Search Results for author:
Found 42 papers, 19 papers with code
Topology-Preserving Class-Incremental Learning
A well-known issue for class-incremental learning is the catastrophic forgetting phenomenon, where the network's recognition performance on old classes degrades severely when incrementally learning new classes.
Driving with Prior Maps: Unified Vector Prior Encoding for Autonomous Vehicle Mapping
High-Definition Maps (HD maps) are essential for the precise navigation and decision-making of autonomous vehicles, yet their creation and upkeep present significant cost and timeliness challenges.
Neural Spectral Decomposition for Dataset Distillation
We aim to discover the low-rank representation of the entire dataset and perform distillation efficiently.
Positional Prompt Tuning for Efficient 3D Representation Learning
Together with the sequential Transformer, the whole module with position encoding comprehensively constructs a multi-scale feature abstraction module that considers both the local parts from the patch and the global parts from center points as position encoding.
Ranked #1 on
3D Parameter-Efficient Fine-Tuning for Classification
on ModelNet40
(Overall Accuracy metric)
3D Parameter-Efficient Fine-Tuning for Classification
3D Point Cloud Classification
+4
Projecting Points to Axes: Oriented Object Detection via Point-Axis Representation
This paper introduces the point-axis representation for oriented object detection, emphasizing its flexibility and geometrically intuitive nature with two key components: points and axes.
Is a 3D-Tokenized LLM the Key to Reliable Autonomous Driving?
Despite its simplicity, Atlas demonstrates superior performance in both 3D detection and ego planning tasks on nuScenes dataset, proving that 3D-tokenized LLM is the key to reliable autonomous driving.
Curriculum Dataset Distillation
Most dataset distillation methods struggle to accommodate large-scale datasets due to their substantial computational and memory requirements.
Few-shot Online Anomaly Detection and Segmentation
Recent research in this domain has emphasized the necessity of a large volume of training data, overlooking the practical scenario where, post-deployment of the model, unlabeled data containing both normal and abnormal samples can be utilized to enhance the model's performance.
CEAT: Continual Expansion and Absorption Transformer for Non-Exemplar Class-Incremental Learning
Besides, to address the classifier bias towards the new classes, we propose a novel approach to generate the pseudo-features to correct the classifier.
DYSON: Dynamic Feature Space Self-Organization for Online Task-Free Class Incremental Learning
Then we propose a novel Dynamic feature space Self-Organization (DYSON) method containing three major components including 1) a feature extractor 2) a Dynamic Feature-Geometry Alignment (DFGA) module aligning the feature space to the optimal geometry computed by DNC and 3) a training-free class-incremental classifier derived from the DNC geometry.
Person-in-WiFi 3D: End-to-End Multi-Person 3D Pose Estimation with Wi-Fi
This paper takes a step forward by introducing Person-in-WiFi 3D a pioneering Wi-Fi system that accomplishes multi-person 3D pose estimation.
ARTrackV2: Prompting Autoregressive Tracker Where to Look and How to Describe
We present ARTrackV2, which integrates two pivotal aspects of tracking: determining where to look (localization) and how to describe (appearance analysis) the target object across video frames.
Ranked #1 on
Visual Object Tracking
on NeedForSpeed
MachMap: End-to-End Vectorized Solution for Compact HD-Map Construction
This report introduces the 1st place winning solution for the Autonomous Driving Challenge 2023 - Online HD-map Construction.
Knowledge Restore and Transfer for Multi-label Class-Incremental Learning
Current class-incremental learning research mainly focuses on single-label classification tasks while multi-label class-incremental learning (MLCIL) with more practical application scenarios is rarely studied.
Deep Dynamic Scene Deblurring from Optical Flow
In this paper, we explore optical flow to remove dynamic scene blur by using the multi-scale spatially variant recurrent neural network (RNN).
Autoregressive Visual Tracking
We present ARTrack, an autoregressive framework for visual object tracking.
Ranked #1 on
Visual Tracking
on TNL2K
Learning Symmetry-Aware Geometry Correspondences for 6D Object Pose Estimation
Taking the symmetry properties of objects into consideration, we design a symmetry-aware matching loss to facilitate the learning of dense point-wise geometry features and improve the performance considerably.
DKT: Diverse Knowledge Transfer Transformer for Class Incremental Learning
Deep neural networks suffer from catastrophic forgetting in class incremental learning, where the classification accuracy of old classes drastically deteriorates when the networks learn the knowledge of new classes.
IR2Net: Information Restriction and Information Recovery for Accurate Binary Neural Networks
In contrast, considering the limited learning ability and information loss caused by the limited representational capability of BNNs, we propose IR$^2$Net to stimulate the potential of BNNs and improve the network accuracy by restricting the input information and recovering the feature information, including: 1) information restriction: for a BNN, by evaluating the learning ability on the input information, discarding some of the information it cannot focus on, and limiting the amount of input information to match its learning ability; 2) information recovery: due to the information loss in forward propagation, the output feature information of the network is not enough to support accurate classification.
End-to-End Multi-Person Pose Estimation With Transformers
Current methods of multi-person pose estimation typically treat the localization and association of body joints separately.
Scene-Adaptive Attention Network for Crowd Counting
First of all, we design a deformable attention in-built Transformer backbone, which learns adaptive feature representations with deformable sampling locations and dynamic attention weights.
SOIT: Segmenting Objects with Instance-Aware Transformers
The pixel-wise mask, especially, is embedded by a group of parameters to construct a lightweight instance-aware transformer.
Online Continual Learning via Multiple Deep Metric Learning and Uncertainty-guided Episodic Memory Replay -- 3rd Place Solution for ICCV 2021 Workshop SSLAD Track 3A Continual Object Classification
Online continual learning in the wild is a very difficult task in machine learning.
Anomaly Detection via Self-organizing Map
Anomaly detection plays a key role in industrial manufacturing for product quality control.
Ranked #55 on
Anomaly Detection
on MVTec AD
InsPose: Instance-Aware Networks for Single-Stage Multi-Person Pose Estimation
Multi-person pose estimation is an attractive and challenging task.
Ranked #4 on
Multi-Person Pose Estimation
on COCO minival
Direct Measure Matching for Crowd Counting
Second, we derive a semi-balanced form of Sinkhorn divergence, based on which a Sinkhorn counting loss is designed for measure matching.
Know Your Surroundings: Panoramic Multi-Object Tracking by Multimodality Collaboration
In this paper, we focus on the multi-object tracking (MOT) problem of automatic driving and robot navigation.
Self-Distribution Binary Neural Networks
In this work, we study the binary neural networks (BNNs) of which both the weights and activations are binary (i. e., 1-bit representation).
Efficient Deep Image Denoising via Class Specific Convolution
In this paper, we propose an efficient deep neural network for image denoising based on pixel-wise classification.
Towards a Universal Model for Cross-Dataset Crowd Counting
This paper proposes to handle the practical problem of learning a universal model for crowd counting across scenes and datasets.
UCP: Uniform Channel Pruning for Deep Convolutional Neural Networks Compression and Acceleration
For ResNet with bottlenecks, we use the pruning method with traditional CNN to trim the 3x3 convolutional layer in the middle of the blocks.
Inertial and gravity wave transmissions near radiative-convective boundaries
Two configurations have been considered: waves propagate from the convective layer to the radiative stratified stable layer, or In this paper, we study inertial and gravity wave transmissions near radiative-convective boundaries on the {\it f}-plane.
Fluid Dynamics Solar and Stellar Astrophysics
Few-Shot Class-Incremental Learning
FSCIL requires CNN models to incrementally learn new classes from very few labelled samples, without forgetting the previously learned ones.
Ranked #9 on
Few-Shot Class-Incremental Learning
on CIFAR-100
(Average Accuracy metric)
Beyond Universal Person Re-ID Attack
We propose a \emph{more universal} adversarial perturbation (MUAP) method for both image-agnostic and model-insensitive person Re-ID attack.
Person Re-identification in Aerial Imagery
Our method can learn a discriminative and compact feature representation for ReID in aerial imagery and can be trained in an end-to-end fashion efficiently.
Bayesian Loss for Crowd Count Estimation with Point Supervision
In crowd counting datasets, each person is annotated by a point, which is usually the center of the head.
Reinforcement Learning Based Emotional Editing Constraint Conversation Generation
In recent years, the generation of conversation content based on deep neural networks has attracted many researchers.
Downhole Track Detection via Multiscale Conditional Generative Adversarial Nets
A multiscale shared convolution structure is adopted in the discriminator network to further supervise training the generator.
Embedding Electronic Health Records for Clinical Information Retrieval
Neural network representation learning frameworks have recently shown to be highly effective at a wide range of tasks ranging from radiography interpretation via data-driven diagnostics to clinical decision support.
Grassmann Pooling as Compact Homogeneous Bilinear Pooling for Fine-Grained Visual Classification
The reason is that the bilinear feature matrix is sensitive to the magnitudes and correlations of local CNN feature elements which can be measured by its singular values.
Fine-Grained Image Classification
Fine-Grained Visual Recognition
+1
Kernelized Subspace Pooling for Deep Local Descriptors
Experimental results on several patch matching benchmarks show that our method outperforms the state-of-the-arts significantly.
Superpixel Hierarchy
Quantitative and qualitative evaluation on a number of computer vision applications was conducted, demonstrating that the proposed method is the top performer.
