Search Results for author:
Found 40 papers, 16 papers with code
Learning Attentive and Hierarchical Representations for 3D Shape Recognition
This paper proposes a novel method for 3D shape representation learning, namely Hyperbolic Embedded Attentive Representation (HEAR).
Adaptive Learning of Consistency and Inconsistency Information for Fake News Detection
Most of fake news detection research focused on integrating text and image information to represent the consistency of multiple modes in news content, while paying less attention to inconsistent information.
AdaLog: Post-Training Quantization for Vision Transformers with Adaptive Logarithm Quantizer
To address these issues, we propose a novel non-uniform quantizer, dubbed the Adaptive Logarithm AdaLog (AdaLog) quantizer.
iVPT: Improving Task-relevant Information Sharing in Visual Prompt Tuning by Cross-layer Dynamic Connection
It innovatively incorporates a cross-layer dynamic connection (CDC) for input prompt tokens from adjacent layers, enabling effective sharing of task-relevant information.
Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model
The direct preference optimization (DPO) method, effective in fine-tuning large language models, eliminates the necessity for a reward model.
The NeurIPS 2022 Neural MMO Challenge: A Massively Multiagent Competition with Specialization and Trade
In this paper, we present the results of the NeurIPS-2022 Neural MMO Challenge, which attracted 500 participants and received over 1, 600 submissions.
Benchmarking Robustness and Generalization in Multi-Agent Systems: A Case Study on Neural MMO
We present the results of the second Neural MMO challenge, hosted at IJCAI 2022, which received 1600+ submissions.
DR-Tune: Improving Fine-tuning of Pretrained Visual Models by Distribution Regularization with Semantic Calibration
Furthermore, to alleviate the interference by semantic drift, we develop the semantic calibration (SC) module to align the global shape and class centers of the pretrained and downstream feature distributions.
CTP-Net: Character Texture Perception Network for Document Image Forgery Localization
We design a Character Texture Stream (CTS) based on optical character recognition to capture features of text areas that are essential components of a document image.
Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images
Object detection on drone images with low-latency is an important but challenging task on the resource-constrained unmanned aerial vehicle (UAV) platform.
OcTr: Octree-based Transformer for 3D Object Detection
A key challenge for LiDAR-based 3D object detection is to capture sufficient features from large scale 3D scenes especially for distant or/and occluded objects.
Recon: Reducing Conflicting Gradients from the Root for Multi-Task Learning
Our experiments show that such a simple approach can greatly reduce the occurrence of conflicting gradients in the remaining shared layers and achieve better performance, with only a slight increase in model parameters in many cases.
Emergent collective intelligence from massive-agent cooperation and competition
Since these learned group strategies arise from individual decisions without an explicit coordination mechanism, we claim that artificial collective intelligence emerges from massive-agent cooperation and competition.
Multi-Agent Path Finding via Tree LSTM
In recent years, Multi-Agent Path Finding (MAPF) has attracted attention from the fields of both Operations Research (OR) and Reinforcement Learning (RL).
SHREC'22 Track: Sketch-Based 3D Shape Retrieval in the Wild
We define two SBSR tasks and construct two benchmarks consisting of more than 46, 000 CAD models, 1, 700 realistic models, and 145, 000 sketches in total.
Representation Learning for Compressed Video Action Recognition via Attentive Cross-modal Interaction with Motion Enhancement
To address the two issues above, this paper proposes a novel framework, namely Attentive Cross-modal Interaction Network with Motion Enhancement (MEACI-Net).
Entropy-based Active Learning for Object Detection with Progressive Diversity Constraint
Active learning is a promising alternative to alleviate the issue of high annotation cost in the computer vision tasks by consciously selecting more informative samples to label.
Target-Relevant Knowledge Preservation for Multi-Source Domain Adaptive Object Detection
Specifically, TRKP adopts the teacher-student framework, where the multi-head teacher network is built to extract knowledge from labeled source domains and guide the student network to learn detectors in unlabeled target domain.
CAT-Det: Contrastively Augmented Transformer for Multi-modal 3D Object Detection
In autonomous driving, LiDAR point-clouds and RGB images are two major data modalities with complementary cues for 3D object detection.
UFPMP-Det: Toward Accurate and Efficient Object Detection on Drone Imagery
This paper proposes a novel approach to object detection on drone imagery, namely Multi-Proxy Detection Network with Unified Foreground Packing (UFPMP-Det).
Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima
Our study shows that existing methods severely suffer from catastrophic forgetting, a well-known problem in incremental learning, which is aggravated due to data scarcity and imbalance in the few-shot setting.
Ranked #8 on
Few-Shot Class-Incremental Learning
on mini-Imagenet
Effectiveness of Pre-training for Few-shot Intent Classification
This paper investigates the effectiveness of pre-training for few-shot intent classification.
Adaptation-Agnostic Meta-Training
Many meta-learning algorithms can be formulated into an interleaved process, in the sense that task-specific predictors are learned during inner-task adaptation and meta-parameters are updated during meta-update.
PR-GCN: A Deep Graph Convolutional Network with Point Refinement for 6D Pose Estimation
This paper proposes a novel deep learning approach, namely Graph Convolutional Network with Point Refinement (PR-GCN), to simultaneously address the issues above in a unified way.
Video Person Re-identification using Attribute-enhanced Features
Video-based person re-identification (Re-ID) which aims to associate people across non-overlapping cameras using surveillance video is a challenging task.
Learning Multi-Granular Hypergraphs for Video-Based Person Re-Identification
In each hypergraph, different temporal granularities are captured by hyperedges that connect a set of graph nodes (i. e., part-based features) across different temporal ranges.
Ranked #6 on
Person Re-Identification
on iLIDS-VID
Learning Multi-Attention Context Graph for Group-Based Re-Identification
Extensive experiments on the novel dataset as well as three existing datasets clearly demonstrate the effectiveness of the proposed framework for both group-based re-id tasks.
A Closer Look at the Training Strategy for Modern Meta-Learning
The support/query (S/Q) episodic training strategy has been widely used in modern meta-learning algorithms and is believed to improve their generalization ability to test environments.
Deep Adversarial Domain Adaptation Based on Multi-layer Joint Kernelized Distance
In this paper, a deep adversarial domain adaptation model based on a multi-layer joint kernelized distance metric is proposed.
Adaptive Energy Management for Real Driving Conditions via Transfer Reinforcement Learning
This article proposes a transfer reinforcement learning (RL) based adaptive energy managing approach for a hybrid electric vehicle (HEV) with parallel topology.
Transferred Energy Management Strategies for Hybrid Electric Vehicles Based on Driving Conditions Recognition
Energy management strategies (EMSs) are the most significant components in hybrid electric vehicles (HEVs) because they decide the potential of energy conservation and emission reduction.
Auto-Encoding Twin-Bottleneck Hashing
One bottleneck (i. e., binary codes) conveys the high-level intrinsic data structure captured by the code-driven graph to the other (i. e., continuous variables for low-level detail information), which in turn propagates the updated network feedback for the encoder to learn more discriminative binary codes.
Variational Metric Scaling for Metric-Based Meta-Learning
In this paper, we recast metric-based meta-learning from a Bayesian perspective and develop a variational metric scaling framework for learning a proper metric scaling parameter.
Embarrassingly Simple Binary Representation Learning
Recent binary representation learning models usually require sophisticated binary optimization, similarity measure or even generative models as auxiliaries.
Deep Sketch-Shape Hashing With Segmented 3D Stochastic Viewing
Sketch-based 3D shape retrieval has been extensively studied in recent works, most of which focus on improving the retrieval accuracy, whilst neglecting the efficiency.
Deep Cross-modality Adaptation via Semantics Preserving Adversarial Learning for Sketch-based 3D Shape Retrieval
Due to the large cross-modality discrepancy between 2D sketches and 3D shapes, retrieving 3D shapes by sketches is a significantly challenging task.
Scale Optimization for Full-Image-CNN Vehicle Detection
By selecting better scales in the region proposal input and by combining feature maps through careful design of the convolutional neural network, we improve performance on smaller objects.
Unsupervised Multi-Domain Image Translation with Domain-Specific Encoders/Decoders
Unsupervised Image-to-Image Translation achieves spectacularly advanced developments nowadays.
Zero-Shot Action Recognition With Error-Correcting Output Codes
Our ZSECOC equips the conventional ECOC with the additional capability of ZSAR, by addressing the domain shift problem.
Ranked #4 on
Zero-Shot Action Recognition
on Olympics
Fast Person Re-Identification via Cross-Camera Semantic Binary Transformation
Numerous methods have been proposed for person re-identification, most of which however neglect the matching efficiency.
