Search Results for author:
Found 235 papers, 124 papers with code
Pre-training Entity Relation Encoder with Intra-span and Inter-span Information
In particular, a span encoder is trained to recover a random shuffling of tokens in a span, and a span pair encoder is trained to predict positive pairs that are from the same sentences and negative pairs that are from different sentences using contrastive loss.
Discriminative Partial Domain Adversarial Network
Previous methods typically match the whole source domain to target domain, which causes negative transfer due to the source-negative classes in source domain that does not exist in target domain.
AutoMix: Mixup Networks for Sample Interpolation via Cooperative Barycenter Learning
This paper proposes new ways of sample mixing by thinking of the process as generation of barycenter in a metric space for data augmentation.
Rethinking the Defocus Blur Detection Problem and A Real-Time Deep DBD Model
In this work, we propose novel perspectives on the DBD problem and design convenient approach to build a real-time cost-effective DBD model.
Exploiting Unlabeled Data with Multiple Expert Teachers for Open Vocabulary Aerial Object Detection and Its Orientation Adaptation
In this paper, we put forth a novel formulation of the aerial object detection problem, namely open-vocabulary aerial object detection (OVAD), which can detect objects beyond training categories without costly collecting new labeled data.
Derail Yourself: Multi-turn LLM Jailbreak Attack through Self-discovered Clues
This study exposes the safety vulnerabilities of Large Language Models (LLMs) in multi-turn interactions, where malicious users can obscure harmful intents across several queries.
Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late in Training
Specifically, we find that SAM efficiently selects flatter minima late in training.
Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy
Diffusion models have recently achieved great success in the synthesis of high-quality images and videos.
DiFSD: Ego-Centric Fully Sparse Paradigm with Uncertainty Denoising and Iterative Refinement for Efficient End-to-End Self-Driving
Specifically, DiFSD mainly consists of sparse perception, hierarchical interaction and iterative motion planner.
Neural Message Passing Induced by Energy-Constrained Diffusion
Learning representations for structured data with certain geometries (observed or unobserved) is a fundamental challenge, wherein message passing neural networks (MPNNs) have become a de facto class of model solutions.
SGFormer: Single-Layer Graph Transformers with Approximation-Free Linear Complexity
Learning representations on large graphs is a long-standing challenge due to the inter-dependence nature.
Learning to Solve Combinatorial Optimization under Positive Linear Constraints via Non-Autoregressive Neural Networks
In this paper, we design a family of non-autoregressive neural networks to solve CO problems under positive linear constraints with the following merits.
RoboSense: Large-scale Dataset and Benchmark for Egocentric Robot Perception and Navigation in Crowded and Unstructured Environments
Reliable embodied perception from an egocentric perspective is challenging yet essential for autonomous navigation technology of intelligent mobile agents.
Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable Segmentation
In this paper, we utilize hallucinations to mine task-related information from images and verify its accuracy for enhancing precision of the generated prompts.
Camouflaged Object Segmentation with a Single Task-generic Prompt
Medical Image Segmentation
+1
Not All Samples Should Be Utilized Equally: Towards Understanding and Improving Dataset Distillation
Our findings suggest that prioritizing the synthesis of easier samples from the original dataset can enhance the quality of distilled datasets, especially in low IPC (image-per-class) settings.
PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
These methods typically include an encoder accepting visible patches (normalized) and corresponding patch centers (position) as input, with the decoder accepting the output of the encoder and the centers (position) of the masked parts to reconstruct each point in the masked patches.
FlatFusion: Delving into Details of Sparse Transformer-based Camera-LiDAR Fusion for Autonomous Driving
The integration of data from diverse sensor modalities (e. g., camera and LiDAR) constitutes a prevalent methodology within the ambit of autonomous driving scenarios.
Re-TASK: Revisiting LLM Tasks from Capability, Skill, and Knowledge Perspectives
This paper introduces the Re-TASK framework, a novel theoretical model that revisits LLM tasks from the perspectives of capability, skill, and knowledge, drawing on the principles of Bloom's Taxonomy and Knowledge Space Theory.
LinSATNet: The Positive Linear Satisfiability Neural Networks
Encoding constraints into neural networks is attractive.
GeoMix: Towards Geometry-Aware Data Augmentation
It effectively utilizes geometry information to interpolate features and labels with those from the nearby neighborhood, generating synthetic nodes and establishing connections for them.
Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models
We cast the dynamics learning as an auto-regressive sequence modeling problem over discrete tokens by leveraging the expressive Transformer architecture, in order to model complex local dynamics across different agents and provide accurate and consistent long-term imaginations.
DocGenome: An Open Large-scale Scientific Document Benchmark for Training and Testing Multi-modal Large Language Models
Scientific documents record research findings and valuable human knowledge, comprising a vast corpus of high-quality data.
STAR: A First-Ever Dataset and A Large-Scale Benchmark for Scene Graph Generation in Large-Size Satellite Imagery
This paper constructs a large-scale dataset for SGG in large-size VHR SAI with image sizes ranging from 512 x 768 to 27, 860 x 31, 096 pixels, named STAR (Scene graph generaTion in lArge-size satellite imageRy), encompassing over 210K objects and over 400K triplets.
Towards Vision-Language Geo-Foundation Model: A Survey
Vision-Language Foundation Models (VLFMs) have made remarkable progress on various multimodal tasks, such as image captioning, image-text retrieval, visual question answering, and visual grounding.
Learning Divergence Fields for Shift-Robust Graph Representations
Real-world data generation often involves certain geometries (e. g., graphs) that induce instance-level interdependence.
Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving
In an era marked by the rapid scaling of foundation models, autonomous driving technologies are approaching a transformative threshold where end-to-end autonomous driving (E2E-AD) emerges due to its potential of scaling up in the data-driven manner.
Ranked #11 on
Bench2Drive
on Bench2Drive
TerDiT: Ternary Diffusion Models with Transformers
Recent developments in large-scale pre-trained text-to-image diffusion models have significantly improved the generation of high-fidelity images, particularly with the emergence of diffusion models based on transformer architecture (DiTs).
Grounding and Enhancing Grid-based Models for Neural Fields
Many contemporary studies utilize grid-based models for neural field representation, but a systematic analysis of grid-based models is still missing, hindering the improvement of those models.
AMP: Autoregressive Motion Prediction Revisited with Next Token Prediction for Autonomous Driving
As an essential task in autonomous driving (AD), motion prediction aims to predict the future states of surround objects for navigation.
Boosting Order-Preserving and Transferability for Neural Architecture Search: a Joint Architecture Refined Search and Fine-tuning Approach
In this work, we analyze the order-preserving ability on the whole search space (global) and a sub-space of top architectures (local), and empirically show that the local order-preserving for current two-stage NAS methods still need to be improved.
Boundary Matters: A Bi-Level Active Finetuning Framework
In this paper, we propose a Bi-Level Active Finetuning framework to select the samples for annotation in one shot, which includes two stages: core sample selection for diversity, and boundary sample selection for uncertainty.
CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion
The rapid advancement of Large Language Models (LLMs) has brought about remarkable generative capabilities but also raised concerns about their potential misuse.
ActiveAD: Planning-Oriented Active Learning for End-to-End Autonomous Driving
End-to-end differentiable learning for autonomous driving (AD) has recently become a prominent paradigm.
Rethinking Classifier Re-Training in Long-Tailed Recognition: A Simple Logits Retargeting Approach
In the long-tailed recognition field, the Decoupled Training paradigm has demonstrated remarkable capabilities among various methods.
Theoretically Achieving Continuous Representation of Oriented Bounding Boxes
Considerable efforts have been devoted to Oriented Object Detection (OOD).
Fast and Interpretable 2D Homography Decomposition: Similarity-Kernel-Similarity and Affine-Core-Affine Transformations
Under the minimal $4$-point configuration, the first and the last similarity transformations in SKS are computed by two anchor points on target and source planes, respectively.
PreRoutGNN for Timing Prediction with Order Preserving Partition: Global Circuit Pre-training, Local Delay Learning and Attentional Cell Modeling
First, we propose global circuit training to pre-train a graph auto-encoder that learns the global graph embedding from circuit netlist.
Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models
Specifically, we propose, for the first time to our best knowledge, post-training approaches for task-agnostic and task-specific expert pruning and skipping of MoE LLMs, tailored to improve deployment efficiency while maintaining model performance across a wide range of tasks.
ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoning
Recently, many versatile Multi-modal Large Language Models (MLLMs) have emerged continuously.
Graph Out-of-Distribution Generalization via Causal Intervention
In this paper, we adopt a bottom-up data-generative perspective and reveal a key observation through causal analysis: the crux of GNNs' failure in OOD generalization lies in the latent confounding bias from the environment.
GSINA: Improving Subgraph Extraction for Graph Invariant Learning via Graph Sinkhorn Attention
Many recent endeavors of GIL focus on extracting the invariant subgraph from the input graph for prediction as a regularization strategy to improve the generalization performance of graph learning.
QuEST: Low-bit Diffusion Model Quantization via Efficient Selective Finetuning
We empirically verify that our approach modifies the activation distribution and provides meaningful temporal information, facilitating easier and more accurate quantization.
On the Emergence of Cross-Task Linearity in the Pretraining-Finetuning Paradigm
The pretraining-finetuning paradigm has become the prevailing trend in modern deep learning.
Poisson Process for Bayesian Optimization
BayesianOptimization(BO) is a sample-efficient black-box optimizer, and extensive methods have been proposed to build the absolute function response of the black-box function through a probabilistic surrogate model, including Tree-structured Parzen Estimator (TPE), random forest (SMAC), and Gaussian process (GP).
ViTree: Single-path Neural Tree for Step-wise Interpretable Fine-grained Visual Categorization
As computer vision continues to advance and finds widespread applications across various domains, the need for interpretability in deep learning models becomes paramount.
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.
Knowledge Guided Entity-aware Video Captioning and A Basketball Benchmark
We develop a knowledge guided entity-aware video captioning network (KEANet) based on a candidate player list in encoder-decoder form for basketball live text broadcast.
Double-Bounded Optimal Transport for Advanced Clustering and Classification
Even with vanilla Softmax trained features, our extensive experimental results show that our method can achieve good results with our improved inference scheme in the testing stage.
MorphGrower: A Synchronized Layer-by-layer Growing Approach for Plausible Neuronal Morphology Generation
Neuronal morphology is essential for studying brain functioning and understanding neurodegenerative disorders.
Machine Learning Insides OptVerse AI Solver: Design Principles and Applications
To this end, we present a comprehensive study on the integration of machine learning (ML) techniques into Huawei Cloud's OptVerse AI Solver, which aims to mitigate the scarcity of real-world mathematical programming instances, and to surpass the capabilities of traditional optimization techniques.
Circuit Design and Efficient Simulation of Quantum Inner Product and Empirical Studies of Its Effect on Near-Term Hybrid Quantum-Classic Machine Learning
However it remains unclear for the embodiment of the quantum circuits (QC) for QIP let alone a (thorough) evaluation of the QIP circuits especially in a practical context in the NISQ era by applying QIP to ML via hybrid quantum-classic pipelines.
LLM4EDA: Emerging Progress in Large Language Models for Electronic Design Automation
Since circuit can be represented with HDL in a textual format, it is reasonable to question whether LLMs can be leveraged in the EDA field to achieve fully automated chip design and generate circuits with improved power, performance, and area (PPA).
LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving
A map, as crucial information for downstream applications of an autonomous driving system, is usually represented in lanelines or centerlines.
Machine Learning for the Multi-Dimensional Bin Packing Problem: Literature Review and Empirical Evaluation
To the best of our knowledge, this is the first systematic review of ML-related methods for BPP.
Open-sourced Data Ecosystem in Autonomous Driving: the Present and Future
With the continuous maturation and application of autonomous driving technology, a systematic examination of open-source autonomous driving datasets becomes instrumental in fostering the robust evolution of the industry ecosystem.
Rethinking Urban Mobility Prediction: A Super-Multivariate Time Series Forecasting Approach
To address this challenge, we present the Super-Multivariate Urban Mobility Transformer (SUMformer), which utilizes a specially designed attention mechanism to calculate temporal and cross-variable correlations and reduce computational costs stemming from a large number of time series.
Unified Batch Normalization: Identifying and Alleviating the Feature Condensation in Batch Normalization and a Unified Framework
In this work, we critically examine BN from a feature perspective, identifying feature condensation during BN as a detrimental factor to test performance.
Point2RBox: Combine Knowledge from Synthetic Visual Patterns for End-to-end Oriented Object Detection with Single Point Supervision
To our best knowledge, Point2RBox is the first end-to-end solution for point-supervised OOD.
PointOBB: Learning Oriented Object Detection via Single Point Supervision
Single point-supervised object detection is gaining attention due to its cost-effectiveness.
GMTR: Graph Matching Transformers
Meanwhile, on Pascal VOC, QueryTrans improves the accuracy of NGMv2 from $80. 1\%$ to $\mathbf{83. 3\%}$, and BBGM from $79. 0\%$ to $\mathbf{84. 5\%}$.
Ranked #1 on
Graph Matching
on PASCAL VOC
(matching accuracy metric)
Benchmarking PtO and PnO Methods in the Predictive Combinatorial Optimization Regime
Our study shows that PnO approaches are better than PtO on 7 out of 8 benchmarks, but there is no silver bullet found for the specific design choices of PnO.
Rethinking Cross-Domain Sequential Recommendation under Open-World Assumptions
To address these challenges under open-world assumptions, we design an \textbf{A}daptive \textbf{M}ulti-\textbf{I}nterest \textbf{D}ebiasing framework for cross-domain sequential recommendation (\textbf{AMID}), which consists of a multi-interest information module (\textbf{MIM}) and a doubly robust estimator (\textbf{DRE}).
RigLSTM: Recurrent Independent Grid LSTM for Generalizable Sequence Learning
Sequential processes in real-world often carry a combination of simple subsystems that interact with each other in certain forms.
LLM4Drive: A Survey of Large Language Models for Autonomous Driving
Recently, large language models (LLMs) have demonstrated abilities including understanding context, logical reasoning, and generating answers.
M3C: A Framework towards Convergent, Flexible, and Unsupervised Learning of Mixture Graph Matching and Clustering
Existing graph matching methods typically assume that there are similar structures between graphs and they are matchable.
On the Evaluation and Refinement of Vision-Language Instruction Tuning Datasets
Instead of evaluating the models directly, in this paper, we try to evaluate the Vision-Language Instruction-Tuning (VLIT) datasets.
Advective Diffusion Transformers for Topological Generalization in Graph Learning
Graph diffusion equations are intimately related to graph neural networks (GNNs) and have recently attracted attention as a principled framework for analyzing GNN dynamics, formalizing their expressive power, and justifying architectural choices.
Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category Theory
In this paper, we expand the concept of equivalent feature and provide the definition of what we call functionally equivalent features.
How Graph Neural Networks Learn: Lessons from Training Dynamics
In particular, we find that the gradient descent optimization of GNNs implicitly leverages the graph structure to update the learned function, as can be quantified by a phenomenon which we call \emph{kernel-graph alignment}.
StructChart: On the Schema, Metric, and Augmentation for Visual Chart Understanding
Specifically, StructChart first reformulates the chart data from the tubular form (linearized CSV) to STR, which can friendlily reduce the task gap between chart perception and reasoning.
Ranked #20 on
Chart Question Answering
on ChartQA
(using extra training data)
SPOT: Scalable 3D Pre-training via Occupancy Prediction for Learning Transferable 3D Representations
Annotating 3D LiDAR point clouds for perception tasks is fundamental for many applications e. g., autonomous driving, yet it still remains notoriously labor-intensive.
ReSimAD: Zero-Shot 3D Domain Transfer for Autonomous Driving with Source Reconstruction and Target Simulation
Domain shifts such as sensor type changes and geographical situation variations are prevalent in Autonomous Driving (AD), which poses a challenge since AD model relying on the previous domain knowledge can be hardly directly deployed to a new domain without additional costs.
DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving
We find that even equipped with a SOTA perception model, directly letting the student model learn the required inputs of the teacher model leads to poor driving performance, which comes from the large distribution gap between predicted privileged inputs and the ground-truth.
Ranked #2 on
Bench2Drive
on Bench2Drive
Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning
On classification tasks, for ViT-S, ADCLR achieves 77. 5% top-1 accuracy on ImageNet with linear probing, outperforming our baseline (DINO) without our devised techniques as plug-in, by 0. 5%.
GraphGLOW: Universal and Generalizable Structure Learning for Graph Neural Networks
Graph structure learning is a well-established problem that aims at optimizing graph structures adaptive to specific graph datasets to help message passing neural networks (i. e., GNNs) to yield effective and robust node embeddings.
SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations
Learning representations on large-sized graphs is a long-standing challenge due to the inter-dependence nature involved in massive data points.
NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification
In this paper, we introduce a novel all-pair message passing scheme for efficiently propagating node signals between arbitrary nodes, as an important building block for a pioneering Transformer-style network for node classification on large graphs, dubbed as \textsc{NodeFormer}.
Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving
End-to-end autonomous driving has made impressive progress in recent years.
Ranked #3 on
Bench2Drive
on Bench2Drive
HIORE: Leveraging High-order Interactions for Unified Entity Relation Extraction
Entity relation extraction consists of two sub-tasks: entity recognition and relation extraction.
Category-Oriented Representation Learning for Image to Multi-Modal Retrieval
We focus on representation learning for IMMR and analyze three key challenges for it: 1) skewed data and noisy label in real-world industrial data, 2) the information-inequality between image and text modality of documents when learning representations, 3) effective and efficient training in large-scale industrial contexts.
OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping
Accurately depicting the complex traffic scene is a vital component for autonomous vehicles to execute correct judgments.
Graph-based Topology Reasoning for Driving Scenes
Understanding the road genome is essential to realize autonomous driving.
Ranked #6 on
3D Lane Detection
on OpenLane-V2 val
Geometric-aware Pretraining for Vision-centric 3D Object Detection
We also conduct experiments on various image backbones and view transformations to validate the efficacy of our approach.
Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigm
We propose a novel method called ActiveFT for active finetuning task to select a subset of data distributing similarly with the entire unlabeled pool and maintaining enough diversity by optimizing a parametric model in the continuous space.
EasyDGL: Encode, Train and Interpret for Continuous-time Dynamic Graph Learning
Dynamic graphs arise in various real-world applications, and it is often welcomed to model the dynamics directly in continuous time domain for its flexibility.
Rethinking Visual Prompt Learning as Masked Visual Token Modeling
To explore prompt learning on the generative pre-trained visual model, as well as keeping the task consistency, we propose Visual Prompt learning as masked visual Token Modeling (VPTM) to transform the downstream visual classification into the pre-trained masked visual token prediction.
ARS-DETR: Aspect Ratio-Sensitive Detection Transformer for Aerial Oriented Object Detection
Existing oriented object detection methods commonly use metric AP$_{50}$ to measure the performance of the model.
M-Tuning: Prompt Tuning with Mitigated Label Bias in Open-Set Scenarios
In realistic open-set scenarios where labels of a part of testing data are totally unknown, when vision-language (VL) prompt learning methods encounter inputs related to unknown classes (i. e., not seen during training), they always predict them as one of the training classes.
Graph Signal Sampling for Inductive One-Bit Matrix Completion: a Closed-form Solution
Inductive one-bit matrix completion is motivated by modern applications such as recommender systems, where new users would appear at test stage with the ratings consisting of only ones and no zeros.
Energy-based Out-of-Distribution Detection for Graph Neural Networks
This paves a way for a simple, powerful and efficient OOD detection model for GNN-based learning on graphs, which we call GNNSafe.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
HardSATGEN: Understanding the Difficulty of Hard SAT Formula Generation and A Strong Structure-Hardness-Aware Baseline
On top of the observations that industrial formulae exhibit clear community structure and oversplit substructures lead to the difficulty in semantic formation of logical structures, we propose HardSATGEN, which introduces a fine-grained control mechanism to the neural split-merge paradigm for SAT formula generation to better recover the structural and computational properties of the industrial benchmarks.
Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting
Utilizing DSW embedding and TSA layer, Crossformer establishes a Hierarchical Encoder-Decoder (HED) to use the information at different scales for the final forecasting.
DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion
Real-world data generation often involves complex inter-dependencies among instances, violating the IID-data hypothesis of standard learning paradigms and posing a challenge for uncovering the geometric structures for learning desired instance representations.
Policy Pre-training for Autonomous Driving via Self-supervised Geometric Modeling
Witnessing the impressive achievements of pre-training techniques on large-scale data in the field of computer vision and natural language processing, we wonder whether this idea could be adapted in a grab-and-go spirit, and mitigate the sample inefficiency problem for visuomotor driving.
Deep Learning of Partial Graph Matching via Differentiable Top-K
Graph matching (GM) aims at discovering node matching between graphs, by maximizing the node- and edge-wise affinities between the matched elements.
Ranked #1 on
Graph Matching
on Willow Object Class
(F1 score metric)
Distilling Focal Knowledge From Imperfect Expert for 3D Object Detection
Specifically, a set of queries are leveraged to locate the instance-level areas for masked feature generation, to intensify feature representation ability in these areas.
Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPs
Graph neural networks (GNNs), as the de-facto model class for representation learning on graphs, are built upon the multi-layer perceptrons (MLP) architecture with additional message passing layers to allow features to flow across nodes.
Localized Contrastive Learning on Graphs
Contrastive learning methods based on InfoNCE loss are popular in node representation learning tasks on graph-structured data.
Leveraging Angular Information Between Feature and Classifier for Long-tailed Learning: A Prediction Reformulation Approach
Deep neural networks still struggle on long-tailed image datasets, and one of the reasons is that the imbalance of training data across categories leads to the imbalance of trained model parameters.
Ranked #21 on
Long-tail Learning
on CIFAR-10-LT (ρ=10)
Rethinking and Improving Robustness of Convolutional Neural Networks: a Shapley Value-based Approach in Frequency Domain
In this work, we introduce Shapley value, a metric of cooperative game theory, into the frequency domain and propose to quantify the positive (negative) impact of every frequency component of data on CNNs.
Towards Out-of-Distribution Sequential Event Prediction: A Causal Treatment
The goal of sequential event prediction is to estimate the next event based on a sequence of historical events, with applications to sequential recommendation, user behavior analysis and clinical treatment.
Geometric Knowledge Distillation: Topology Compression for Graph Neural Networks
We study a new paradigm of knowledge transfer that aims at encoding graph topological information into graph neural networks (GNNs) by distilling knowledge from a teacher GNN model trained on a complete graph to a student GNN model operating on a smaller or sparser graph.
End-to-End Context-Aided Unicity Matching for Person Re-identification
Based on a natural assumption that images belonging to the same person identity should not match with images belonging to multiple different person identities across views, called the unicity of person matching on the identity level, we propose an end-to-end person unicity matching architecture for learning and refining the person matching relations.
Learning Universe Model for Partial Matching Networks over Multiple Graphs
We consider the general setting for partial matching of two or multiple graphs, in the sense that not necessarily all the nodes in one graph can find their correspondences in another graph and vice versa.
H2RBox: Horizontal Box Annotation is All You Need for Oriented Object Detection
Oriented object detection emerges in many applications from aerial images to autonomous driving, while many existing detection benchmarks are annotated with horizontal bounding box only which is also less costive than fine-grained rotated box, leading to a gap between the readily available training corpus and the rising demand for oriented object detection.
Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalization
Existing detection methods commonly use a parameterized bounding box (BBox) to model and detect (horizontal) objects and an additional rotation angle parameter is used for rotated objects.
ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning
In particular, we propose a spatial-temporal feature learning scheme towards a set of more representative features for perception, prediction and planning tasks simultaneously, which is called ST-P3.
Ranked #7 on
Bird's-Eye View Semantic Segmentation
on nuScenes
(IoU ped - 224x480 - Vis filter. - 100x100 at 0.5 metric)
Level 2 Autonomous Driving on a Single Device: Diving into the Devils of Openpilot
Equipped with a wide span of sensors, predominant autonomous driving solutions are becoming more modular-oriented for safe system design.
Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline
The two branches are connected so that the control branch receives corresponding guidance from the trajectory branch at each time step.
Ranked #3 on
Autonomous Driving
on CARLA Leaderboard
Learning Unbiased Transferability for Domain Adaptation by Uncertainty Modeling
However, due to the significant imbalance between the amount of annotated data in the source and target domains, usually only the target distribution is aligned to the source domain, leading to adapting unnecessary source specific knowledge to the target domain, i. e., biased domain adaptation.
CEP3: Community Event Prediction with Neural Point Process on Graph
Many real world applications can be formulated as event forecasting on Continuous Time Dynamic Graphs (CTDGs) where the occurrence of a timed event between two entities is represented as an edge along with its occurrence timestamp in the graphs. However, most previous works approach the problem in compromised settings, either formulating it as a link prediction task on the graph given the event time or a time prediction problem given which event will happen next.
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.
DOTIN: Dropping Task-Irrelevant Nodes for GNNs
Scalability is an important consideration for deep graph neural networks.
MMRotate: A Rotated Object Detection Benchmark using PyTorch
We present an open-source toolbox, named MMRotate, which provides a coherent algorithm framework of training, inferring, and evaluation for the popular rotated object detection algorithm based on deep learning.
MHSCNet: A Multimodal Hierarchical Shot-aware Convolutional Network for Video Summarization
However, the optimal video summaries need to reflect the most valuable keyframe with its own information, and one with semantic power of the whole content.
Modeling Dynamic User Preference via Dictionary Learning for Sequential Recommendation
Capturing the dynamics in user preference is crucial to better predict user future behaviors because user preferences often drift over time.
Learning Self-Modulating Attention in Continuous Time Space with Applications to Sequential Recommendation
User interests are usually dynamic in the real world, which poses both theoretical and practical challenges for learning accurate preferences from rich behavior data.
On Understanding and Mitigating the Dimensional Collapse of Graph Contrastive Learning: a Non-Maximum Removal Approach
Graph Contrastive Learning (GCL) has shown promising performance in graph representation learning (GRL) without the supervision of manual annotations.
PersFormer: 3D Lane Detection via Perspective Transformer and the OpenLane Benchmark
Methods for 3D lane detection have been recently proposed to address the issue of inaccurate lane layouts in many autonomous driving scenarios (uphill/downhill, bump, etc.).
Ranked #6 on
3D Lane Detection
on Apollo Synthetic 3D Lane
EAutoDet: Efficient Architecture Search for Object Detection
In contrast, this paper introduces an efficient framework, named EAutoDet, that can discover practical backbone and FPN architectures for object detection in 1. 4 GPU-days.
Ranked #32 on
Object Detection In Aerial Images
on DOTA
(using extra training data)
Object Localization under Single Coarse Point Supervision
In this study, we propose a POL method using coarse point annotations, relaxing the supervision signals from accurate key points to freely spotted points.
A Survey for Solving Mixed Integer Programming via Machine Learning
This paper surveys the trend of leveraging machine learning to solve mixed integer programming (MIP) problems.
Machine Learning Methods in Solving the Boolean Satisfiability Problem
This paper reviews the recent literature on solving the Boolean satisfiability problem (SAT), an archetypal NP-complete problem, with the help of machine learning techniques.
Learning Neural Hamiltonian Dynamics: A Methodological Overview
The past few years have witnessed an increased interest in learning Hamiltonian dynamics in deep learning frameworks.
Towards Machine Learning for Placement and Routing in Chip Design: a Methodological Overview
Placement and routing are two indispensable and challenging (NP-hard) tasks in modern chip design flows.
From Quantum Graph Computing to Quantum Graph Learning: A Survey
Quantum computing (QC) is a new computational paradigm whose foundations relate to quantum physics.
Molecule Generation for Drug Design: a Graph Learning Perspective
Machine learning, particularly graph learning, is gaining increasing recognition for its transformative impact across various fields.
Transformers in Time Series: A Survey
From the perspective of network structure, we summarize the adaptations and modifications that have been made to Transformers in order to accommodate the challenges in time series analysis.
Handling Distribution Shifts on Graphs: An Invariance Perspective
There is increasing evidence suggesting neural networks' sensitivity to distribution shifts, so that research on out-of-distribution (OOD) generalization comes into the spotlight.
GNNRank: Learning Global Rankings from Pairwise Comparisons via Directed Graph Neural Networks
In this paper, we introduce neural networks into the ranking recovery problem by proposing the so-called GNNRank, a trainable GNN-based framework with digraph embedding.
The KFIoU Loss for Rotated Object Detection
This is in contrast to recent Gaussian modeling based rotation detectors e. g. GWD loss and KLD loss that involve a human-specified distribution distance metric which require additional hyperparameter tuning that vary across datasets and detectors.
Towards Quantum Graph Neural Networks: An Ego-Graph Learning Approach
The architecture is based on a novel mapping from real-world data to Hilbert space.
Align Representations With Base: A New Approach to Self-Supervised Learning
Existing symmetric contrastive learning methods suffer from collapses (complete and dimensional) or quadratic complexity of objectives.
Appearance and Structure Aware Robust Deep Visual Graph Matching: Attack, Defense and Beyond
We first show that an adversarial attack on keypoint localities and the hidden graphs can cause significant accuracy drop to deep GM models.
Ranked #7 on
Graph Matching
on PASCAL VOC
(matching accuracy metric)
Optimal LED Spectral Multiplexing for NIR2RGB Translation
The industry practice for night video surveillance is to use auxiliary near-infrared (NIR) LED diodes, usually centered at 850nm or 940nm, for scene illumination.
A General Framework for Evaluating Robustness of Combinatorial Optimization Solvers on Graphs
Solving combinatorial optimization (CO) on graphs is among the fundamental tasks for upper-stream applications in data mining, machine learning and operations research.
GRIN: Generative Relation and Intention Network for Multi-agent Trajectory Prediction
Learning the distribution of future trajectories conditioned on the past is a crucial problem for understanding multi-agent systems.
AlphaRotate: A Rotation Detection Benchmark using TensorFlow
AlphaRotate is an open-source Tensorflow benchmark for performing scalable rotation detection on various datasets.
On Joint Learning for Solving Placement and Routing in Chip Design
To achieve end-to-end placement learning, we first propose a joint learning method termed by DeepPlace for the placement of macros and standard cells, by the integration of reinforcement learning with a gradient based optimization scheme.
ZARTS: On Zero-order Optimization for Neural Architecture Search
Also, we search on the search space of DARTS to compare with peer methods, and our discovered architecture achieves 97. 54% accuracy on CIFAR-10 and 75. 7% top-1 accuracy on ImageNet, which are state-of-the-art performance.
Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach
We target open-world feature extrapolation problem where the feature space of input data goes through expansion and a model trained on partially observed features needs to handle new features in test data without further retraining.
DAAS: Differentiable Architecture and Augmentation Policy Search
Neural architecture search (NAS) has been an active direction of automatic machine learning (Auto-ML), aiming to explore efficient network structures.
On the Expressiveness, Predictability and Interpretability of Neural Temporal Point Processes
Despite the fast advance in neural temporal point processes (NTPP) which enjoys high model capacity, there are still some standing gaps to fill including model expressiveness, predictability, and interpretability, especially with the wide application of event sequence modeling.
Zero-CL: Instance and Feature decorrelation for negative-free symmetric contrastive learning
The proposed two methods (FCL, ICL) can be combined synthetically, called Zero-CL, where ``Zero'' means negative samples are \textbf{zero} relevant, which allows Zero-CL to completely discard negative pairs i. e., with \textbf{zero} negative samples.
$m$-mix: Generating hard negatives via multiple samples mixing for contrastive learning
Negative pairs are essential in contrastive learning, which plays the role of avoiding degenerate solutions.