Search Results for author:
Found 185 papers, 80 papers with code
TopoGAN: A Topology-Aware Generative Adversarial Network
We show in experiments that our method generates synthetic images with realistic topology.
New Threats against Object Detector with Non-local Block
The experiments show that the universal patches are able to mislead the detector with greater probabilities.
PLATO-KAG: Unsupervised Knowledge-Grounded Conversation via Joint Modeling
Large-scale conversation models are turning to leveraging external knowledge to improve the factual accuracy in response generation.
MentalGLM Series: Explainable Large Language Models for Mental Health Analysis on Chinese Social Media
The proposed models were evaluated on three downstream tasks and achieved better or comparable performance compared to deep learning models, generalized LLMs, and task fine-tuned LLMs.
Deeper Insights Without Updates: The Power of In-Context Learning Over Fine-Tuning
Fine-tuning and in-context learning (ICL) are two prevalent methods in imbuing large language models with task-specific knowledge.
Dynamic Diffusion Transformer
In addition, we design a Spatial-wise Dynamic Token (SDT) strategy to avoid redundant computation at unnecessary spatial locations.
AnyLogo: Symbiotic Subject-Driven Diffusion System with Gemini Status
Diffusion models have made compelling progress on facilitating high-throughput daily production.
RealisDance: Equip controllable character animation with realistic hands
2) The hands generated using the DWPose sequence are blurry and unrealistic.
RealisHuman: A Two-Stage Approach for Refining Malformed Human Parts in Generated Images
First, it generates realistic human parts, such as hands or faces, using the original malformed parts as references, ensuring consistent details with the original image.
LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs
The widespread adoption of cloud-based proprietary large language models (LLMs) has introduced significant challenges, including operational dependencies, privacy concerns, and the necessity of continuous internet connectivity.
MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing
Novel View Synthesis (NVS) and 3D generation have recently achieved prominent improvements.
A Generic Review of Integrating Artificial Intelligence in Cognitive Behavioral Therapy
Cognitive Behavioral Therapy (CBT) is a well-established intervention for mitigating psychological issues by modifying maladaptive cognitive and behavioral patterns.
MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence
Our approach utilizes autoregressive models for global narrative coherence, predicting sequences of visual tokens that are subsequently transformed into high-quality video frames through diffusion rendering.
Large-vocabulary forensic pathological analyses via prototypical cross-modal contrastive learning
Forensic pathology is critical in determining the cause and manner of death through post-mortem examinations, both macroscopic and microscopic.
Animate3D: Animating Any 3D Model with Multi-view Video Diffusion
The core idea is two-fold: 1) We propose a novel multi-view video diffusion model (MV-VDM) conditioned on multi-view renderings of the static 3D object, which is trained on our presented large-scale multi-view video dataset (MV-Video).
Exploring the Causality of End-to-End Autonomous Driving
Deep learning-based models are widely deployed in autonomous driving areas, especially the increasingly noticed end-to-end solutions.
BEVWorld: A Multimodal World Model for Autonomous Driving via Unified BEV Latent Space
The world model consists of two parts: the multi-modal tokenizer and the latent BEV sequence diffusion model.
VCD-Texture: Variance Alignment based 3D-2D Co-Denoising for Text-Guided Texturing
Recent research on texture synthesis for 3D shapes benefits a lot from dramatically developed 2D text-to-image diffusion models, including inpainting-based and optimization-based approaches.
A Survey on Mixture of Experts
Large language models (LLMs) have garnered unprecedented advancements across diverse fields, ranging from natural language processing to computer vision and beyond.
A Survey on Large Language Models for Code Generation
Despite the active exploration of LLMs for a variety of code tasks, either from the perspective of natural language processing (NLP) or software engineering (SE) or both, there is a noticeable absence of a comprehensive and up-to-date literature review dedicated to LLM for code generation.
Inference-Time Alignment of Diffusion Models with Direct Noise Optimization
In this work, we focus on the alignment problem of diffusion models with a continuous reward function, which represents specific objectives for downstream tasks, such as increasing darkness or improving the aesthetics of images.
Benchmarking General-Purpose In-Context Learning
In-context learning (ICL) empowers generative models to address new tasks effectively and efficiently on the fly, without relying on any artificially crafted optimization techniques.
Certified $\ell_2$ Attribution Robustness via Uniformly Smoothed Attributions
Model attribution is a popular tool to explain the rationales behind model predictions.
Deep RAW Image Super-Resolution. A NTIRE 2024 Challenge Survey
This paper reviews the NTIRE 2024 RAW Image Super-Resolution Challenge, highlighting the proposed solutions and results.
SC4D: Sparse-Controlled Video-to-4D Generation and Motion Transfer
Recent advances in 2D/3D generative models enable the generation of dynamic 3D objects from a single-view video.
Uncovering the Text Embedding in Text-to-Image Diffusion Models
The correspondence between input text and the generated image exhibits opacity, wherein minor textual modifications can induce substantial deviations in the generated image.
XScale-NVS: Cross-Scale Novel View Synthesis with Hash Featurized Manifold
We also introduce a novel dataset, namely GigaNVS, to benchmark cross-scale, high-resolution novel view synthesis of realworld large-scale scenes.
Text Data-Centric Image Captioning with Interactive Prompts
Among them, the mainstream solution is to project image embeddings into the text embedding space with the assistance of consistent representations between image-text pairs from the CLIP model.
Learning-based Multi-continuum Model for Multiscale Flow Problems
Multiscale problems can usually be approximated through numerical homogenization by an equation with some effective parameters that can capture the macroscopic behavior of the original system on the coarse grid to speed up the simulation.
Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation
Existing parameter-efficient fine-tuning (PEFT) methods have achieved significant success on vision transformers (ViTs) adaptation by improving parameter efficiency.
Neural radiance fields-based holography [Invited]
NeRF is a state-of-the-art technique for 3D light-field reconstruction from 2D images based on volume rendering.
Accelerating Parallel Sampling of Diffusion Models
Our experiments demonstrate that ParaTAA can decrease the inference steps required by common sequential sampling algorithms such as DDIM and DDPM by a factor of 4$\sim$14 times.
Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach
At inference, we generate images with arbitrary expansion multiples by inputting an anchor image and its corresponding positional embeddings.
DMT: Comprehensive Distillation with Multiple Self-supervised Teachers
Numerous self-supervised learning paradigms, such as contrastive learning and masked image modeling, have been proposed to acquire powerful and general representations from unlabeled data.
CL2CM: Improving Cross-Lingual Cross-Modal Retrieval via Cross-Lingual Knowledge Transfer
Cross-lingual cross-modal retrieval has garnered increasing attention recently, which aims to achieve the alignment between vision and target language (V-T) without using any annotated V-T data pairs.
Towards a Psychological Generalist AI: A Survey of Current Applications of Large Language Models and Future Prospects
The complexity of psychological principles underscore a significant societal challenge, given the vast social implications of psychological problems.
Language-guided Few-shot Semantic Segmentation
Few-shot learning is a promising way for reducing the label cost in new categories adaptation with the guidance of a small, well labeled support set.
OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning
Towards holistic understanding of 3D scenes, a general 3D segmentation method is needed that can segment diverse objects without restrictions on object quantity or categories, while also reflecting the inherent hierarchical structure.
Pre-Training on Large-Scale Generated Docking Conformations with HelixDock to Unlock the Potential of Protein-ligand Structure Prediction Models
In this work, we show that by pre-training on a large-scale docking conformation generated by traditional physics-based docking tools and then fine-tuning with a limited set of experimentally validated receptor-ligand complexes, we can obtain a protein-ligand structure prediction model with outstanding performance.
SingleInsert: Inserting New Concepts from a Single Image into Text-to-Image Models for Flexible Editing
To utilize the abundant visual priors in the off-the-shelf T2I models, a series of methods try to invert an image to proper embedding that aligns with the semantic space of the T2I model.
SCT: A Simple Baseline for Parameter-Efficient Fine-Tuning via Salient Channels
Experiments on 19 visual transfer learning downstream tasks demonstrate that our SCT outperforms full fine-tuning on 18 out of 19 tasks by adding only 0. 11M parameters of the ViT-B, which is 780$\times$ fewer than its full fine-tuning counterpart.
Viewpoint Integration and Registration with Vision Language Foundation Model for Image Change Understanding
Therefore, they cannot be directly applied to cope with image change understanding (ICU), which requires models to capture actual changes between multiple images and describe them in language.
Temporal compressive edge imaging enabled by a lensless diffuser camera
Lensless imagers based on diffusers or encoding masks enable high-dimensional imaging from a single shot measurement and have been applied in various applications.
Dual-view Curricular Optimal Transport for Cross-lingual Cross-modal Retrieval
Therefore, we propose Dual-view Curricular Optimal Transport (DCOT) to learn with noisy correspondence in CCR.
DiffAug: Enhance Unsupervised Contrastive Learning with Domain-Knowledge-Free Diffusion-based Data Augmentation
With the help of iterative training of the semantic encoder and diffusion model, DiffAug improves the representation ability in an uninterrupted and unsupervised manner.
Ranked #1 on
Data Augmentation
on GA1457
Punctate White Matter Lesion Segmentation in Preterm Infants Powered by Counterfactually Generative Learning
In this paper, we propose to leverage the idea of counterfactual reasoning coupled with the auxiliary task of brain tissue segmentation to learn fine-grained positional and morphological representations of PWMLs for accurate localization and segmentation.
Supervised Learning and Large Language Model Benchmarks on Mental Health Datasets: Cognitive Distortions and Suicidal Risks in Chinese Social Media
We also evaluated the performance of the LLMs after fine-tuning on the proposed tasks.
Region Generation and Assessment Network for Occluded Person Re-Identification
Then, to measure the importance of each generated region, we introduce a Region Assessment Module (RAM) that assigns confidence scores to different regions and reduces the negative impact of the occlusion regions by lower scores.
Enhancing Psychological Counseling with Large Language Model: A Multifaceted Decision-Support System for Non-Professionals
In the contemporary landscape of social media, an alarming number of users express negative emotions, some of which manifest as strong suicidal intentions.
Forensic Histopathological Recognition via a Context-Aware MIL Network Powered by Self-Supervised Contrastive Learning
Forensic pathology is critical in analyzing death manner and time from the microscopic aspect to assist in the establishment of reliable factual bases for criminal investigation.
Graph-Segmenter: Graph Transformer with Boundary-aware Attention for Semantic Segmentation
To address this issue, we propose a Graph-Segmenter, including a Graph Transformer and a Boundary-aware Attention module, which is an effective network for simultaneously modeling the more profound relation between windows in a global view and various pixels inside each window as a local one, and for substantial low-cost boundary adjustment.
ICPC: Instance-Conditioned Prompting with Contrastive Learning for Semantic Segmentation
Second, we propose an align-guided contrastive loss to refine the alignment of vision and text embeddings.
Dual Meta-Learning with Longitudinally Generalized Regularization for One-Shot Brain Tissue Segmentation Across the Human Lifespan
However, segmentation on longitudinal data is challenging due to dynamic brain changes across the lifespan.
Revisiting Vision Transformer from the View of Path Ensemble
Therefore, we propose the path pruning and EnsembleScale skills for improvement, which cut out the underperforming paths and re-weight the ensemble components, respectively, to optimize the path combination and make the short paths focus on providing high-quality representation for subsequent paths.
Dynamic Token-Pass Transformers for Semantic Segmentation
Vision transformers (ViT) usually extract features via forwarding all the tokens in the self-attention layers from top to toe.
RegionBLIP: A Unified Multi-modal Pre-training Framework for Holistic and Regional Comprehension
To this end, we propose to extract features corresponding to regional objects as soft prompts for LLM, which provides a straightforward and scalable approach and eliminates the need for LLM fine-tuning.
Improved Neural Radiance Fields Using Pseudo-depth and Fusion
To make the constructed volumes as close as possible to the surfaces of objects in the scene and the rendered depth more accurate, we propose to perform depth prediction and radiance field reconstruction simultaneously.
Points-to-3D: Bridging the Gap between Sparse Points and Shape-Controllable Text-to-3D Generation
To better utilize the sparse 3D points, we propose an efficient point cloud guidance loss to adaptively drive the NeRF's geometry to align with the shape of the sparse 3D points.
Graph Convolution Based Efficient Re-Ranking for Visual Retrieval
In particular, the plain GCR is extended for cross-camera retrieval and an improved feature propagation formulation is presented to leverage affinity relationships across different cameras.
Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training
Most previous works either simply learn coarse-grained representations of the overall image and text, or elaborately establish the correspondence between image regions or pixels and text words.
SwinRDM: Integrate SwinRNN with Diffusion Model towards High-Resolution and High-Quality Weather Forecasting
Recurrent predictions for future atmospheric fields are firstly performed at 1. 40625-degree resolution, and then a diffusion-based super-resolution model is leveraged to recover the high spatial resolution and finer-scale atmospheric details.
Lens-to-lens bokeh effect transformation. NTIRE 2023 challenge report
We present the new Bokeh Effect Transformation Dataset (BETD), and review the proposed solutions for this novel task at the NTIRE 2023 Bokeh Effect Transformation Challenge.
MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks
To account for the uncertainty caused by the limited training tasks, we propose a variational MetaModulation where the modulation parameters are treated as latent variables.
NIKI: Neural Inverse Kinematics with Invertible Neural Networks for 3D Human Pose and Shape Estimation
In this work, we present NIKI (Neural Inverse Kinematics with Invertible Neural Network), which models bi-directional errors to improve the robustness to occlusions and obtain pixel-aligned accuracy.
Ranked #1 on
3D Human Pose Estimation
on AGORA
UniNeXt: Exploring A Unified Architecture for Vision Recognition
Interestingly, the ranking of these spatial token mixers also changes under our UniNeXt, suggesting that an excellent spatial token mixer may be stifled due to a suboptimal general architecture, which further shows the importance of the study on the general architecture of vision backbone.
DOAD: Decoupled One Stage Action Detection Network
Specifically, one branch focuses on detection representation for actor detection, and the other one for action recognition.
Beyond Appearance: a Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks
Unlike the existing self-supervised learning methods, prior knowledge from human images is utilized in SOLIDER to build pseudo semantic labels and import more semantic information into the learned representation.
Ranked #1 on
Person Search
on PRW
ARMBench: An Object-centric Benchmark Dataset for Robotic Manipulation
This paper introduces Amazon Robotic Manipulation Benchmark (ARMBench), a large-scale, object-centric benchmark dataset for robotic manipulation in the context of a warehouse.
Ranked #7 on
Instance Segmentation
on ARMBench
EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation
In this paper, we propose the EPro-PnP, a probabilistic PnP layer for general end-to-end pose estimation, which outputs a distribution of pose with differentiable probability density on the SE(3) manifold.
Ranked #4 on
6D Pose Estimation using RGB
on LineMOD
Making Vision Transformers Efficient from A Token Sparsification View
In this work, we propose a novel Semantic Token ViT (STViT), for efficient global and local vision transformers, which can also be revised to serve as backbone for downstream tasks.
Revisit Parameter-Efficient Transfer Learning: A Two-Stage Paradigm
In view of the practicality of PETL, previous works focus on tuning a small set of parameters for each downstream task in an end-to-end manner while rarely considering the task distribution shift issue between the pre-training task and the downstream task.
Time series anomaly detection with reconstruction-based state-space models
In this work, we propose a novel unsupervised anomaly detection method for time series data.
A Practical Upper Bound for the Worst-Case Attribution Deviations
Model attribution is a critical component of deep neural networks (DNNs) for its interpretability to complex models.
Foundation Model Drives Weakly Incremental Learning for Semantic Segmentation
In this work, we propose a novel and data-efficient framework for WILSS, named FMWISS.
LMSeg: Language-guided Multi-dataset Segmentation
Instead of relabeling each dataset with the unified taxonomy, a category-guided decoding module is designed to dynamically guide predictions to each datasets taxonomy.
Dual-mode adaptive-SVD ghost imaging
In this paper, we present a dual-mode adaptive singular value decomposition ghost imaging (A-SVD GI), which can be easily switched between the modes of imaging and edge detection.
Head-Free Lightweight Semantic Segmentation with Linear Transformer
On the ADE20K dataset, our model achieves 41. 8 mIoU and 4. 6 GFLOPs, which is 4. 4 mIoU higher than Segformer, with 45% less GFLOPs.
Efficient Mask Correction for Click-Based Interactive Image Segmentation
To this end, we propose an efficient method to correct the mask with a lightweight mask correction network.
Dual Meta-Learning with Longitudinally Consistent Regularization for One-Shot Brain Tissue Segmentation Across the Human Lifespan
However, segmentation on longitudinal data is challenging due to dynamic brain changes across the lifespan.
NeuroExplainer: Fine-Grained Attention Decoding to Uncover Cortical Development Patterns of Preterm Infants
Deploying reliable deep learning techniques in interdisciplinary applications needs learned models to output accurate and (even more importantly) explainable predictions.
MHPL: Minimum Happy Points Learning for Active Source Free Domain Adaptation
Source free domain adaptation (SFDA) aims to transfer a trained source model to the unlabeled target domain without accessing the source data.
Query Enhanced Knowledge-Intensive Conversation via Unsupervised Joint Modeling
In this paper, we propose an unsupervised query enhanced approach for knowledge-intensive conversations, namely QKConv.
CAT: Learning to Collaborate Channel and Spatial Attention from Multi-Information Fusion
Channel and spatial attention mechanism has proven to provide an evident performance boost of deep convolution neural networks (CNNs).
Surround-view Fisheye BEV-Perception for Valet Parking: Dataset, Baseline and Distortion-insensitive Multi-task Framework
Most existing networks based on public datasets may generalize suboptimal results on these valet parking scenes, also affected by the fisheye distortion.
Complete Solution for Vehicle Re-ID in Surround-view Camera System
Vehicle re-identification (Re-ID) is a critical component of the autonomous driving perception system, and research in this area has accelerated in recent years.
A Unified Multimodal De- and Re-coupling Framework for RGB-D Motion Recognition
Although improving motion recognition to some extent, these methods still face sub-optimal situations in the following aspects: (i) Data augmentation, i. e., the scale of the RGB-D datasets is still limited, and few efforts have been made to explore novel data augmentation strategies for videos; (ii) Optimization mechanism, i. e., the tightly space-time-entangled network structure brings more challenges to spatiotemporal information modeling; And (iii) cross-modal knowledge fusion, i. e., the high similarity between multimodal representations caused to insufficient late fusion.
Ranked #4 on
Action Recognition
on NTU RGB+D
PLATO-K: Internal and External Knowledge Enhanced Dialogue Generation
Recently, the practical deployment of open-domain dialogue systems has been plagued by the knowledge issue of information deficiency and factual inaccuracy.
VTC-LFC: Vision Transformer Compression with Low-Frequency Components
Although Vision transformers (ViTs) have recently dominated many vision tasks, deploying ViT models on resource-limited devices remains a challenging problem.
Behavioral Intention Prediction in Driving Scenes: A Survey
Behavioral Intention Prediction (BIP) simulates such a human consideration process and fulfills the early prediction of specific behaviors.
Q-TOD: A Query-driven Task-oriented Dialogue System
Firstly, as the query is in the form of natural language and not confined to the schema of the knowledge base, the issue of domain adaption is alleviated remarkably in Q-TOD.
Effective Vision Transformer Training: A Data-Centric Perspective
To achieve these two purposes, we propose a novel data-centric ViT training framework to dynamically measure the ``difficulty'' of training samples and generate ``effective'' samples for models at different training stages.
FAKD: Feature Augmented Knowledge Distillation for Semantic Segmentation
Inspired by the recent progress on semantic directions on feature-space, we propose to include augmentations in feature space for efficient distillation.
Towards Boosting the Open-Domain Chatbot with Human Feedback
Many open-domain dialogue models pre-trained with social media comments can generate coherent replies but have difficulties producing engaging responses when interacting with real users.
GEM-2: Next Generation Molecular Property Prediction Network by Modeling Full-range Many-body Interactions
Full-range many-body interactions between electrons have been proven effective in obtaining an accurate solution of the Schr"odinger equation by classical computational chemistry methods, although modeling such interactions consumes an expensive computational cost.
HelixFold-Single: MSA-free Protein Structure Prediction by Using Protein Language Model as an Alternative
Our proposed method, HelixFold-Single, first pre-trains a large-scale protein language model (PLM) with thousands of millions of primary sequences utilizing the self-supervised learning paradigm, which will be used as an alternative to MSAs for learning the co-evolution information.
Dynamic Gradient Reactivation for Backward Compatible Person Re-identification
To address this issue, we propose the Ranking-based Backward Compatible Learning (RBCL), which directly optimizes the ranking metric between new features and old features.
HelixFold: An Efficient Implementation of AlphaFold2 using PaddlePaddle
Due to the complex model architecture and large memory consumption, it requires lots of computational resources and time to implement the training and inference of AlphaFold2 from scratch.
TCR: A Transformer Based Deep Network for Predicting Cancer Drugs Response
Our study highlights the prediction power of TCR and its potential value for cancer drug repurpose and precision oncology treatment.
Link the World: Improving Open-domain Conversation with Dynamic Spatiotemporal-aware Knowledge
Making chatbots world aware in a conversation like a human is a crucial challenge, where the world may contain dynamic knowledge and spatiotemporal state.
HCFRec: Hash Collaborative Filtering via Normalized Flow with Structural Consensus for Efficient Recommendation
The ever-increasing data scale of user-item interactions makes it challenging for an effective and efficient recommender system.
Active Source Free Domain Adaptation
We then propose minimum happy points learning (MHPL) to actively explore and exploit MH points.
HelixADMET: a robust and endpoint extensible ADMET system incorporating self-supervised knowledge transfer
Additionally, the pre-trained model provided by H-ADMET can be fine-tuned to generate new and customised ADMET endpoints, meeting various demands of drug research and development requirements.
Exploiting the Relationship Between Kendall's Rank Correlation and Cosine Similarity for Attribution Protection
In this paper, we first show that the expected Kendall's rank correlation is positively correlated to cosine similarity and then indicate that the direction of attribution is the key to attribution robustness.
An empirical equilibrium model of formal and informal credit markets in developing countries
I develop and estimate a dynamic equilibrium model of risky entrepreneurs' borrowing and savings decisions incorporating both formal and local-informal credit markets.
Optimal allocations to heterogeneous agents with an application to stimulus checks
A planner allocates discrete transfers of size $D_g$ to $N$ heterogeneous groups labeled $g$ and has CES preferences over the resulting outcomes, $H_g(D_g)$.
Structure-aware Protein Self-supervised Learning
Furthermore, we propose to leverage the available protein language model pretrained on protein sequences to enhance the self-supervised learning.
Early life height and weight production functions with endogenous energy and protein inputs
We examine effects of protein and energy intakes on height and weight growth for children between 6 and 24 months old in Guatemala and the Philippines.
You are what your parents expect: Height and local reference points
We explore the exogenous variation in reference height produced by a protein-supplementation experiment in Guatemala to estimate our model's parameters.
Fewer, better pathways for all? Intersectional impacts of rural school consolidation in China's minority regions
Much more than Han youth, ethnic minority youth were negatively affected by closure, in terms of its impact on both educational attainment and written Mandarin facility.
Same environment, stratified impacts? Air pollution, extreme temperatures, and birth weight in south China
This paper investigates whether associations between birth weight and prenatal ambient environmental conditions--pollution and extreme temperatures--differ by 1) maternal education; 2) children's innate health; and 3) interactions between these two.
Estimating the Effects of Educational System Consolidation: The Case of China's Rural School Closure Initiative
We estimate the impact of educational infrastructure consolidation on educational attainment using the case of China's rural primary school closure policies in the early 2000s.
EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimation
The 2D-3D coordinates and corresponding weights are treated as intermediate variables learned by minimizing the KL divergence between the predicted and target pose distribution.
Ranked #6 on
6D Pose Estimation using RGB
on LineMOD
Controllable energy angular spectrum method
A controllable energy method, which considers the undersampling issue of the transfer function and valid spectral energy of a source signal, is proposed to implement angular spectrum diffraction calculation in near and far fields.
Information retrieval for label noise document ranking by bag sampling and group-wise loss
To fit bag sampling well, after query and document are encoded, the global features of each group are extracted by convolutional layer and max-pooling to improve the model's resistance to the impact of labeling noise, finally, calculate the LCE group-wise loss.
Detecting Owner-member Relationship with Graph Convolution Network in Fisheye Camera System
The owner-member relationship between wheels and vehicles contributes significantly to the 3D perception of vehicles, especially in embedded environments.
Image-to-Video Re-Identification via Mutual Discriminative Knowledge Transfer
During the KD process, the TCL loss transfers the local structure, exploits the higher order information, and mitigates the misalignment of the heterogeneous output of teacher and student networks.
Network-ELAA Beamforming and Coverage Analysis for eMBB/URLLC in Spatially Non-Stationary Rician Channels
Finally, it is shown that the network-ELAA can offer significant coverage extension (50% or more in most of cases) when comparing with the single-AP scenario.
Lightweight Object-level Topological Semantic Mapping and Long-term Global Localization based on Graph Matching
In this paper, we present a novel lightweight object-level mapping and localization method with high accuracy and robustness.
Exploring Domain-Invariant Parameters for Source Free Domain Adaptation
In contrast, we provide a fascinating insight: rather than attempting to learn domain-invariant representations, it is better to explore the domain-invariant parameters of the source model.
Memory-Augmented Deep Conditional Unfolding Network for Pan-Sharpening
Pan-sharpening aims to obtain high-resolution multispectral (MS) images for remote sensing systems and deep learning-based methods have achieved remarkable success.
TAGPerson: A Target-Aware Generation Pipeline for Person Re-identification
In TAGPerson, we extract information from target scenes and use them to control our parameterized rendering process to generate target-aware synthetic images, which would hold a smaller gap to the real images in the target domain.
TOD-DA: Towards Boosting the Robustness of Task-oriented Dialogue Modeling on Spoken Conversations
Task-oriented dialogue systems have been plagued by the difficulties of obtaining large-scale and high-quality annotated conversations.
ELSA: Enhanced Local Self-Attention for Vision Transformer
Self-attention is powerful in modeling long-range dependencies, but it is weak in local finer-level feature learning.
Ranked #47 on
Semantic Segmentation
on ADE20K val
Decoupling and Recoupling Spatiotemporal Representation for RGB-D-based Motion Recognition
Decoupling spatiotemporal representation refers to decomposing the spatial and temporal features into dimension-independent factors.
Ranked #1 on
Hand Gesture Recognition
on NVGesture
Multimodal Pre-Training Model for Sequence-based Prediction of Protein-Protein Interaction
However, neither sequences nor contact maps can fully characterize structures and functions of the proteins, which are closely related to the PPI problem.
TransFGU: A Top-down Approach to Fine-Grained Unsupervised Semantic Segmentation
Unsupervised semantic segmentation aims to obtain high-level semantic representation on low-level visual features without manual annotations.
Ranked #2 on
Unsupervised Semantic Segmentation
on COCO-Stuff-171
(using extra training data)
HelixMO: Sample-Efficient Molecular Optimization in Scene-Sensitive Latent Space
Efficient exploration of the chemical space to search the candidate drugs that satisfy various constraints is a fundamental task of drug discovery.
Self-Supervised Pre-Training for Transformer-Based Person Re-Identification
We first investigate self-supervised learning (SSL) methods with Vision Transformer (ViT) pretrained on unlabelled person images (the LUPerson dataset), and empirically find it significantly surpasses ImageNet supervised pre-training models on ReID tasks.
Ranked #1 on
Unsupervised Person Re-Identification
on Market-1501
(using extra training data)
Docking-based Virtual Screening with Multi-Task Learning
Machine learning shows great potential in virtual screening for drug discovery.
Achieving Human Parity on Visual Question Answering
The Visual Question Answering (VQA) task utilizes both visual image and language analysis to answer a textual question with respect to an image.
Ranked #8 on
Visual Question Answering (VQA)
on VQA v2 test-dev
Amendable Generation for Dialogue State Tracking
In this paper, we propose a novel Amendable Generation for Dialogue State Tracking (AG-DST), which contains a two-pass generation process: (1) generating a primitive dialogue state based on the dialogue of the current turn and the previous dialogue state, and (2) amending the primitive dialogue state from the first pass.
Ranked #1 on
Dialogue State Tracking
on Wizard-of-Oz
Dialogue State Tracking
Multi-domain Dialogue State Tracking
+1
Do What Nature Did To Us: Evolving Plastic Recurrent Neural Networks For Generalized Tasks
While artificial neural networks (ANNs) have been widely adopted in machine learning, researchers are increasingly obsessed by the gaps between ANNs and natural neural networks (NNNs).
PLATO-XL: Exploring the Large-scale Pre-training of Dialogue Generation
To explore the limit of dialogue generation pre-training, we present the models of PLATO-XL with up to 11 billion parameters, trained on both Chinese and English social media conversations.
Reinforcement Learning with Evolutionary Trajectory Generator: A General Approach for Quadrupedal Locomotion
However, due to the complex nonlinear dynamics in quadrupedal robots and reward sparsity, it is still difficult for RL to learn effective gaits from scratch, especially in challenging tasks such as walking over the balance beam.
CDTrans: Cross-domain Transformer for Unsupervised Domain Adaptation
Along with the pseudo labels, a weight-sharing triple-branch transformer framework is proposed to apply self-attention and cross-attention for source/target feature learning and source-target domain alignment, respectively.
Ranked #4 on
Domain Adaptation
on Office-31
Scaled ReLU Matters for Training Vision Transformers
In this paper, we further investigate this problem and extend the above conclusion: only early convolutions do not help for stable training, but the scaled ReLU operation in the \textit{convolutional stem} (\textit{conv-stem}) matters.
Evolving Decomposed Plasticity Rules for Information-Bottlenecked Meta-Learning
In contrast, biological neural networks (BNNs) can adapt to various new tasks by continually updating the neural connections based on the inputs, which is aligned with the paradigm of learning effective learning rules in addition to static parameters, e. g., meta-learning.
ADER:Adapting between Exploration and Robustness for Actor-Critic Methods
Combining off-policy reinforcement learning methods with function approximators such as neural networks has been found to lead to overestimation of the value function and sub-optimal solutions.
Exploring the Quality of GAN Generated Images for Person Re-Identification
Recently, GAN based method has demonstrated strong effectiveness in generating augmentation data for person re-identification (ReID), on account of its ability to bridge the gap between domains and enrich the data variety in feature space.
Structure-aware Interactive Graph Neural Networks for the Prediction of Protein-Ligand Binding Affinity
To this end, we propose a structure-aware interactive graph neural network (SIGN) which consists of two components: polar-inspired graph attention layers (PGAL) and pairwise interactive pooling (PiPool).
Ranked #3 on
Protein-Ligand Affinity Prediction
on PDBbind
Graph Convolution for Re-ranking in Person Re-identification
In this work, we propose a graph-based re-ranking method to improve learned features while still keeping Euclidean distance as the similarity metric.
Action Set Based Policy Optimization for Safe Power Grid Management
At the planning stage, the search space is limited to the action set produced by the policy.
ChemRL-GEM: Geometry Enhanced Molecular Representation Learning for Property Prediction
Recent advances in graph neural networks (GNNs) have shown great promise in applying GNNs for molecular representation learning.
Ranked #2 on
Molecular Property Prediction
on QM9
KVT: k-NN Attention for Boosting Vision Transformers
A key component in vision transformers is the fully-connected self-attention which is more powerful than CNNs in modelling long range dependencies.
An Empirical Study of Vehicle Re-Identification on the AI City Challenge
We mainly focus on four points, i. e. training data, unsupervised domain-adaptive (UDA) training, post-processing, model ensembling in this challenge.
City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones
Multi-Target Multi-Camera Tracking has a wide range of applications and is the basis for many advanced inferences and predictions.
TopoTxR: A Topological Biomarker for Predicting Treatment Response in Breast Cancer
Characterization of breast parenchyma on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is a challenging task owing to the complexity of underlying tissue structures.
A Unified Pre-training Framework for Conversational AI
In this work, we explore the application of PLATO-2 on various dialogue systems, including open-domain conversation, knowledge grounded dialogue, and task-oriented conversation.
Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generation
Temporal action proposal generation (TAPG) is a fundamental and challenging task in video understanding, especially in temporal action detection.
Molecular Representation Learning by Leveraging Chemical Information
As graph neural networks have achieved great success in many domains, some studies apply graph neural networks to molecular property prediction and regard each molecule as a graph.
Ranked #6 on
Graph Property Prediction
on ogbg-molhiv