Search Results for author:
Found 86 papers, 61 papers with code
Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation
On the other hand, JPMA is proposed to assemble multiple hypotheses generated by D3DP into a single 3D pose for practical use.
Masked Image Modeling with Local Multi-Scale Reconstruction
The lower layers are not explicitly guided and the interaction among their patches is only used for calculating new activations.
Redistribution of Weights and Activations for AdderNet Quantization
To this end, we first thoroughly analyze the difference on distributions of weights and activations in AdderNet and then propose a new quantization algorithm by redistributing the weights and the activations.
FastMIM: Expediting Masked Image Modeling Pre-training for Vision
This paper presents FastMIM, a simple and generic framework for expediting masked image modeling with the following two steps: (i) pre-training vision backbones with low-resolution input images; and (ii) reconstructing Histograms of Oriented Gradients (HOG) feature instead of original RGB values of the input images.
GhostNetV2: Enhance Cheap Operation with Long-Range Attention
The convolutional operation can only capture local information in a window region, which prevents performance from being further improved.
Novel Class Discovery without Forgetting
Inspired by this, we identify and formulate a new, pragmatic problem setting of NCDwF: Novel Class Discovery without Forgetting, which tasks a machine learning model to incrementally discover novel categories of instances from unlabeled data, while maintaining its performance on the previously seen categories.
Network Amplification With Efficient MACs Allocation
In particular, the proposed method is used to enlarge models sourced by GhostNet, we achieve state-of-the-art 80. 9% and 84. 3% ImageNet top-1 accuracies under the setting of 600M and 4. 4B MACs, respectively.
Vision GNN: An Image is Worth Graph of Nodes
In this paper, we propose to represent the image as a graph structure and introduce a new Vision GNN (ViG) architecture to extract graph-level feature for visual tasks.
Ranked #319 on
Image Classification
on ImageNet
Spacing Loss for Discovering Novel Categories
Novel Class Discovery (NCD) is a learning paradigm, where a machine learning model is tasked to semantically group instances from unlabeled data, by utilizing labeled instances from a disjoint set of classes.
JIFF: Jointly-aligned Implicit Face Function for High Quality Single View Clothed Human Reconstruction
In this paper, we focus on improving the quality of face in the reconstruction and propose a novel Jointly-aligned Implicit Face Function (JIFF) that combines the merits of the implicit function based approach and model based approach.
SharpContour: A Contour-based Boundary Refinement Approach for Efficient and Accurate Instance Segmentation
Contour-based models are efficient and generic to be incorporated with any existing segmentation methods, but they often generate over-smoothed contour and tend to fail on corner areas.
GhostNets on Heterogeneous Devices via Cheap Operations
The proposed C-Ghost module can be taken as a plug-and-play component to upgrade existing convolutional neural networks.
Generalized Category Discovery
Here, the unlabelled images may come from labelled classes or from novel ones.
Ranked #1 on
Open-World Semi-Supervised Learning
on CIFAR-10
(Seen accuracy (50% Labeled) metric)
Fine-Grained Visual Recognition
Open-World Semi-Supervised Learning
+1
PyramidTNT: Improved Transformer-in-Transformer Baselines with Pyramid Architecture
We hope this new baseline will be helpful to the further research and application of vision transformer.
Instance-Aware Dynamic Neural Network Quantization
However, natural images are of huge diversity with abundant content and using such a universal quantization configuration for all samples is not an optimal strategy.
An Image Patch is a Wave: Phase-Aware Vision MLP
To dynamically aggregate tokens, we propose to represent each token as a wave function with two parts, amplitude and phase.
Open-Set Recognition: a Good Closed-Set Classifier is All You Need?
In this paper, we first demonstrate that the ability of a classifier to make the 'none-of-above' decision is highly correlated with its accuracy on the closed-set classes.
Ranked #10 on
Out-of-Distribution Detection
on CIFAR-100 vs CIFAR-10
Symmetry-Enhanced Attention Network for Acute Ischemic Infarct Segmentation with Non-Contrast CT Images
In this paper, we propose a symmetry enhanced attention network (SEAN) for acute ischemic infarct segmentation.
Learning Versatile Convolution Filters for Efficient Visual Recognition
A series of secondary filters can be derived from a primary filter with the help of binary masks.
Hire-MLP: Vision MLP via Hierarchical Rearrangement
Previous vision MLPs such as MLP-Mixer and ResMLP accept linearly flattened image patches as input, making them inflexible for different input sizes and hard to capture spatial information.
Greedy Network Enlarging
Recent studies on deep convolutional neural networks present a simple paradigm of architecture design, i. e., models with more MACs typically achieve better accuracy, such as EfficientNet and RegNet.
Real-time Keypoints Detection for Autonomous Recovery of the Unmanned Ground Vehicle
UGV-KPNet is computationally efficient with a small number of parameters and provides pixel-level accurate keypoints detection results in real-time.
CMT: Convolutional Neural Networks Meet Vision Transformers
Vision transformers have been successfully applied to image recognition tasks due to their ability to capture long-range dependencies within an image.
Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation
In this paper, we tackle the problem of novel visual category discovery, i. e., grouping unlabelled images from new classes into different semantic partitions by leveraging a labelled dataset that contains images from other different but relevant categories.
Learning Efficient Vision Transformers via Fine-Grained Manifold Distillation
Specifically, we train a tiny student model to match a pre-trained teacher model in the patch-level manifold space.
Augmented Shortcuts for Vision Transformers
Transformer models have achieved great progress on computer vision tasks recently.
AutoNovel: Automatically Discovering and Learning Novel Visual Categories
We present a new approach called AutoNovel to address this problem by combining three ideas: (1) we suggest that the common approach of bootstrapping an image representation using the labelled data only introduces an unwanted bias, and that this can be avoided by using self-supervised learning to train the representation from scratch on the union of labelled and unlabelled data; (2) we use ranking statistics to transfer the model's knowledge of the labelled classes to the problem of clustering the unlabelled images; and, (3) we train the data representation by optimizing a joint objective function on the labelled and unlabelled subsets of the data, improving both the supervised classification of the labelled data, and the clustering of the unlabelled data.
Ranked #1 on
Novel Class Discovery
on SVHN
Post-Training Quantization for Vision Transformer
Recently, transformer has achieved remarkable performance on a variety of computer vision applications.
ReNAS: Relativistic Evaluation of Neural Architecture Search
An effective and efficient architecture performance evaluation scheme is essential for the success of Neural Architecture Search (NAS).
Positive-Unlabeled Data Purification in the Wild for Object Detection
In this paper, we present a positive-unlabeled learning based scheme to expand training data by purifying valuable images from massive unlabeled ones, where the original training data are viewed as positive data and the unlabeled images in the wild are unlabeled data.
Patch Slimming for Efficient Vision Transformers
We first identify the effective patches in the last layer and then use them to guide the patch selection process of previous layers.
Dynamic Resolution Network
To this end, we propose a novel dynamic-resolution network (DRNet) in which the input resolution is determined dynamically based on each input sample.
Dense Reconstruction of Transparent Objects by Altering Incident Light Paths Through Refraction
We present a simple setup that allows us to alter the incident light paths before light rays enter the object by immersing the object partially in a liquid, and develop a method for recovering the object surface through reconstructing and triangulating such incident light paths.
Joint Representation Learning and Novel Category Discovery on Single- and Multi-modal Data
This paper studies the problem of novel category discovery on single- and multi-modal data with labels from different but relevant categories.
Vision Transformer Pruning
Vision transformer has achieved competitive performance on a variety of computer vision applications.
Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification
Learning discriminative image representations plays a vital role in long-tailed image classification because it can ease the classifier learning in imbalanced cases.
Ranked #8 on
Long-tail Learning
on CIFAR-10-LT (ρ=10)
Distilling Object Detectors via Decoupled Features
To this end, we present a novel distillation algorithm via decoupled features (DeFeat) for learning a better student detector.
Learning Frequency Domain Approximation for Binary Neural Networks
Binary neural networks (BNNs) represent original full-precision weights and activations into 1-bit with sign function.
Transformer in Transformer
In this paper, we point out that the attention inside these local patches are also essential for building visual transformers with high performance and we explore a new architecture, namely, Transformer iN Transformer (TNT).
AdderNet and its Minimalist Hardware Design for Energy-Efficient Artificial Intelligence
With a comprehensive comparison on the performance, power consumption, hardware resource consumption and network generalization capability, we conclude the AdderNet is able to surpass all the other competitors including the classical CNN, novel memristor-network, XNOR-Net and the shift-kernel based network, indicating its great potential in future high performance and energy-efficient artificial intelligence applications.
Fixed Viewpoint Mirror Surface Reconstruction under an Uncalibrated Camera
This paper addresses the problem of mirror surface reconstruction, and proposes a solution based on observing the reflections of a moving reference plane on the mirror surface.
GhostSR: Learning Ghost Features for Efficient Image Super-Resolution
Based on the observation that many features in SISR models are also similar to each other, we propose to use shift operation to generate the redundant features (i. e., ghost features).
A Flexible Framework for Discovering Novel Categories with Contrastive Learning
This paper studies the problem of novel category discovery on single- and multi-modal data with labels from different but relevant categories.
A Survey on Vision Transformer
Transformer, first applied to the field of natural language processing, is a type of deep neural network mainly based on the self-attention mechanism.
$\mathbb{X}$Resolution Correspondence Networks
In this paper, we aim at establishing accurate dense correspondences between a pair of images with overlapping field of view under challenging illumination variation, viewpoint changes, and style differences.
Dynamic Feature Pyramid Networks for Object Detection
An attempt to enhance the FPN is enriching the spatial information by expanding the receptive fields, which is promising to largely improve the detection accuracy.
Model Rubik’s Cube: Twisting Resolution, Depth and Width for TinyNets
To this end, we summarize a tiny formula for downsizing neural architectures through a series of smaller models derived from the EfficientNet-B0 with the FLOPs constraint.
VEGA: Towards an End-to-End Configurable AutoML Pipeline
Automated Machine Learning (AutoML) is an important industrial solution for automatic discovery and deployment of the machine learning models.
Model Rubik's Cube: Twisting Resolution, Depth and Width for TinyNets
To this end, we summarize a tiny formula for downsizing neural architectures through a series of smaller models derived from the EfficientNet-B0 with the FLOPs constraint.
Ranked #608 on
Image Classification
on ImageNet
Deterministic Approximation for Submodular Maximization over a Matroid in Nearly Linear Time
We study the problem of maximizing a non-monotone, non-negative submodular function subject to a matroid constraint.
Training Binary Neural Networks through Learning with Noisy Supervision
This paper formalizes the binarization operations over neural networks from a learning perspective.
Searching for Low-Bit Weights in Quantized Neural Networks
Quantized neural networks with low-bit weights and activations are attractive for developing AI accelerators.
Revisiting Modified Greedy Algorithm for Monotone Submodular Maximization with a Knapsack Constraint
Second, we enhance the modified greedy algorithm to derive a data-dependent upper bound on the optimum.
Deep Photometric Stereo for Non-Lambertian Surfaces
To deal with the uncalibrated scenario where light directions are unknown, we introduce a new convolutional network, named LCNet, to estimate light directions from input images.
LSD-C: Linearly Separable Deep Clusters
We present LSD-C, a novel method to identify clusters in an unlabeled dataset.
Dual-Resolution Correspondence Networks
The fine-resolution feature maps are used to obtain the final dense correspondences guided by the refined coarse 4D correlation tensor.
Efficient Approximation Algorithms for Adaptive Influence Maximization
In this paper, we propose the first practical algorithm for the adaptive IM problem that could provide the worst-case approximation guarantee of $1-\mathrm{e}^{\rho_b(\varepsilon-1)}$, where $\rho_b=1-(1-1/b)^b$ and $\varepsilon \in (0, 1)$ is a user-specified parameter.
Social and Information Networks
Anisotropic Convolutional Networks for 3D Semantic Scene Completion
In contrast to the standard 3D convolution that is limited to a fixed 3D receptive field, our module is capable of modeling the dimensional anisotropy voxel-wisely.
Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection
To this end, we propose a hierarchical trinity search framework to simultaneously discover efficient architectures for all components (i. e. backbone, neck, and head) of object detector in an end-to-end manner.
Correspondence Networks with Adaptive Neighbourhood Consensus
This is a challenging task due to large intra-class variations and a lack of dense pixel level annotations.
Ranked #8 on
Semantic correspondence
on PF-PASCAL
Learning Inverse Rendering of Faces from Real-world Videos
To alleviate this problem, we propose a weakly supervised training approach to train our model on real face videos, based on the assumption of consistency of albedo and normal across different frames, thus bridging the gap between real and synthetic face images.
Automatically Discovering and Learning New Visual Categories with Ranking Statistics
In this work we address this problem by combining three ideas: (1) we suggest that the common approach of bootstrapping an image representation using the labeled data only introduces an unwanted bias, and that this can be avoided by using self-supervised learning to train the representation from scratch on the union of labelled and unlabelled data; (2) we use rank statistics to transfer the model's knowledge of the labelled classes to the problem of clustering the unlabelled images; and, (3) we train the data representation by optimizing a joint objective function on the labelled and unlabelled subsets of the data, improving both the supervised classification of the labelled data, and the clustering of the unlabelled data.
Widening and Squeezing: Towards Accurate and Efficient QNNs
Quantization neural networks (QNNs) are very attractive to the industry because their extremely cheap calculation and storage overhead, but their performance is still worse than that of networks with full-precision parameters.
GhostNet: More Features from Cheap Operations
Deploying convolutional neural networks (CNNs) on embedded devices is difficult due to the limited memory and computation resources.
Ranked #764 on
Image Classification
on ImageNet
Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification
On the other hand, there still exist many useful contextual cues that do not fall into the scope of predefined human parts or attributes.
Ranked #57 on
Person Re-Identification
on DukeMTMC-reID
ReNAS:Relativistic Evaluation of Neural Architecture Search
An effective and efficient architecture performance evaluation scheme is essential for the success of Neural Architecture Search (NAS).
Balanced Binary Neural Networks with Gated Residual
In this paper, we attempt to maintain the information propagated in the forward process and propose a Balanced Binary Neural Networks with Gated Residual (BBG for short).
Ranked #858 on
Image Classification
on ImageNet
Positive-Unlabeled Compression on the Cloud
In practice, only a small portion of the original training set is required as positive examples and more useful training examples can be obtained from the massive unlabeled data on the cloud through a PU classifier with an attention based multi-scale feature extractor.
Searching for Accurate Binary Neural Architectures
Binary neural networks have attracted tremendous attention due to the efficiency for deploying them on mobile devices.
Learning to Discover Novel Visual Categories via Deep Transfer Clustering
The second contribution is a method to estimate the number of classes in the unlabelled data.
Full-Stack Filters to Build Minimum Viable CNNs
Existing works used to decrease the number or size of requested convolution filters for a minimum viable CNN on edge devices.
Attribute Aware Pooling for Pedestrian Attribute Recognition
This paper expands the strength of deep convolutional neural networks (CNNs) to the pedestrian attribute recognition problem by devising a novel attribute aware pooling algorithm.
Learning Instance-wise Sparsity for Accelerating Deep Models
Exploring deep convolutional neural networks of high efficiency and low memory usage is very essential for a wide variety of machine learning tasks.
Co-Evolutionary Compression for Unpaired Image Translation
Generative adversarial networks (GANs) have been successfully used for considerable computer vision tasks, especially the image-to-image translation.
Learning Transparent Object Matting
In this paper, we formulate transparent object matting as a refractive flow estimation problem, and propose a deep learning framework, called TOM-Net, for learning the refractive flow.
Semi-Supervised Learning with Scarce Annotations
The first is a simple but effective one: we leverage the power of transfer learning among different tasks and self-supervision to initialize a good representation of the data without making use of any label.
Unsupervised Image Matching and Object Discovery as Optimization
Learning with complete or partial supervision is powerful but relies on ever-growing human annotation efforts.
Ranked #2 on
Single-object colocalization
on Object Discovery
Self-calibrating Deep Photometric Stereo Networks
This paper proposes an uncalibrated photometric stereo method for non-Lambertian scenes based on deep learning.
Attribute-Aware Attention Model for Fine-grained Representation Learning
Based on the considerations above, we propose a novel Attribute-Aware Attention Model ($A^3M$), which can learn local attribute representation and global category representation simultaneously in an end-to-end manner.
Ranked #4 on
Fine-Grained Image Classification
on CompCars
Greedy Hash: Towards Fast Optimization for Accurate Hash Coding in CNN
To convert the input into binary code, hashing algorithm has been widely used for approximate nearest neighbor search on large-scale image sets due to its computation and storage efficiency.
PS-FCN: A Flexible Learning Framework for Photometric Stereo
This paper addresses the problem of photometric stereo for non-Lambertian surfaces.
TOM-Net: Learning Transparent Object Matting from a Single Image
In this paper, we first formulate transparent object matting as a refractive flow estimation problem.
AutoEncoder Inspired Unsupervised Feature Selection
High-dimensional data in many areas such as computer vision and machine learning tasks brings in computational and analytical difficulty.
SCNet: Learning Semantic Correspondence
This paper addresses the problem of establishing semantic correspondences between images depicting different instances of the same object or scene category.
Mirror Surface Reconstruction Under an Uncalibrated Camera
Unlike previous approaches which require tedious work to calibrate the camera, our method can recover both the camera intrinsics and extrinsics together with the mirror surface from reflections of the reference plane under at least three unknown distinct poses.
A Fixed Viewpoint Approach for Dense Reconstruction of Transparent Objects
In this paper, we develop a fixed viewpoint approach for dense surface reconstruction of transparent objects based on refraction of light.
