Search Results for author:
Found 114 papers, 53 papers with code
PillarNeSt: Embracing Backbone Scaling and Pretraining for Pillar-based 3D Object Detection
Pillar-based methods mainly employ randomly initialized 2D convolution neural network (ConvNet) for feature extraction and fail to enjoy the benefits from the backbone scaling and pretraining in the image domain.
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.
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
Bird's-Eye View Semantic Segmentation
on nuScenes
(IoU lane - 224x480 - 100x100 at 0.5 metric)
cosFormer: Rethinking Softmax in Attention
As one of its core components, the softmax attention helps to capture long-range dependencies yet prohibits its scale-up due to the quadratic space and time complexity to the sequence length.
Ranked #4 on
Offline RL
on D4RL
One to Transfer All: A Universal Transfer Framework for Vision Foundation Model with Few Data
Transferring with few data in a general way to thousands of downstream tasks is becoming a trend of the foundation model's application.
INTERN: A New Learning Paradigm Towards General Vision
Enormous waves of technological innovations over the past several years, marked by the advances in AI technologies, are profoundly reshaping the industry and the society.
MQBench: Towards Reproducible and Deployable Model Quantization Benchmark
Surprisingly, no existing algorithm wins every challenge in MQBench, and we hope this work could inspire future research directions.
Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm
Recently, large-scale Contrastive Language-Image Pre-training (CLIP) has attracted unprecedented attention for its impressive zero-shot recognition ability and excellent transferability to downstream tasks.
BN-NAS: Neural Architecture Search with Batch Normalization
We present BN-NAS, neural architecture search with Batch Normalization (BN-NAS), to accelerate neural architecture search (NAS).
PSViT: Better Vision Transformer via Token Pooling and Attention Sharing
Then, a compact set of the possible combinations for different token pooling and attention sharing mechanisms are constructed.
Geometry Uncertainty Projection Network for Monocular 3D Object Detection
In this paper, we propose a Geometry Uncertainty Projection Network (GUP Net) to tackle the error amplification problem at both inference and training stages.
3D Object Detection From Monocular Images
Depth Estimation
+3
GLiT: Neural Architecture Search for Global and Local Image Transformer
We introduce the first Neural Architecture Search (NAS) method to find a better transformer architecture for image recognition.
Ranked #498 on
Image Classification
on ImageNet
GAIA: A Transfer Learning System of Object Detection that Fits Your Needs
Transfer learning with pre-training on large-scale datasets has played an increasingly significant role in computer vision and natural language processing recently.
AutoSampling: Search for Effective Data Sampling Schedules
Data sampling acts as a pivotal role in training deep learning models.
Efficient Transfer Learning via Joint Adaptation of Network Architecture and Weight
Transfer learning can boost the performance on the targettask by leveraging the knowledge of the source domain.
Temporal Context Aggregation Network for Temporal Action Proposal Refinement
In this paper, we propose Temporal Context Aggregation Network (TCANet) to generate high-quality action proposals through "local and global" temporal context aggregation and complementary as well as progressive boundary refinement.
Ranked #9 on
Temporal Action Localization
on ActivityNet-1.3
Higher Performance Visual Tracking with Dual-Modal Localization
Visual Object Tracking (VOT) has synchronous needs for both robustness and accuracy.
Real-Time Visual Object Tracking via Few-Shot Learning
Visual Object Tracking (VOT) can be seen as an extended task of Few-Shot Learning (FSL).
Learning Statistical Texture for Semantic Segmentation
In this paper, we fully take advantages of the low-level texture features and propose a novel Statistical Texture Learning Network (STLNet) for semantic segmentation.
Inter-class Discrepancy Alignment for Face Recognition
In this study, we make a key observation that the local con-text represented by the similarities between the instance and its inter-class neighbors1plays an important role forFR.
Inception Convolution with Efficient Dilation Search
To develop a practical method for learning complex inception convolution based on the data, a simple but effective search algorithm, referred to as efficient dilation optimization (EDO), is developed.
DETR for Crowd Pedestrian Detection
Furthermore, the bipartite match of ED harms the training efficiency due to the large ground truth number in crowd scenes.
Context-Aware Graph Convolution Network for Target Re-identification
Most existing re-identification methods focus on learning robust and discriminative features with deep convolution networks.
PV-NAS: Practical Neural Architecture Search for Video Recognition
Recently, deep learning has been utilized to solve video recognition problem due to its prominent representation ability.
Adaptive Gradient Method with Resilience and Momentum
Several variants of stochastic gradient descent (SGD) have been proposed to improve the learning effectiveness and efficiency when training deep neural networks, among which some recent influential attempts would like to adaptively control the parameter-wise learning rate (e. g., Adam and RMSProp).
Once Quantization-Aware Training: High Performance Extremely Low-bit Architecture Search
Therefore, we propose to combine Network Architecture Search methods with quantization to enjoy the merits of the two sides.
Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks
To facilitate the training, we represent the network connectivity of each sample in an adjacency matrix.
Improving Auto-Augment via Augmentation-Wise Weight Sharing
On CIFAR-10, we achieve a top-1 error rate of 1. 24%, which is currently the best performing single model without extra training data.
Once Quantized for All: Progressively Searching for Quantized Compact Models
Automatic search of Quantized Neural Networks (QNN) has attracted a lot of attention.
MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection
In this paper, we propose MimicDet, a novel and efficient framework to train a one-stage detector by directly mimic the two-stage features, aiming to bridge the accuracy gap between one-stage and two-stage detectors.
BSN++: Complementary Boundary Regressor with Scale-Balanced Relation Modeling for Temporal Action Proposal Generation
In this paper, we present BSN++, a new framework which exploits complementary boundary regressor and relation modeling for temporal proposal generation.
Collaborative Distillation in the Parameter and Spectrum Domains for Video Action Recognition
Second, the parameter frequency distribution is further adopted to guide the student network to learn the appearance modeling process from the teacher.
Learning Connectivity of Neural Networks from a Topological Perspective
In this paper, we attempt to optimize the connectivity in neural networks.
CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations
The main reason is that current face anti-spoofing datasets are limited in both quantity and diversity.
Complementary Boundary Generator with Scale-Invariant Relation Modeling for Temporal Action Localization: Submission to ActivityNet Challenge 2020
Specifically, in order to generate high-quality proposals, we consider several factors including the video feature encoder, the proposal generator, the proposal-proposal relations, the scale imbalance, and ensemble strategy.
Class-wise Dynamic Graph Convolution for Semantic Segmentation
Specifically, the CDGC module takes the coarse segmentation result as class mask to extract node features for graph construction and performs dynamic graph convolutions on the constructed graph to learn the feature aggregation and weight allocation.
Powering One-shot Topological NAS with Stabilized Share-parameter Proxy
Specifically, the difficulties for architecture searching in such a complex space has been eliminated by the proposed stabilized share-parameter proxy, which employs Stochastic Gradient Langevin Dynamics to enable fast shared parameter sampling, so as to achieve stabilized measurement of architecture performance even in search space with complex topological structures.
Large-Scale Object Detection in the Wild from Imbalanced Multi-Labels
Training with more data has always been the most stable and effective way of improving performance in deep learning era.
COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification
To address the clothes changing person re-id problem, we construct a novel large-scale re-id benchmark named ClOthes ChAnging Person Set (COCAS), which provides multiple images of the same identity with different clothes.
DMCP: Differentiable Markov Channel Pruning for Neural Networks
In DMCP, we model the channel pruning as a Markov process, in which each state represents for retaining the corresponding channel during pruning, and transitions between states denote the pruning process.
1st Place Solutions for OpenImage2019 -- Object Detection and Instance Segmentation
Given such good instance bounding box, we further design a simple instance-level semantic segmentation pipeline and achieve the 1st place on the segmentation challenge.
Top-1 Solution of Multi-Moments in Time Challenge 2019
In this technical report, we briefly introduce the solutions of our team 'Efficient' for the Multi-Moments in Time challenge in ICCV 2019.
Equalization Loss for Long-Tailed Object Recognition
Based on it, we propose a simple but effective loss, named equalization loss, to tackle the problem of long-tailed rare categories by simply ignoring those gradients for rare categories.
Ranked #17 on
Long-tail Learning
on CIFAR-10-LT (ρ=10)
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.
Cross-dataset Training for Class Increasing Object Detection
Given two or more already labeled datasets that target for different object classes, cross-dataset training aims to detect the union of the different classes, so that we do not have to label all the classes for all the datasets.
Towards Unified INT8 Training for Convolutional Neural Network
In this paper, we give an attempt to build a unified 8-bit (INT8) training framework for common convolutional neural networks from the aspects of both accuracy and speed.
Computation Reallocation for Object Detection
However, classification allocation pattern is usually adopted directly to object detector, which is proved to be sub-optimal.
Efficient Neural Architecture Transformation Search in Channel-Level for Object Detection
Instead of searching and constructing an entire network, NATS explores the architecture space on the base of existing network and reusing its weights.
Equalization Loss for Large Vocabulary Instance Segmentation
Recent object detection and instance segmentation tasks mainly focus on datasets with a relatively small set of categories, e. g. Pascal VOC with 20 classes and COCO with 80 classes.
Improving One-shot NAS by Suppressing the Posterior Fading
In this paper, we analyse existing weight sharing one-shot NAS approaches from a Bayesian point of view and identify the posterior fading problem, which compromises the effectiveness of shared weights.
Diving into Optimization of Topology in Neural Networks
Seeking effective networks has become one of the most crucial and practical areas in deep learning.
CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval
Text-image cross-modal retrieval is a challenging task in the field of language and vision.
Ranked #9 on
Image Retrieval
on Flickr30K 1K test
Efficient Neural Architecture Transformation Searchin Channel-Level for Object Detection
With the combination of these two designs, an architecture transformation scheme could be discovered to adapt a network designed for image classification to task of object detection.
POD: Practical Object Detection with Scale-Sensitive Network
Scale-sensitive object detection remains a challenging task, where most of the existing methods could not learn it explicitly and are not robust to scale variance.
Towards Flops-constrained Face Recognition
Large scale face recognition is challenging especially when the computational budget is limited.
Differentiable Soft Quantization: Bridging Full-Precision and Low-Bit Neural Networks
Hardware-friendly network quantization (e. g., binary/uniform quantization) can efficiently accelerate the inference and meanwhile reduce memory consumption of the deep neural networks, which is crucial for model deployment on resource-limited devices like mobile phones.
STM: SpatioTemporal and Motion Encoding for Action Recognition
Spatiotemporal and motion features are two complementary and crucial information for video action recognition.
Ranked #1 on
Action Recognition In Videos
on HMDB-51
Learning to Auto Weight: Entirely Data-driven and Highly Efficient Weighting Framework
Example weighting algorithm is an effective solution to the training bias problem, however, most previous typical methods are usually limited to human knowledge and require laborious tuning of hyperparameters.
Online Hyper-parameter Learning for Auto-Augmentation Strategy
Data augmentation is critical to the success of modern deep learning techniques.
AM-LFS: AutoML for Loss Function Search
The key contribution of this work is the design of search space which can guarantee the generalization and transferability on different vision tasks by including a bunch of existing prevailing loss functions in a unified formulation.
P2SGrad: Refined Gradients for Optimizing Deep Face Models
Cosine-based softmax losses significantly improve the performance of deep face recognition networks.
PRUNING WITH HINTS: AN EFFICIENT FRAMEWORK FOR MODEL ACCELERATION
Hints can improve the performance of student model by transferring knowledge from teacher model.
Learning to Cluster Faces on an Affinity Graph
Face recognition sees remarkable progress in recent years, and its performance has reached a very high level.
Video Generation from Single Semantic Label Map
This paper proposes the novel task of video generation conditioned on a SINGLE semantic label map, which provides a good balance between flexibility and quality in the generation process.
Dynamic Multi-path Neural Network
Although deeper and larger neural networks have achieved better performance, the complex network structure and increasing computational cost cannot meet the demands of many resource-constrained applications.
WIDER Face and Pedestrian Challenge 2018: Methods and Results
This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian.
Dynamic Curriculum Learning for Imbalanced Data Classification
Human attribute analysis is a challenging task in the field of computer vision, since the data is largely imbalance-distributed.
Multi-Object Tracking with Multiple Cues and Switcher-Aware Classification
In this paper, we propose a unified Multi-Object Tracking (MOT) framework learning to make full use of long term and short term cues for handling complex cases in MOT scenes.
SiamRPN++: Evolution of Siamese Visual Tracking with Very Deep Networks
Moreover, we propose a new model architecture to perform depth-wise and layer-wise aggregations, which not only further improves the accuracy but also reduces the model size.
Ranked #5 on
Visual Object Tracking
on VOT2017/18
IRLAS: Inverse Reinforcement Learning for Architecture Search
Motivated by the fact that human-designed networks are elegant in topology with a fast inference speed, we propose a mirror stimuli function inspired by biological cognition theory to extract the abstract topological knowledge of an expert human-design network (ResNeXt).
An Embarrassingly Simple Approach for Knowledge Distillation
Knowledge Distillation (KD) aims at improving the performance of a low-capacity student model by inheriting knowledge from a high-capacity teacher model.
Grid R-CNN
This paper proposes a novel object detection framework named Grid R-CNN, which adopts a grid guided localization mechanism for accurate object detection.
Ranked #9 on
2D Object Detection
on SARDet-100K
Synaptic Strength For Convolutional Neural Network
Inspired by the relevant concept in neural science literature, we propose Synaptic Pruning: a data-driven method to prune connections between input and output feature maps with a newly proposed class of parameters called Synaptic Strength.
Multi-Label Image Classification via Knowledge Distillation from Weakly-Supervised Detection
Specifically, given the image-level annotations, (1) we first develop a weakly-supervised detection (WSD) model, and then (2) construct an end-to-end multi-label image classification framework augmented by a knowledge distillation module that guides the classification model by the WSD model according to the class-level predictions for the whole image and the object-level visual features for object RoIs.
Ranked #9 on
Multi-Label Classification
on NUS-WIDE
Consensus-Driven Propagation in Massive Unlabeled Data for Face Recognition
Face recognition has witnessed great progress in recent years, mainly attributed to the high-capacity model designed and the abundant labeled data collected.
Fully Motion-Aware Network for Video Object Detection
Video objection detection is challenging in the presence of appearance deterioration in certain video frames.
Localization Guided Learning for Pedestrian Attribute Recognition
Pedestrian attribute recognition has attracted many attentions due to its wide applications in scene understanding and person analysis from surveillance videos.
Distractor-aware Siamese Networks for Visual Object Tracking
During the off-line training phase, an effective sampling strategy is introduced to control this distribution and make the model focus on the semantic distractors.
Ranked #11 on
Visual Object Tracking
on VOT2017/18
BlockQNN: Efficient Block-wise Neural Network Architecture Generation
The block-wise generation brings unique advantages: (1) it yields state-of-the-art results in comparison to the hand-crafted networks on image classification, particularly, the best network generated by BlockQNN achieves 2. 35% top-1 error rate on CIFAR-10.
Eliminating Background-Bias for Robust Person Re-Identification
State-of-the-art methods mainly utilize deep learning based approaches for learning visual features for describing person appearances.
High Performance Visual Tracking With Siamese Region Proposal Network
Visual object tracking has been a fundamental topic in recent years and many deep learning based trackers have achieved state-of-the-art performance on multiple benchmarks.
Ranked #7 on
Visual Object Tracking
on VOT2017/18
FaceID-GAN: Learning a Symmetry Three-Player GAN for Identity-Preserving Face Synthesis
Existing methods typically formulate GAN as a two-player game, where a discriminator distinguishes face images from the real and synthesized domains, while a generator reduces its discriminativeness by synthesizing a face of photo-realistic quality.
Quantization Mimic: Towards Very Tiny CNN for Object Detection
To the best of our knowledge, our method, called Quantization Mimic, is the first one focusing on very tiny networks.
Beyond Trade-off: Accelerate FCN-based Face Detector with Higher Accuracy
Fully convolutional neural network (FCN) has been dominating the game of face detection task for a few years with its congenital capability of sliding-window-searching with shared kernels, which boiled down all the redundant calculation, and most recent state-of-the-art methods such as Faster-RCNN, SSD, YOLO and FPN use FCN as their backbone.
Exploring Disentangled Feature Representation Beyond Face Identification
This paper proposes learning disentangled but complementary face features with minimal supervision by face identification.
Deep Cocktail Network: Multi-source Unsupervised Domain Adaptation with Category Shift
Motivated by the theoretical results in \cite{mansour2009domain}, the target distribution can be represented as the weighted combination of source distributions, and, the multi-source unsupervised domain adaptation via DCTN is then performed as two alternating steps: i) It deploys multi-way adversarial learning to minimize the discrepancy between the target and each of the multiple source domains, which also obtains the source-specific perplexity scores to denote the possibilities that a target sample belongs to different source domains.
Multi-Source Unsupervised Domain Adaptation
Unsupervised Domain Adaptation
Accelerated Training for Massive Classification via Dynamic Class Selection
Massive classification, a classification task defined over a vast number of classes (hundreds of thousands or even millions), has become an essential part of many real-world systems, such as face recognition.
FOTS: Fast Oriented Text Spotting with a Unified Network
Incidental scene text spotting is considered one of the most difficult and valuable challenges in the document analysis community.
Ranked #4 on
Scene Text Detection
on ICDAR 2017 MLT
Impression Network for Video Object Detection
Video object detection is more challenging compared to image object detection.
Peephole: Predicting Network Performance Before Training
The quest for performant networks has been a significant force that drives the advancements of deep learning in recent years.
End-to-end Flow Correlation Tracking with Spatial-temporal Attention
Discriminative correlation filters (DCF) with deep convolutional features have achieved favorable performance in recent tracking benchmarks.
Orientation Invariant Feature Embedding and Spatial Temporal Regularization for Vehicle Re-Identification
In our vehicle ReID framework, an orientation invariant feature embedding module and a spatial-temporal regularization module are proposed.
HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis
Pedestrian analysis plays a vital role in intelligent video surveillance and is a key component for security-centric computer vision systems.
Ranked #2 on
Pedestrian Attribute Recognition
on RAP
Practical Block-wise Neural Network Architecture Generation
Convolutional neural networks have gained a remarkable success in computer vision.
Recurrent Scale Approximation for Object Detection in CNN
To further increase efficiency and accuracy, we (a): design a scale-forecast network to globally predict potential scales in the image since there is no need to compute maps on all levels of the pyramid.
Ranked #3 on
Face Detection
on Annotated Faces in the Wild
Spindle Net: Person Re-Identification With Human Body Region Guided Feature Decomposition and Fusion
Person re-identification (ReID) is an important task in video surveillance and has various applications.
Mimicking Very Efficient Network for Object Detection
More specifically, we conduct a mimic method for the features sampled from the entire feature map and use a transform layer to map features from the small network onto the same dimension of the large network.
Quality Aware Network for Set to Set Recognition
In this paper, the quality aware network (QAN) is proposed to confront this problem, where the quality of each sample can be automatically learned although such information is not explicitly provided in the training stage.
Ranked #6 on
Face Verification
on YouTube Faces DB
Object Detection in Videos with Tubelet Proposal Networks
Object detection in videos has drawn increasing attention recently with the introduction of the large-scale ImageNet VID dataset.
POI: Multiple Object Tracking with High Performance Detection and Appearance Feature
In this paper, we explore the high-performance detection and deep learning based appearance feature, and show that they lead to significantly better MOT results in both online and offline setting.
Crafting GBD-Net for Object Detection
The effectiveness of GBD-Net is shown through experiments on three object detection datasets, ImageNet, Pascal VOC2007 and Microsoft COCO.
Joint Training of Cascaded CNN for Face Detection
Cascade has been widely used in face detection, where classifier with low computation cost can be firstly used to shrink most of the background while keeping the recall.
CRAFT Objects from Images
They decompose the object detection problem into two cascaded easier tasks: 1) generating object proposals from images, 2) classifying proposals into various object categories.
T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
Temporal and contextual information of videos are not fully investigated and utilized.
Object Detection by Labeling Superpixels
Object detection is always conducted by object proposal generation and classification sequentially.
High-Fidelity Pose and Expression Normalization for Face Recognition in the Wild
Pose and expression normalization is a crucial step to recover the canonical view of faces under arbitrary conditions, so as to improve the face recognition performance.
Convolutional Channel Features
With the combination of CNN features and boosting forest, CCF benefits from the richer capacity in feature representation compared with channel features, as well as lower cost in computation and storage compared with end-to-end CNN methods.
To Make a Robot Secure: An Experimental Analysis of Cyber Security Threats Against Teleoperated Surgical Robots
Our work seeks to answer this question by systematically analyzing possible cyber security attacks against Raven II, an advanced teleoperated robotic surgery system.
Robotics Cryptography and Security
Aggregate channel features for multi-view face detection
Face detection has drawn much attention in recent decades since the seminal work by Viola and Jones.
Ranked #37 on
Face Detection
on WIDER Face (Medium)
Multiple Target Tracking Based on Undirected Hierarchical Relation Hypergraph
Multi-target tracking is an interesting but challenging task in computer vision field.
The Fastest Deformable Part Model for Object Detection
Three prohibitive steps in cascade version of DPM are accelerated, including 2D correlation between root filter and feature map, cascade part pruning and HOG feature extraction.
Robust Multi-resolution Pedestrian Detection in Traffic Scenes
The model contains resolution aware transformations to map pedestrians in different resolutions to a common space, where a shared detector is constructed to distinguish pedestrians from background.
