Search Results for author:
Found 110 papers, 37 papers with code
The 1st Tiny Object Detection Challenge:Methods and Results
The 1st Tiny Object Detection (TOD) Challenge aims to encourage research in developing novel and accurate methods for tiny object detection in images which have wide views, with a current focus on tiny person detection.
Implicit Diffusion Models for Continuous Super-Resolution
IDM integrates an implicit neural representation and a denoising diffusion model in a unified end-to-end framework, where the implicit neural representation is adopted in the decoding process to learn continuous-resolution representation.
Ranked #1 on
Image Super-Resolution
on CelebA-HQ 128x128
HRank: Filter Pruning using High-Rank Feature Map
The principle behind our pruning is that low-rank feature maps contain less information, and thus pruned results can be easily reproduced.
Multinomial Distribution Learning for Effective Neural Architecture Search
Therefore, NAS can be transformed to a multinomial distribution learning problem, i. e., the distribution is optimized to have a high expectation of the performance.
CCMB: A Large-scale Chinese Cross-modal Benchmark
In this work, we build a large-scale high-quality Chinese Cross-Modal Benchmark named CCMB for the research community, which contains the currently largest public pre-training dataset Zero and five human-annotated fine-tuning datasets for downstream tasks.
Ranked #3 on
Image Retrieval
on Flickr30k-CN
Channel Pruning via Automatic Structure Search
In this paper, we propose a new channel pruning method based on artificial bee colony algorithm (ABC), dubbed as ABCPruner, which aims to efficiently find optimal pruned structure, i. e., channel number in each layer, rather than selecting "important" channels as previous works did.
Self-Supervised Monocular Depth and Ego-Motion Estimation in Endoscopy: Appearance Flow to the Rescue
Recently, self-supervised learning technology has been applied to calculate depth and ego-motion from monocular videos, achieving remarkable performance in autonomous driving scenarios.
Rotated Binary Neural Network
In this paper, for the first time, we explore the influence of angular bias on the quantization error and then introduce a Rotated Binary Neural Network (RBNN), which considers the angle alignment between the full-precision weight vector and its binarized version.
SiMaN: Sign-to-Magnitude Network Binarization
In this paper, we show that our weight binarization provides an analytical solution by encoding high-magnitude weights into +1s, and 0s otherwise.
Q-ViT: Accurate and Fully Quantized Low-bit Vision Transformer
The large pre-trained vision transformers (ViTs) have demonstrated remarkable performance on various visual tasks, but suffer from expensive computational and memory cost problems when deployed on resource-constrained devices.
RSBuilding: Towards General Remote Sensing Image Building Extraction and Change Detection with Foundation Model
RSBuilding is designed to enhance cross-scene generalization and task universality.
PAMS: Quantized Super-Resolution via Parameterized Max Scale
Specifically, most state-of-the-art SR models without batch normalization have a large dynamic quantization range, which also serves as another cause of performance drop.
Towards Optimal Structured CNN Pruning via Generative Adversarial Learning
In this paper, we propose an effective structured pruning approach that jointly prunes filters as well as other structures in an end-to-end manner.
Face Animation with an Attribute-Guided Diffusion Model
Face animation has achieved much progress in computer vision.
DDPNAS: Efficient Neural Architecture Search via Dynamic Distribution Pruning
With the proposed efficient network generation method, we directly obtain the optimal neural architectures on given constraints, which is practical for on-device models across diverse search spaces and constraints.
Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compression
The relationship between the input feature maps and 2D kernels is revealed in a theoretical framework, based on which a kernel sparsity and entropy (KSE) indicator is proposed to quantitate the feature map importance in a feature-agnostic manner to guide model compression.
FNeVR: Neural Volume Rendering for Face Animation
In FNeVR, we design a 3D Face Volume Rendering (FVR) module to enhance the facial details for image rendering.
IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization
In this paper, we observe an interesting phenomenon of intra-class heterogeneity in real data and show that existing methods fail to retain this property in their synthetic images, which causes a limited performance increase.
Memory Attention Networks for Skeleton-based Action Recognition
Specifically, the TARM is deployed in a residual learning module that employs a novel attention learning network to recalibrate the temporal attention of frames in a skeleton sequence.
Ranked #89 on
Skeleton Based Action Recognition
on NTU RGB+D
Q-DETR: An Efficient Low-Bit Quantized Detection Transformer
At the upper level, we introduce a new foreground-aware query matching scheme to effectively transfer the teacher information to distillation-desired features to minimize the conditional information entropy.
Long term 5G network traffic forecasting via modeling non-stationarity with deep learning
However, long term prediction horizon exposes the non-stationarity of series data, which deteriorates the performance of existing approaches.
IPDreamer: Appearance-Controllable 3D Object Generation with Image Prompts
Recent advances in 3D generation have been remarkable, with methods such as DreamFusion leveraging large-scale text-to-image diffusion-based models to supervise 3D generation.
Recurrent Bilinear Optimization for Binary Neural Networks
To address this issue, Recurrent Bilinear Optimization is proposed to improve the learning process of BNNs (RBONNs) by associating the intrinsic bilinear variables in the back propagation process.
Deep Fisher Discriminant Learning for Mobile Hand Gesture Recognition
Gesture recognition is a challenging problem in the field of biometrics.
Ranked #1 on
Hand Gesture Recognition
on MGB
iffDetector: Inference-aware Feature Filtering for Object Detection
In this paper, we propose a new feature optimization approach to enhance features and suppress background noise in both the training and inference stages.
IDa-Det: An Information Discrepancy-aware Distillation for 1-bit Detectors
This explains why existing KD methods are less effective for 1-bit detectors, caused by a significant information discrepancy between the real-valued teacher and the 1-bit student.
Resilient Binary Neural Network
In this paper, we introduce a Resilient Binary Neural Network (ReBNN) to mitigate the frequent oscillation for better BNNs' training.
Few-Shot Learning with Visual Distribution Calibration and Cross-Modal Distribution Alignment
However, with only a few training images, there exist two crucial problems: (1) the visual feature distributions are easily distracted by class-irrelevant information in images, and (2) the alignment between the visual and language feature distributions is difficult.
Aha! Adaptive History-Driven Attack for Decision-Based Black-Box Models
A common practice is to start from a large perturbation and then iteratively reduce it with a deterministic direction and a random one while keeping it adversarial.
Controllable Mind Visual Diffusion Model
Brain signal visualization has emerged as an active research area, serving as a critical interface between the human visual system and computer vision models.
A General and Efficient Training for Transformer via Token Expansion
The remarkable performance of Vision Transformers (ViTs) typically requires an extremely large training cost.
ZONE: Zero-Shot Instruction-Guided Local Editing
We then propose a Region-IoU scheme for precise image layer extraction from an off-the-shelf segment model.
Self-Enhancement Improves Text-Image Retrieval in Foundation Visual-Language Models
The emergence of cross-modal foundation models has introduced numerous approaches grounded in text-image retrieval.
Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler
In this paper, we propose a novel Knowledge-driven Differential Filter Sampler~(KDFS) with Masked Filter Modeling~(MFM) framework for filter pruning, which globally prunes the redundant filters based on the prior knowledge of a pre-trained model in a differential and non-alternative optimization.
The Structure Transfer Machine Theory and Applications
Representation learning is a fundamental but challenging problem, especially when the distribution of data is unknown.
Federated Learning via Input-Output Collaborative Distillation
Federated learning (FL) is a machine learning paradigm in which distributed local nodes collaboratively train a central model without sharing individually held private data.
Anti-Retroactive Interference for Lifelong Learning
Second, according to the similarity between incremental knowledge and base knowledge, we design an adaptive fusion of incremental knowledge, which helps the model allocate capacity to the knowledge of different difficulties.
Object detection and tracking benchmark in industry based on improved correlation filter
Real-time object detection and tracking have shown to be the basis of intelligent production for industrial 4. 0 applications.
One-Two-One Networks for Compression Artifacts Reduction in Remote Sensing
Compression artifacts reduction (CAR) is a challenging problem in the field of remote sensing.
Gabor Convolutional Networks
Steerable properties dominate the design of traditional filters, e. g., Gabor filters, and endow features the capability of dealing with spatial transformations.
Latent Constrained Correlation Filter
In this paper, we introduce an intermediate step -- solution sampling -- after the data sampling step to form a subspace, in which an optimal solution can be estimated.
Manifold Constrained Low-Rank Decomposition
Low-rank decomposition (LRD) is a state-of-the-art method for visual data reconstruction and modelling.
Latent Constrained Correlation Filters for Object Localization
There is a neglected fact in the traditional machine learning methods that the data sampling can actually lead to the solution sampling.
Deep Spatio-temporal Manifold Network for Action Recognition
Visual data such as videos are often sampled from complex manifold.
Output Constraint Transfer for Kernelized Correlation Filter in Tracking
Kernelized Correlation Filter (KCF) is one of the state-of-the-art object trackers.
Self-learning Scene-specific Pedestrian Detectors using a Progressive Latent Model
In this paper, a self-learning approach is proposed towards solving scene-specific pedestrian detection problem without any human' annotation involved.
Boosting-like Deep Learning For Pedestrian Detection
This paper proposes boosting-like deep learning (BDL) framework for pedestrian detection.
The BeiHang Keystroke Dynamics Authentication System
Keystroke Dynamics is an important biometric solution for person authentication.
Projection Convolutional Neural Networks for 1-bit CNNs via Discrete Back Propagation
The advancement of deep convolutional neural networks (DCNNs) has driven significant improvement in the accuracy of recognition systems for many computer vision tasks.
Modulated Convolutional Networks
In this paper, we propose new Modulated Convolutional Networks (MCNs) to improve the portability of CNNs via binarized filters.
Sparse Representation Classification With Manifold Constraints Transfer
The fact that image data samples lie on a manifold has been successfully exploited in many learning and inference problems.
Cross-Modality Binary Code Learning via Fusion Similarity Hashing
In this paper, we propose a hashing scheme, termed Fusion Similarity Hashing (FSH), which explicitly embeds the graph-based fusion similarity across modalities into a common Hamming space.
Crowd Counting and Density Estimation by Trellis Encoder-Decoder Network
In this paper, we propose a trellis encoder-decoder network (TEDnet) for crowd counting, which focuses on generating high-quality density estimation maps.
Supervised Online Hashing via Similarity Distribution Learning
In this paper, we propose to model the similarity distributions between the input data and the hashing codes, upon which a novel supervised online hashing method, dubbed as Similarity Distribution based Online Hashing (SDOH), is proposed, to keep the intrinsic semantic relationship in the produced Hamming space.
Interpretable Neural Network Decoupling
More specifically, we introduce a novel architecture controlling module in each layer to encode the network architecture by a vector.
Bayesian Optimized 1-Bit CNNs
Deep convolutional neural networks (DCNNs) have dominated the recent developments in computer vision through making various record-breaking models.
RBCN: Rectified Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNs
Binarized convolutional neural networks (BCNNs) are widely used to improve memory and computation efficiency of deep convolutional neural networks (DCNNs) for mobile and AI chips based applications.
Semantic-aware Image Deblurring
Specially, we propose a novel Structured-Spatial Semantic Embedding model for image deblurring (termed S3E-Deblur), which introduces a novel Structured-Spatial Semantic tree model (S3-tree) to bridge two basic tasks in computer vision: image deblurring (ImD) and image captioning (ImC).
Aggregation Signature for Small Object Tracking
In this paper, we propose a novel aggregation signature suitable for small object tracking, especially aiming for the challenge of sudden and large drift.
Circulant Binary Convolutional Networks: Enhancing the Performance of 1-bit DCNNs with Circulant Back Propagation
The CiFs can be easily incorporated into existing deep convolutional neural networks (DCNNs), which leads to new Circulant Binary Convolutional Networks (CBCNs).
Variational Structured Semantic Inference for Diverse Image Captioning
To model these two inherent diversities in image captioning, we propose a Variational Structured Semantic Inferring model (termed VSSI-cap) executed in a novel structured encoder-inferer-decoder schema.
Binarized Neural Architecture Search
A variant, binarized neural architecture search (BNAS), with a search space of binarized convolutions, can produce extremely compressed models.
GBCNs: Genetic Binary Convolutional Networks for Enhancing the Performance of 1-bit DCNNs
The BGA method is proposed to modify the binary process of GBCNs to alleviate the local minima problem, which can significantly improve the performance of 1-bit DCNNs.
NAS-Count: Counting-by-Density with Neural Architecture Search
Most of the recent advances in crowd counting have evolved from hand-designed density estimation networks, where multi-scale features are leveraged to address the scale variation problem, but at the expense of demanding design efforts.
CP-NAS: Child-Parent Neural Architecture Search for Binary Neural Networks
To this end, a Child-Parent (CP) model is introduced to a differentiable NAS to search the binarized architecture (Child) under the supervision of a full-precision model (Parent).
Cogradient Descent for Bilinear Optimization
Conventional learning methods simplify the bilinear model by regarding two intrinsically coupled factors independently, which degrades the optimization procedure.
Anti-Bandit Neural Architecture Search for Model Defense
Deep convolutional neural networks (DCNNs) have dominated as the best performers in machine learning, but can be challenged by adversarial attacks.
Binarized Neural Architecture Search for Efficient Object Recognition
In this paper, binarized neural architecture search (BNAS), with a search space of binarized convolutions, is introduced to produce extremely compressed models to reduce huge computational cost on embedded devices for edge computing.
A Review of Recent Advances of Binary Neural Networks for Edge Computing
Edge computing is promising to become one of the next hottest topics in artificial intelligence because it benefits various evolving domains such as real-time unmanned aerial systems, industrial applications, and the demand for privacy protection.
Fast Class-wise Updating for Online Hashing
To achieve fast online adaptivity, a class-wise updating method is developed to decompose the binary code learning and alternatively renew the hash functions in a class-wise fashion, which well addresses the burden on large amounts of training batches.
Deformable Gabor Feature Networks for Biomedical Image Classification
In recent years, deep learning has dominated progress in the field of medical image analysis.
Multi-UAV Mobile Edge Computing and Path Planning Platform based on Reinforcement Learning
Unmanned Aerial vehicles (UAVs) are widely used as network processors in mobile networks, but more recently, UAVs have been used in Mobile Edge Computing as mobile servers.
Interpretable Attention Guided Network for Fine-grained Visual Classification
We propose an Interpretable Attention Guided Network (IAGN) for fine-grained visual classification.
Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections
This leads to a new problem of confidence discrepancy for the detector ensembles.
Dual-stream Network for Visual Recognition
Transformers with remarkable global representation capacities achieve competitive results for visual tasks, but fail to consider high-level local pattern information in input images.
Oriented Object Detection with Transformer
Object detection with Transformers (DETR) has achieved a competitive performance over traditional detectors, such as Faster R-CNN.
Cogradient Descent for Dependable Learning
Conventional gradient descent methods compute the gradients for multiple variables through the partial derivative.
Layer-Wise Searching for 1-Bit Detectors
At each layer, it exploits a differentiable binarization search (DBS) to minimize the angular error in a student-teacher framework.
Toward Joint Thing-and-Stuff Mining for Weakly Supervised Panoptic Segmentation
To date, learning weakly supervised panoptic segmentation (WSPS) with only image-level labels remains unexplored.
IDARTS: Interactive Differentiable Architecture Search
Differentiable Architecture Search (DARTS) improves the efficiency of architecture search by learning the architecture and network parameters end-to-end.
Parallel Detection-and-Segmentation Learning for Weakly Supervised Instance Segmentation
Weakly supervised instance segmentation (WSIS) with only image-level labels has recently drawn much attention.
Towards Comprehensive Monocular Depth Estimation: Multiple Heads Are Better Than One
In this work, we investigate into the phenomenon and propose to integrate the strengths of multiple weak depth predictor to build a comprehensive and accurate depth predictor, which is critical for many real-world applications, e. g., 3D reconstruction.
Auxiliary learning induced graph convolutional networks
In this article, we propose a novel auxiliary learning induced graph convolutional network in a multi-task fashion.
POEM: 1-bit Point-wise Operations based on Expectation-Maximization for Efficient Point Cloud Processing
Real-time point cloud processing is fundamental for lots of computer vision tasks, while still challenged by the computational problem on resource-limited edge devices.
Associative Adversarial Learning Based on Selective Attack
We show that our method improves the recognition accuracy of adversarial training on ImageNet by 8. 32% compared with the baseline.
TerViT: An Efficient Ternary Vision Transformer
Vision transformers (ViTs) have demonstrated great potential in various visual tasks, but suffer from expensive computational and memory cost problems when deployed on resource-constrained devices.
Confidence Dimension for Deep Learning based on Hoeffding Inequality and Relative Evaluation
Research on the generalization ability of deep neural networks (DNNs) has recently attracted a great deal of attention.
Bi-level Doubly Variational Learning for Energy-based Latent Variable Models
In this paper, we propose Bi-level doubly variational learning (BiDVL), which is based on a new bi-level optimization framework and two tractable variational distributions to facilitate learning EBLVMs.
MAFormer: A Transformer Network with Multi-scale Attention Fusion for Visual Recognition
We develop a simple but effective module to explore the full potential of transformers for visual representation by learning fine-grained and coarse-grained features at a token level and dynamically fusing them.
Rethinking the Number of Shots in Robust Model-Agnostic Meta-Learning
Based on this observation, we propose a simple strategy, i. e., increasing the number of training shots, to mitigate the loss of intrinsic dimension caused by robustness-promoting regularization.
Feature Calibration Network for Occluded Pedestrian Detection
FC-Net is based on the observation that the visible parts of pedestrians are selective and decisive for detection, and is implemented as a self-paced feature learning framework with a self-activation (SA) module and a feature calibration (FC) module.
CircleNet: Reciprocating Feature Adaptation for Robust Pedestrian Detection
In this paper we propose a novel feature learning model, referred to as CircleNet, to achieve feature adaptation by mimicking the process humans looking at low resolution and occluded objects: focusing on it again, at a finer scale, if the object can not be identified clearly for the first time.
Confidence-driven Bounding Box Localization for Small Object Detection
C-BBL quantizes continuous labels into grids and formulates two-hot ground truth labels.
MVP-SEG: Multi-View Prompt Learning for Open-Vocabulary Semantic Segmentation
CLIP (Contrastive Language-Image Pretraining) is well-developed for open-vocabulary zero-shot image-level recognition, while its applications in pixel-level tasks are less investigated, where most efforts directly adopt CLIP features without deliberative adaptations.
AttriCLIP: A Non-Incremental Learner for Incremental Knowledge Learning
Text consists of a category name and a fixed number of learnable parameters which are selected from our designed attribute word bank and serve as attributes.
Bi-ViT: Pushing the Limit of Vision Transformer Quantization
Vision transformers (ViTs) quantization offers a promising prospect to facilitate deploying large pre-trained networks on resource-limited devices.
Decom--CAM: Tell Me What You See, In Details! Feature-Level Interpretation via Decomposition Class Activation Map
Although the Class Activation Map (CAM) is widely used to interpret deep model predictions by highlighting object location, it fails to provide insight into the salient features used by the model to make decisions.
DCP-NAS: Discrepant Child-Parent Neural Architecture Search for 1-bit CNNs
One natural approach is to use 1-bit CNNs to reduce the computation and memory cost of NAS by taking advantage of the strengths of each in a unified framework, while searching the 1-bit CNNs is more challenging due to the more complicated processes involved.
Q-YOLO: Efficient Inference for Real-time Object Detection
Real-time object detection plays a vital role in various computer vision applications.
Representation Disparity-aware Distillation for 3D Object Detection
In this paper, we focus on developing knowledge distillation (KD) for compact 3D detectors.
Heterogeneous Generative Knowledge Distillation with Masked Image Modeling
Masked image modeling (MIM) methods achieve great success in various visual tasks but remain largely unexplored in knowledge distillation for heterogeneous deep models.
LatentWarp: Consistent Diffusion Latents for Zero-Shot Video-to-Video Translation
As a result, the corresponding regions across the adjacent frames can share closely-related query tokens and attention outputs, which can further improve latent-level consistency to enhance visual temporal coherence of generated videos.
Tuning-Free Inversion-Enhanced Control for Consistent Image Editing
Consistent editing of real images is a challenging task, as it requires performing non-rigid edits (e. g., changing postures) to the main objects in the input image without changing their identity or attributes.
Class-Imbalanced Semi-Supervised Learning for Large-Scale Point Cloud Semantic Segmentation via Decoupling Optimization
Semi-supervised learning (SSL), thanks to the significant reduction of data annotation costs, has been an active research topic for large-scale 3D scene understanding.
Push Quantization-Aware Training Toward Full Precision Performances via Consistency Regularization
Existing Quantization-Aware Training (QAT) methods intensively depend on the complete labeled dataset or knowledge distillation to guarantee the performances toward Full Precision (FP) accuracies.
Effective Gradient Sample Size via Variation Estimation for Accelerating Sharpness aware Minimization
Concretely, we discover that the gradient of SAM is a combination of the gradient of SGD and the Projection of the Second-order gradient matrix onto the First-order gradient (PSF).
A Channel-ensemble Approach: Unbiased and Low-variance Pseudo-labels is Critical for Semi-supervised Classification
Semi-supervised learning (SSL) is a practical challenge in computer vision.
$\mathrm{F^2Depth}$: Self-supervised Indoor Monocular Depth Estimation via Optical Flow Consistency and Feature Map Synthesis
To evaluate the generalization ability of our $\mathrm{F^2Depth}$, we collect a Campus Indoor depth dataset composed of approximately 1500 points selected from 99 images in 18 scenes.
Indoor Monocular Depth Estimation
Monocular Depth Estimation
+2
Fusion-Mamba for Cross-modality Object Detection
In this paper, we investigate cross-modality fusion by associating cross-modal features in a hidden state space based on an improved Mamba with a gating mechanism.
Real-time guidewire tracking and segmentation in intraoperative x-ray
For this purpose, real-time and accurate guidewire segmentation and tracking can enhance the visualization of guidewires and provide visual feedback for physicians during the intervention as well as for robot-assisted interventions.
