Facial Representation Learning in a Visual-Linguistic Manner
In this paper, we study the transfer performance of pre-trained models on face analysis tasks and introduce a framework, called FaRL, for general Facial Representation Learning in a visual-linguistic manner.
Ranked #1 on
Face Parsing
on CelebAMask-HQ
(using extra training data)
Vector Quantized Diffusion Model for Text-to-Image Synthesis
Our experiments indicate that the VQ-Diffusion model with the reparameterization is fifteen times faster than traditional AR methods while achieving a better image quality.
Ranked #2 on
Text-to-Image Generation
on Oxford 102 Flowers
(using extra training data)
PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers
This paper explores a better prediction target for BERT pre-training of vision transformers.
Multi-agent Reinforcement Learning for Cooperative Lane Changing of Connected and Autonomous Vehicles in Mixed Traffic
In this paper, we formulate the lane-changing decision making of multiple AVs in a mixed-traffic highway environment as a multi-agent reinforcement learning (MARL) problem, where each AV makes lane-changing decisions based on the motions of both neighboring AVs and HDVs.
Performance Evaluation of Deep Transfer Learning on Multiclass Identification of Common Weed Species in Cotton Production Systems
Precision weed management offers a promising solution for sustainable cropping systems through the use of chemical-reduced/non-chemical robotic weeding techniques, which apply suitable control tactics to individual weeds.
Proteome-informed machine learning studies of cocaine addiction
Cocaine addiction accounts for a large portion of substance use disorders and threatens millions of lives worldwide.
Exploring Temporal Coherence for More General Video Face Forgery Detection
The first stage is a fully temporal convolution network (FTCN).
Ranked #4 on
DeepFake Detection
on FakeAVCeleb
Dual Path Learning for Domain Adaptation of Semantic Segmentation
In this paper, based on the observation that domain adaptation frameworks performed in the source and target domain are almost complementary in terms of image translation and SSL, we propose a novel dual path learning (DPL) framework to alleviate visual inconsistency.
Instance-wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translation
In this paper, we uncover that the negative examples play a critical role in the performance of contrastive learning for image translation.
CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows
By further pretraining on the larger dataset ImageNet-21K, we achieve 87. 5% Top-1 accuracy on ImageNet-1K and high segmentation performance on ADE20K with 55. 7 mIoU.
Ranked #27 on
Semantic Segmentation
on ADE20K val
Robust Mutual Learning for Semi-supervised Semantic Segmentation
The proposed robust mutual learning demonstrates state-of-the-art performance on semantic segmentation in low-data regime.
Deep Multi-agent Reinforcement Learning for Highway On-Ramp Merging in Mixed Traffic
On-ramp merging is a challenging task for autonomous vehicles (AVs), especially in mixed traffic where AVs coexist with human-driven vehicles (HDVs).
High-Fidelity and Arbitrary Face Editing
However, we observe that the generator tends to find a tricky way to hide information from the original image to satisfy the constraint of cycle consistency, making it impossible to maintain the rich details (e. g., wrinkles and moles) of non-editing areas.
Control Distance IoU and Control Distance IoU Loss Function for Better Bounding Box Regression
In this paper, we first present an evaluation-feedback module, which is proposed to consist of evaluation system and feedback mechanism.
Style-based Point Generator with Adversarial Rendering for Point Cloud Completion
In this paper, we proposed a novel Style-based Point Generator with Adversarial Rendering (SpareNet) for point cloud completion.
Ranked #1 on
Point Cloud Completion
on ShapeNet
(Earth Mover's Distance metric)
Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation
In this paper, we rely on representative prototypes, the feature centroids of classes, to address the two issues for unsupervised domain adaptation.
Ranked #10 on
Semantic Segmentation
on GTAV-to-Cityscapes Labels
Robust Meta-learning with Noise via Eigen-Reptile
In particular, we first cast the meta-overfitting problem (overfitting on sampling and label noise) as a gradient noise problem since few available samples cause meta-learner to overfit on existing examples (clean or corrupted) of an individual task at every gradient step.
Unsupervised Pre-training for Person Re-identification
In this paper, we present a large scale unlabeled person re-identification (Re-ID) dataset "LUPerson" and make the first attempt of performing unsupervised pre-training for improving the generalization ability of the learned person Re-ID feature representation.
Ranked #1 on
Person Re-Identification
on Market-1501
(mAP metric)
Identity-Driven DeepFake Detection
Our approach takes as input the suspect image/video as well as the target identity information (a reference image or video).
Evidence of topological nodal lines and surface states in the centrosymmetric superconductor SnTaS2
Utilizing angle-resolved photoemission spectroscopy and first-principles calculations, here, we demonstrate the existence of topological nodal-line states and drumheadlike surface states in centrosymmetric superconductor SnTaS2, which is a type-II superconductor with a critical transition temperature of about 3 K. The valence bands from Ta 5d orbitals and the conduction bands from Sn 5p orbitals cross each other, forming two nodal lines in the vicinity of the Fermi energy without the inclusion of spin-orbit coupling (SOC), protected by the spatial-inversion symmetry and time-reversal symmetry.
Superconductivity
CoCosNet v2: Full-Resolution Correspondence Learning for Image Translation
We present the full-resolution correspondence learning for cross-domain images, which aids image translation.
PowerNet: Multi-agent Deep Reinforcement Learning for Scalable Powergrid Control
Specifically, we consider the decentralized inverter-based secondary voltage control problem in distributed generators (DGs), which is first formulated as a cooperative multi-agent reinforcement learning (MARL) problem.
Deep Reinforcement Learning
Multi-agent Reinforcement Learning
+2
Learnable Sampling 3D Convolution for Video Enhancement and Action Recognition
A key challenge in video enhancement and action recognition is to fuse useful information from neighboring frames.
GreedyFool: Distortion-Aware Sparse Adversarial Attack
Sparse adversarial samples are a special branch of adversarial samples that can fool the target model by only perturbing a few pixels.
SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving
We open-source the SMARTS platform and the associated benchmark tasks and evaluation metrics to encourage and empower research on multi-agent learning for autonomous driving.
Old Photo Restoration via Deep Latent Space Translation
Unlike conventional restoration tasks that can be solved through supervised learning, the degradation in real photos is complex and the domain gap between synthetic images and real old photos makes the network fail to generalize.
Unified Representation Learning for Cross Model Compatibility
We propose a unified representation learning framework to address the Cross Model Compatibility (CMC) problem in the context of visual search applications.
PriorGAN: Real Data Prior for Generative Adversarial Nets
To address these two issues, we propose a novel prior that captures the whole real data distribution for GANs, which are called PriorGANs.
Cross-Task Transfer for Geotagged Audiovisual Aerial Scene Recognition
With the help of this dataset, we evaluate three proposed approaches for transferring the sound event knowledge to the aerial scene recognition task in a multimodal learning framework, and show the benefit of exploiting the audio information for the aerial scene recognition.
Disentangled and Controllable Face Image Generation via 3D Imitative-Contrastive Learning
Our method can also be used to embed real images into the disentangled latent space.
Deep 3D Portrait from a Single Image
We evaluate the accuracy of our method both in 3D and with pose manipulation tasks on 2D images.
Uncertainty Quantification for Hyperspectral Image Denoising Frameworks based on Low-rank Matrix Approximation
Sliding-window based low-rank matrix approximation (LRMA) is a technique widely used in hyperspectral images (HSIs) denoising or completion.
Bringing Old Photos Back to Life
Unlike conventional restoration tasks that can be solved through supervised learning, the degradation in real photos is complex and the domain gap between synthetic images and real old photos makes the network fail to generalize.
Cross-domain Correspondence Learning for Exemplar-based Image Translation
The output has the style (e. g., color, texture) in consistency with the semantically corresponding objects in the exemplar.
Ranked #1 on
Image-to-Image Translation
on ADE20K-Outdoor Labels-to-Photos
(FID metric)
Curved Buildings Reconstruction from Airborne LiDAR Data by Matching and Deforming Geometric Primitives
To this end, we propose a new framework for curved building reconstruction via assembling and deforming geometric primitives.
GIQA: Generated Image Quality Assessment
Generative adversarial networks (GANs) have achieved impressive results today, but not all generated images are perfect.
Online Semantic Exploration of Indoor Maps
In this paper we propose a method to extract an abstracted floor plan from typical grid maps using Bayesian reasoning.
Table-Top Scene Analysis Using Knowledge-Supervised MCMC
Our approach to generate scene graphs is probabilistic: Uncertainty in the object poses is addressed by a probabilistic sensor model that is embedded in a data driven MCMC process.
TCM-ICP: Transformation Compatibility Measure for Registering Multiple LIDAR Scans
In this work, we present an algorithm for registering multiple, overlapping LiDAR scans.
Face X-ray for More General Face Forgery Detection
For this reason, face X-ray provides an effective way for detecting forgery generated by most existing face manipulation algorithms.
FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping
We propose a novel attributes encoder for extracting multi-level target face attributes, and a new generator with carefully designed Adaptive Attentional Denormalization (AAD) layers to adaptively integrate the identity and the attributes for face synthesis.
Autonomous Driving using Safe Reinforcement Learning by Incorporating a Regret-based Human Lane-Changing Decision Model
The predicted decisions are incorporated in the safety constraints for reinforcement learning in training and in implementation.
Deep Exemplar-based Video Colorization
This paper presents the first end-to-end network for exemplar-based video colorization.
Face Parsing with RoI Tanh-Warping
It uses hierarchical local based method for inner facial components and global methods for outer facial components.
Mask-Guided Portrait Editing with Conditional GANs
Portrait editing is a popular subject in photo manipulation.
Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set
Recently, deep learning based 3D face reconstruction methods have shown promising results in both quality and efficiency. However, training deep neural networks typically requires a large volume of data, whereas face images with ground-truth 3D face shapes are scarce.
Ranked #3 on
3D Face Reconstruction
on Florence
(RMSE Cooperative metric)
WIDER Face and Pedestrian Challenge 2018: Methods and Results
This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian.
Exploring Hypergraph Representation on Face Anti-spoofing Beyond 2D Attacks
Face anti-spoofing plays a crucial role in protecting face recognition systems from various attacks.
A novel active learning framework for classification: using weighted rank aggregation to achieve multiple query criteria
The proposed method serves as a heuristic means to select high-value samples of high scalability and generality and is implemented through a three-step process: (1) the transformation of the sample selection to sample ranking and scoring, (2) the computation of the self-adaptive weights of each criterion, and (3) the weighted aggregation of each sample rank list.
Towards Open-Set Identity Preserving Face Synthesis
We then recombine the identity vector and the attribute vector to synthesize a new face of the subject with the extracted attribute.
CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training
Our approach models an image as a composition of label and latent attributes in a probabilistic model.
Supervised Transformer Network for Efficient Face Detection
For real-time performance, we run the cascaded network only on regions of interests produced from a boosting cascade face detector.
Ranked #5 on
Face Detection
on PASCAL Face
Neural Aggregation Network for Video Face Recognition
The network takes a face video or face image set of a person with a variable number of face images as its input, and produces a compact, fixed-dimension feature representation for recognition.
Ranked #3 on
Face Identification
on DroneSURF
Blessing of Dimensionality: High-Dimensional Feature and Its Efficient Compression for Face Verification
Making a high-dimensional (e. g., 100K-dim) feature for face recognition seems not a good idea because it will bring difficulties on consequent training, computation, and storage.
Ranked #9 on
Age-Invariant Face Recognition
on CACDVS
