Search Results for author:
Found 144 papers, 85 papers with code
Detecting Backdoors in Pre-trained Encoders
We show the effectiveness of our method on image encoders pre-trained on ImageNet and OpenAI's CLIP 400 million image-text pairs.
Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection
In this paper, we propose a long-sequence modeling framework, named StreamPETR, for multi-view 3D object detection.
VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking
Our core insight is to predict objects directly based on sparse voxel features, without relying on hand-crafted proxies.
Ranked #1 on
3D Object Detection
on Argoverse2
Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perception
In this paper, we explore an embarrassingly simple long-term recurrent fusion strategy built upon the LSS-based methods and find it already able to enjoy the merits from both sides, i. e., rich long-term information and efficient fusion pipeline.
Referring Multi-Object Tracking
In this paper, we propose a new and general referring understanding task, termed referring multi-object tracking (RMOT).
Contrast with Reconstruct: Contrastive 3D Representation Learning Guided by Generative Pretraining
This motivates us to learn 3D representations by sharing the merits of both paradigms, which is non-trivial due to the pattern difference between the two paradigms.
Ranked #1 on
Few-Shot 3D Point Cloud Classification
on ModelNet40 5-way (10-shot)
(using extra training data)
3D Point Cloud Linear Classification
Few-Shot 3D Point Cloud Classification
+2
KNOD: Domain Knowledge Distilled Tree Decoder for Automated Program Repair
KNOD has two major novelties, including (1) a novel three-stage tree decoder, which directly generates Abstract Syntax Trees of patched code according to the inherent tree structure, and (2) a novel domain-rule distillation, which leverages syntactic and semantic rules and teacher-student distributions to explicitly inject the domain knowledge into the decoding procedure during both the training and inference phases.
Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attacks
We improve adversarial robustness against physical-world attacks using L0-norm-bounded perturbation in training.
BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense
Attack forensics, a critical counter-measure for traditional cyber attacks, is hence of importance for defending model backdoor attacks.
Cross Modal Transformer: Towards Fast and Robust 3D Object Detection
In this paper, we propose a robust 3D detector, named Cross Modal Transformer (CMT), for end-to-end 3D multi-modal detection.
Understanding Imbalanced Semantic Segmentation Through Neural Collapse
Based on our empirical and theoretical analysis, we point out that semantic segmentation naturally brings contextual correlation and imbalanced distribution among classes, which breaks the equiangular and maximally separated structure of neural collapse for both feature centers and classifiers.
Reversible Column Networks
Such architectural scheme attributes RevCol very different behavior from conventional networks: during forward propagation, features in RevCol are learned to be gradually disentangled when passing through each column, whose total information is maintained rather than compressed or discarded as other network does.
Ranked #7 on
Object Detection
on COCO minival
(using extra training data)
Backdoor Vulnerabilities in Normally Trained Deep Learning Models
We leverage 20 different types of injected backdoor attacks in the literature as the guidance and study their correspondences in normally trained models, which we call natural backdoor vulnerabilities.
Near-Field Channel Estimation for Extremely Large-Scale Array Communications: A model-based deep learning approach
In particular, we first formulate the XL-MIMO near-field channel estimation task as a compressed sensing problem using the spatial gridding-based sparsifying dictionary, and then solve the resulting problem by applying the Learning Iterative Shrinkage and Thresholding Algorithm (LISTA).
Twin-S: A Digital Twin for Skull-base Surgery
Twin-S tracks and updates the virtual model in real-time given measurements from modern tracking technologies.
MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception
This paper proposes an efficient multi-camera to Bird's-Eye-View (BEV) view transformation method for 3D perception, dubbed MatrixVT.
MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors
In this paper, we propose MOTRv2, a simple yet effective pipeline to bootstrap end-to-end multi-object tracking with a pretrained object detector.
Ranked #1 on
Multi-Object Tracking
on DanceTrack
(using extra training data)
Towards 3D Object Detection with 2D Supervision
We propose a temporal 2D transformation to bridge the 3D predictions with temporal 2D labels.
The 1st-place Solution for ECCV 2022 Multiple People Tracking in Group Dance Challenge
We present our 1st place solution to the Group Dance Multiple People Tracking Challenge.
Multi-Object Tracking
Multiple Object Tracking with Transformer
+1
FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning
In this work, we theoretically analyze the connection among cross-entropy loss, attack success rate, and clean accuracy in this setting.
A New Approach to Extract Fetal Electrocardiogram Using Affine Combination of Adaptive Filters
Compared with the state-of-the-art MSF-ANC method, CRLS shows improved performance.
From Model-Based to Model-Free: Learning Building Control for Demand Response
We demonstrate, in this context, that hybrid methods offer many benefits over both purely model-free and model-based methods as long as certain requirements are met.
PQLM -- Multilingual Decentralized Portable Quantum Language Model for Privacy Protection
In this work, we propose a highly Portable Quantum Language Model (PQLM) that can easily transmit information to downstream tasks on classical machines.
End-to-End Lyrics Recognition with Self-supervised Learning
Lyrics recognition is an important task in music processing.
Differentiable Architecture Search with Random Features
Differentiable architecture search (DARTS) has significantly promoted the development of NAS techniques because of its high search efficiency and effectiveness but suffers from performance collapse.
Ranked #11 on
Neural Architecture Search
on NAS-Bench-201, CIFAR-10
Understanding Masked Image Modeling via Learning Occlusion Invariant Feature
Recently, Masked Image Modeling (MIM) achieves great success in self-supervised visual recognition.
Revisiting the Critical Factors of Augmentation-Invariant Representation Learning
We focus on better understanding the critical factors of augmentation-invariant representation learning.
Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches
Experimental results show that our method can generate stealthy, effective, and robust adversarial patches for different target objects and models and achieves more than 6 meters mean depth estimation error and 93% attack success rate (ASR) in object detection with a patch of 1/9 of the vehicle's rear area.
Robust Watermarking for Video Forgery Detection with Improved Imperceptibility and Robustness
We jointly train a 3D-UNet-based watermark embedding network and a decoder that predicts the tampering mask.
LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs
Recent advance in 2D CNNs has revealed that large kernels are important.
DECK: Model Hardening for Defending Pervasive Backdoors
As such, using the samples derived from our attack in adversarial training can harden a model against these backdoor vulnerabilities.
PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images
More specifically, we extend the 3D position embedding (3D PE) in PETR for temporal modeling.
Ranked #2 on
3D Lane Detection
on OpenLane
Re-parameterizing Your Optimizers rather than Architectures
For the extreme simplicity of model structure, we focus on a VGG-style plain model and showcase that such a simple model trained with a RepOptimizer, which is referred to as RepOpt-VGG, performs on par with or better than the recent well-designed models.
Self-Supervised Visual Representation Learning with Semantic Grouping
The semantic grouping is performed by assigning pixels to a set of learnable prototypes, which can adapt to each sample by attentive pooling over the feature and form new slots.
Ranked #6 on
Unsupervised Semantic Segmentation
on COCO-Stuff-27
GL-RG: Global-Local Representation Granularity for Video Captioning
Video captioning is a challenging task as it needs to accurately transform visual understanding into natural language description.
Focal Sparse Convolutional Networks for 3D Object Detection
In this paper, we introduce two new modules to enhance the capability of Sparse CNNs, both are based on making feature sparsity learnable with position-wise importance prediction.
When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search
TNAS performs a modified bi-level Breadth-First Search in the proposed trees to discover a high-performance architecture.
Simple Baselines for Image Restoration
Although there have been significant advances in the field of image restoration recently, the system complexity of the state-of-the-art (SOTA) methods is increasing as well, which may hinder the convenient analysis and comparison of methods.
Ranked #1 on
Deblurring
on MSU BASED
Near-optimality for infinite-horizon restless bandits with many arms
Although an average-case-optimal policy can be computed via stochastic dynamic programming, the computation required grows exponentially with the number of arms $N$.
Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation
The tree energy loss is effective and easy to be incorporated into existing frameworks by combining it with a traditional segmentation loss.
Progressive End-to-End Object Detection in Crowded Scenes
Experiments show that our method can significantly boost the performance of query-based detectors in crowded scenes.
Ranked #2 on
Object Detection
on CrowdHuman (full body)
Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs
We revisit large kernel design in modern convolutional neural networks (CNNs).
Ranked #65 on
Image Classification
on ImageNet
(using extra training data)
PETR: Position Embedding Transformation for Multi-View 3D Object Detection
Object query can perceive the 3D position-aware features and perform end-to-end object detection.
Curriculum-based Reinforcement Learning for Distribution System Critical Load Restoration
This paper focuses on the critical load restoration problem in distribution systems following major outages.
Constrained Optimization with Dynamic Bound-scaling for Effective NLPBackdoor Defense
We develop a novel optimization method for NLPbackdoor inversion.
Relieving Long-tailed Instance Segmentation via Pairwise Class Balance
In this paper, we explore to excavate the confusion matrix, which carries the fine-grained misclassification details, to relieve the pairwise biases, generalizing the coarse one.
Communication-Efficient TeraByte-Scale Model Training Framework for Online Advertising
In this paper, we propose a hardware-aware training workflow that couples the hardware topology into the algorithm design.
Better Trigger Inversion Optimization in Backdoor Scanning
A popular trigger inversion method is by optimization.
Bounded Adversarial Attack on Deep Content Features
We propose a novel adversarial attack targeting content features in some deep layer, that is, individual neurons in the layer.
Complex Backdoor Detection by Symmetric Feature Differencing
Our results on the TrojAI competition rounds 2-4, which have patch backdoors and filter backdoors, show that existing scanners may produce hundreds of false positives (i. e., clean models recognized as trojaned), while our technique removes 78-100% of them with a small increase of false negatives by 0-30%, leading to 17-41% overall accuracy improvement.
RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality
Our results reveal that 1) Locality Injection is a general methodology for MLP models; 2) RepMLPNet has favorable accuracy-efficiency trade-off compared to the other MLPs; 3) RepMLPNet is the first MLP that seamlessly transfer to Cityscapes semantic segmentation.
Ranked #52 on
Semantic Segmentation
on Cityscapes val
On Efficient Transformer-Based Image Pre-training for Low-Level Vision
Pre-training has marked numerous state of the arts in high-level computer vision, while few attempts have ever been made to investigate how pre-training acts in image processing systems.
Implicit Feature Refinement for Instance Segmentation
Our IFR enjoys several advantages: 1) simulates an infinite-depth refinement network while only requiring parameters of single residual block; 2) produces high-level equilibrium instance features of global receptive field; 3) serves as a plug-and-play general module easily extended to most object recognition frameworks.
Two-step Lookahead Bayesian Optimization with Inequality Constraints
Recent advances in computationally efficient non-myopic Bayesian optimization (BO) improve query efficiency over traditional myopic methods like expected improvement while only modestly increasing computational cost.
Spherical Motion Dynamics: Learning Dynamics of Normalized Neural Network using SGD and Weight Decay
Specifically, 1) we introduce the assumptions that can lead to equilibrium state in SMD, and prove equilibrium can be reached in a linear rate regime under given assumptions; 2) we propose ``angular update" as a substitute for effective learning rate to depict the state of SMD, and derive the theoretical value of angular update in equilibrium state; 3) we verify our assumptions and theoretical results on various large-scale computer vision tasks including ImageNet and MSCOCO with standard settings.
Constrained Two-step Look-Ahead Bayesian Optimization
Recent advances in computationally efficient non-myopic Bayesian optimization offer improved query efficiency over traditional myopic methods like expected improvement, with only a modest increase in computational cost.
PowerGridworld: A Framework for Multi-Agent Reinforcement Learning in Power Systems
We present the PowerGridworld software package to provide users with a lightweight, modular, and customizable framework for creating power-systems-focused, multi-agent Gym environments that readily integrate with existing training frameworks for reinforcement learning (RL).
Multi-agent Reinforcement Learning
reinforcement-learning
+1
A Comparison of Model-Free and Model Predictive Control for Price Responsive Water Heaters
We demonstrate that optimal control for this problem is challenging, requiring more than 8-hour lookahead for MPC with perfect forecasting to attain the minimum cost.
Instance-Conditional Knowledge Distillation for Object Detection
Knowledge distillation has shown great success in classification, however, it is still challenging for detection.
Raw Bayer Pattern Image Synthesis for Computer Vision-oriented Image Signal Processing Pipeline Design
It is shown that by adding another transformation, the proposed method is able to synthesize high-quality RAW Bayer images with arbitrary size.
RWN: Robust Watermarking Network for Image Cropping Localization
At the recipient's side, ACP extracts the watermark from the attacked image, and we conduct feature matching on the original and extracted watermark to locate the position of the crop in the original image plane.
Partial to Whole Knowledge Distillation: Progressive Distilling Decomposed Knowledge Boosts Student Better
Knowledge distillation field delicately designs various types of knowledge to shrink the performance gap between compact student and large-scale teacher.
LGD: Label-guided Self-distillation for Object Detection
Instead, we generate an instructive knowledge based only on student representations and regular labels.
Image Synthesis via Semantic Composition
In this paper, we present a novel approach to synthesize realistic images based on their semantic layouts.
Anchor DETR: Query Design for Transformer-Based Object Detection
Thanks to the query design and the attention variant, the proposed detector that we called Anchor DETR, can achieve better performance and run faster than the DETR with 10$\times$ fewer training epochs.
Accelerating Markov Random Field Inference with Uncertainty Quantification
In this paper, we propose a high-throughput accelerator for Markov Random Field (MRF) inference, a powerful model for representing a wide range of applications, using MCMC with Gibbs sampling.
Restless Bandits with Many Arms: Beating the Central Limit Theorem
Thus, there is substantial value in understanding the performance of index policies and other policies that can be computed efficiently for large $N$.
The Threat of Offensive AI to Organizations
Although offensive AI has been discussed in the past, there is a need to analyze and understand the threat in the context of organizations.
SOLQ: Segmenting Objects by Learning Queries
Moreover, the joint learning of unified query representation can greatly improve the detection performance of DETR.
Ranked #4 on
Object Detection
on COCO minival
(AP75 metric)
Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report
A detailed description of all models developed in the challenge is provided in this paper.
MOTR: End-to-End Multiple-Object Tracking with Transformer
Temporal modeling of objects is a key challenge in multiple object tracking (MOT).
Ranked #6 on
Multi-Object Tracking
on DanceTrack
RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition
We propose RepMLP, a multi-layer-perceptron-style neural network building block for image recognition, which is composed of a series of fully-connected (FC) layers.
Ranked #663 on
Image Classification
on ImageNet
Points as Queries: Weakly Semi-supervised Object Detection by Points
We propose a novel point annotated setting for the weakly semi-supervised object detection task, in which the dataset comprises small fully annotated images and large weakly annotated images by points.
Joint User Association and Power Allocation in Heterogeneous Ultra Dense Network via Semi-Supervised Representation Learning
We model the HUDNs as a heterogeneous graph and train a Graph Neural Network (GNN) to approach this representation function by using semi-supervised learning, in which the loss function is composed of the unsupervised part that helps the GNN approach the optimal representation function and the supervised part that utilizes the previous experience to reduce useless exploration.
Diverse Branch Block: Building a Convolution as an Inception-like Unit
We propose a universal building block of Convolutional Neural Network (ConvNet) to improve the performance without any inference-time costs.
You Only Look One-level Feature
From the perspective of optimization, we introduce an alternative way to address the problem instead of adopting the complex feature pyramids - {\em utilizing only one-level feature for detection}.
Ranked #28 on
Object Detection
on COCO test-dev
EX-RAY: Distinguishing Injected Backdoor from Natural Features in Neural Networks by Examining Differential Feature Symmetry
A prominent challenge is hence to distinguish natural features and injected backdoors.
Backdoor Scanning for Deep Neural Networks through K-Arm Optimization
By iteratively and stochastically selecting the most promising labels for optimization with the guidance of an objective function, we substantially reduce the complexity, allowing to handle models with many classes.
Neural Architecture Search with Random Labels
In this paper, we investigate a new variant of neural architecture search (NAS) paradigm -- searching with random labels (RLNAS).
RepVGG: Making VGG-style ConvNets Great Again
We present a simple but powerful architecture of convolutional neural network, which has a VGG-like inference-time body composed of nothing but a stack of 3x3 convolution and ReLU, while the training-time model has a multi-branch topology.
Ranked #35 on
Semantic Segmentation
on Cityscapes val
Implicit Feature Pyramid Network for Object Detection
In this paper, we present an implicit feature pyramid network (i-FPN) for object detection.
Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification
Trojan (backdoor) attack is a form of adversarial attack on deep neural networks where the attacker provides victims with a model trained/retrained on malicious data.
Rethinking Learnable Tree Filter for Generic Feature Transform
The Learnable Tree Filter presents a remarkable approach to model structure-preserving relations for semantic segmentation.
Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detection
Object detectors usually achieve promising results with the supervision of complete instance annotations.
Microlensing Predictions: Impact of Galactic Disc Dynamical Models
Additionally, we find the asymptotic power-law behaviors in both $\theta_{\rm E}$ and $\pi_{\rm E}$ distributions, and we provide a simple model to understand them.
Astrophysics of Galaxies Earth and Planetary Astrophysics Solar and Stellar Astrophysics
Joint COCO and Mapillary Workshop at ICCV 2019: COCO Instance Segmentation Challenge Track
In this report, we present our object detection/instance segmentation system, MegDetV2, which works in a two-pass fashion, first to detect instances then to obtain segmentation.
EqCo: Equivalent Rules for Self-supervised Contrastive Learning
In this paper, we propose EqCo (Equivalent Rules for Contrastive Learning) to make self-supervised learning irrelevant to the number of negative samples in the contrastive learning framework.
MPG-Net: Multi-Prediction Guided Network for Segmentation of Retinal Layers in OCT Images
In this paper, we propose a novel multiprediction guided attention network (MPG-Net) for automated retinal layer segmentation in OCT images.
Deep Learning & Software Engineering: State of Research and Future Directions
The intent of this report is to serve as a potential roadmap to guide future work that sits at the intersection of SE & DL.
Activate or Not: Learning Customized Activation
We present a simple, effective, and general activation function we term ACON which learns to activate the neurons or not.
Black-box Adversarial Sample Generation Based on Differential Evolution
The technique does not require any knowledge of the structure or weights of the target DNN.
WeightNet: Revisiting the Design Space of Weight Networks
WeightNet is easy and memory-conserving to train, on the kernel space instead of the feature space.
Funnel Activation for Visual Recognition
We present a conceptually simple but effective funnel activation for image recognition tasks, called Funnel activation (FReLU), that extends ReLU and PReLU to a 2D activation by adding a negligible overhead of spatial condition.
LabelEnc: A New Intermediate Supervision Method for Object Detection
In this paper we propose a new intermediate supervision method, named LabelEnc, to boost the training of object detection systems.
Weight-dependent Gates for Network Pruning
In this paper, a simple yet effective network pruning framework is proposed to simultaneously address the problems of pruning indicator, pruning ratio, and efficiency constraint.
Spherical Motion Dynamics: Learning Dynamics of Neural Network with Normalization, Weight Decay, and SGD
In this work, we comprehensively reveal the learning dynamics of neural network with normalization, weight decay (WD), and SGD (with momentum), named as Spherical Motion Dynamics (SMD).
D-square-B: Deep Distribution Bound for Natural-looking Adversarial Attack
We propose a novel technique that can generate natural-looking adversarial examples by bounding the variations induced for internal activation values in some deep layer(s), through a distribution quantile bound and a polynomial barrier loss function.
Exhaustive goodness-of-fit via smoothed inference and graphics
Classical tests of goodness-of-fit aim to validate the conformity of a postulated model to the data under study.
Methodology Statistics Theory Applications Statistics Theory
Joint Multi-Dimension Pruning via Numerical Gradient Update
To tackle these three naturally different dimensions, we proposed a general framework by defining pruning as seeking the best pruning vector (i. e., the numerical value of layer-wise channel number, spacial size, depth) and construct a unique mapping from the pruning vector to the pruned network structures.
Angle-based Search Space Shrinking for Neural Architecture Search
Comprehensive experiments show that ABS can dramatically enhance existing NAS approaches by providing a promising shrunk search space.
Dynamic Scale Training for Object Detection
We propose a Dynamic Scale Training paradigm (abbreviated as DST) to mitigate scale variation challenge in object detection.
Towards Feature Space Adversarial Attack
We propose a new adversarial attack to Deep Neural Networks for image classification.
Personalized Re-ranking for Improving Diversity in Live Recommender Systems
To overcome such limitation, our re-ranking model proposes a personalized DPP to model the trade-off between accuracy and diversity for each individual user.
Attentive Normalization for Conditional Image Generation
Traditional convolution-based generative adversarial networks synthesize images based on hierarchical local operations, where long-range dependency relation is implicitly modeled with a Markov chain.
Learning Human-Object Interaction Detection using Interaction Points
Human-object interaction (HOI) detection strives to localize both the human and an object as well as the identification of complex interactions between them.
Dynamic Region-Aware Convolution
More gracefully, our DRConv transfers the increasing channel-wise filters to spatial dimension with learnable instructor, which not only improve representation ability of convolution, but also maintains computational cost and the translation-invariance as standard convolution dose.
Ranked #4 on
Semantic Segmentation
on MCubeS
Learning Dynamic Routing for Semantic Segmentation
To demonstrate the superiority of the dynamic property, we compare with several static architectures, which can be modeled as special cases in the routing space.
Detection in Crowded Scenes: One Proposal, Multiple Predictions
We propose a simple yet effective proposal-based object detector, aiming at detecting highly-overlapped instances in crowded scenes.
Ranked #2 on
Pedestrian Detection
on TJU-Ped-campus
PointINS: Point-based Instance Segmentation
In this paper, we explore the mask representation in instance segmentation with Point-of-Interest (PoI) features.
Learning Delicate Local Representations for Multi-Person Pose Estimation
To tackle this problem, we propose an efficient attention mechanism - Pose Refine Machine (PRM) to make a trade-off between local and global representations in output features and further refine the keypoint locations.
Ranked #1 on
Keypoint Detection
on COCO
Beyond Application End-Point Results: Quantifying Statistical Robustness of MCMC Accelerators
Applying the framework to guide design space exploration shows that statistical robustness comparable to floating-point software can be achieved by slightly increasing the bit representation, without floating-point hardware requirements.
Towards Stabilizing Batch Statistics in Backward Propagation of Batch Normalization
Therefore many modified normalization techniques have been proposed, which either fail to restore the performance of BN completely, or have to introduce additional nonlinear operations in inference procedure and increase huge consumption.
Learning-Accelerated ADMM for Distributed Optimal Power Flow
We propose a novel data-driven method to accelerate the convergence of Alternating Direction Method of Multipliers (ADMM) for solving distributed DC optimal power flow (DC-OPF) where lines are shared between independent network partitions.
A Case for Quantifying Statistical Robustness of Specialized Probabilistic AI Accelerators
Although a common approach is to compare the end-point result quality using community-standard benchmarks and metrics, we claim a probabilistic architecture should provide some measure (or guarantee) of statistical robustness.
Resizable Neural Networks
We introduce the adaptive resizable networks as dynamic networks, which further improve the performance with less computational cost via data-dependent inference.
VAENAS: Sampling Matters in Neural Architecture Search
In this paper, we propose a learnable sampling module based on variational auto-encoder (VAE) for neural architecture search (NAS), named as VAENAS, which can be easily embedded into existing weight sharing NAS framework, e. g., one-shot approach and gradient-based approach, and significantly improve the performance of searching results.
Testing Deep Learning Models for Image Analysis Using Object-Relevant Metamorphic Relations
The corresponding rate for the object detection models is over 8. 5%.
Arbitrage of Energy Storage in Electricity Markets with Deep Reinforcement Learning
In this letter, we address the problem of controlling energy storage systems (ESSs) for arbitrage in real-time electricity markets under price uncertainty.
Single Path One-Shot Neural Architecture Search with Uniform Sampling
It is easy to train and fast to search.
Ranked #88 on
Neural Architecture Search
on ImageNet
(Accuracy metric)
DetNAS: Backbone Search for Object Detection
In this work, we present DetNAS to use Neural Architecture Search (NAS) for the design of better backbones for object detection.
MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning
In this paper, we propose a novel meta learning approach for automatic channel pruning of very deep neural networks.
Meta-SR: A Magnification-Arbitrary Network for Super-Resolution
In this work, we propose a novel method called Meta-SR to firstly solve super-resolution of arbitrary scale factor (including non-integer scale factors) with a single model.
Daedalus: Breaking Non-Maximum Suppression in Object Detection via Adversarial Examples
Experimental results demonstrate that the attack effectively stops NMS from filtering redundant bounding boxes.
Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples
Results show that our technique can achieve 94% detection accuracy for 7 different kinds of attacks with 9. 91% false positives on benign inputs.
Bounding Box Regression with Uncertainty for Accurate Object Detection
Large-scale object detection datasets (e. g., MS-COCO) try to define the ground truth bounding boxes as clear as possible.
Ranked #21 on
Object Detection
on PASCAL VOC 2007
DetNet: Design Backbone for Object Detection
(1) Recent object detectors like FPN and RetinaNet usually involve extra stages against the task of image classification to handle the objects with various scales.
An Open Access Database for Evaluating the Algorithms of Electrocardiogram Rhythm and Morphology Abnormality Detection
Over the past few decades, methods for classification and detection of rhythm or morphology abnormalities in ECG signals have been widely studied.
ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
Datasets, Transforms and Models specific to Computer Vision
Ranked #772 on
Image Classification
on ImageNet
MetaAnchor: Learning to Detect Objects with Customized Anchors
We propose a novel and flexible anchor mechanism named MetaAnchor for object detection frameworks.
CrowdHuman: A Benchmark for Detecting Human in a Crowd
There are a total of $470K$ human instances from the train and validation subsets, and $~22. 6$ persons per image, with various kinds of occlusions in the dataset.
Ranked #5 on
Pedestrian Detection
on Caltech
(using extra training data)
DetNet: A Backbone network for Object Detection
Due to the gap between the image classification and object detection, we propose DetNet in this paper, which is a novel backbone network specifically designed for object detection.
ExFuse: Enhancing Feature Fusion for Semantic Segmentation
Modern semantic segmentation frameworks usually combine low-level and high-level features from pre-trained backbone convolutional models to boost performance.
Ranked #3 on
Semantic Segmentation
on PASCAL VOC 2012 val
(using extra training data)
MegDet: A Large Mini-Batch Object Detector
The improvements in recent CNN-based object detection works, from R-CNN [11], Fast/Faster R-CNN [10, 31] to recent Mask R-CNN [14] and RetinaNet [24], mainly come from new network, new framework, or novel loss design.
Light-Head R-CNN: In Defense of Two-Stage Object Detector
More importantly, simply replacing the backbone with a tiny network (e. g, Xception), our Light-Head R-CNN gets 30. 7 mmAP at 102 FPS on COCO, significantly outperforming the single-stage, fast detectors like YOLO and SSD on both speed and accuracy.
Channel Pruning for Accelerating Very Deep Neural Networks
In this paper, we introduce a new channel pruning method to accelerate very deep convolutional neural networks. Given a trained CNN model, we propose an iterative two-step algorithm to effectively prune each layer, by a LASSO regression based channel selection and least square reconstruction.
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices
We introduce an extremely computation-efficient CNN architecture named ShuffleNet, which is designed specially for mobile devices with very limited computing power (e. g., 10-150 MFLOPs).
Ranked #77 on
Person Re-Identification
on DukeMTMC-reID
Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Network
One of recent trends [30, 31, 14] in network architec- ture design is stacking small filters (e. g., 1x1 or 3x3) in the entire network because the stacked small filters is more ef- ficient than a large kernel, given the same computational complexity.
Ranked #7 on
Semantic Segmentation
on PASCAL VOC 2012 val
Identity Mappings in Deep Residual Networks
Deep residual networks have emerged as a family of extremely deep architectures showing compelling accuracy and nice convergence behaviors.
Ranked #16 on
Image Classification
on Kuzushiji-MNIST
Deep Residual Learning for Image Recognition
Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
Accelerating Very Deep Convolutional Networks for Classification and Detection
This paper aims to accelerate the test-time computation of convolutional neural networks (CNNs), especially very deep CNNs that have substantially impacted the computer vision community.
Object Detection Networks on Convolutional Feature Maps
We discover that aside from deep feature maps, a deep and convolutional per-region classifier is of particular importance for object detection, whereas latest superior image classification models (such as ResNets and GoogLeNets) do not directly lead to good detection accuracy without using such a per-region classifier.
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
In this work, we study rectifier neural networks for image classification from two aspects.
Efficient and Accurate Approximations of Nonlinear Convolutional Networks
This paper aims to accelerate the test-time computation of deep convolutional neural networks (CNNs).
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
This requirement is "artificial" and may reduce the recognition accuracy for the images or sub-images of an arbitrary size/scale.
Ranked #25 on
Object Detection
on PASCAL VOC 2007
