Search Results for author:
Found 47 papers, 15 papers with code
COST: Contrastive One-Stage Transformer for Vision-Language Small Object Tracking
In this work, we propose COST, a contrastive one-stage transformer fusion framework for VL tracking, aiming to learn semantically consistent and unified VL representations.
Towards Personalized Federated Learning via Comprehensive Knowledge Distillation
By applying knowledge distillation, we effectively transfer global generalized knowledge and historical personalized knowledge to the local model, thus mitigating catastrophic forgetting and enhancing the general performance of personalized models.
Personalized Federated Learning via Backbone Self-Distillation
These weights are then aggregated to create a global backbone, which is returned to each client for updating.
Federated Learning with Label-Masking Distillation
Inspired by this, we propose a label-masking distillation approach termed FedLMD to facilitate federated learning via perceiving the various label distributions of each client.
Interpret the Predictions of Deep Networks via Re-Label Distillation
After that, using the labels annotated by the deep network as teacher, a linear student model is trained to approximate the annotations by mapping these synthetic images to the classes.
Privacy-Preserving Student Learning with Differentially Private Data-Free Distillation
The main idea is generating synthetic data to learn a student that can mimic the ability of a teacher well-trained on private data.
Look Through Masks: Towards Masked Face Recognition with De-Occlusion Distillation
Many real-world applications today like video surveillance and urban governance need to address the recognition of masked faces, where content replacement by diverse masks often brings in incomplete appearance and ambiguous representation, leading to a sharp drop in accuracy.
Distilling Channels for Efficient Deep Tracking
However, these networks are too complex to represent a specific moving object, leading to poor generalization as well as high computational and memory costs.
Efficient Low-Resolution Face Recognition via Bridge Distillation
Face recognition in the wild is now advancing towards light-weight models, fast inference speed and resolution-adapted capability.
Distilling Generative-Discriminative Representations for Very Low-Resolution Face Recognition
After that, the discriminative representation distillation further considers a pretrained face recognizer as the discriminative teacher to supervise the learning of the student head via cross-resolution relational contrastive distillation.
Look One and More: Distilling Hybrid Order Relational Knowledge for Cross-Resolution Image Recognition
In spite of great success in many image recognition tasks achieved by recent deep models, directly applying them to recognize low-resolution images may suffer from low accuracy due to the missing of informative details during resolution degradation.
Low-Resolution Object Recognition with Cross-Resolution Relational Contrastive Distillation
Recent studies have shown that knowledge distillation approaches can effectively transfer knowledge from a high-resolution teacher model to a low-resolution student model by aligning cross-resolution representations.
Learning Privacy-Preserving Student Networks via Discriminative-Generative Distillation
In this work, we propose a discriminative-generative distillation approach to learn privacy-preserving deep models.
Low-Resolution Face Recognition via Adaptable Instance-Relation Distillation
In this manner, the capability of recovering missing details of familiar low-resolution faces can be effectively enhanced, leading to a better knowledge transfer.
Learning Differentially Private Diffusion Models via Stochastic Adversarial Distillation
Specifically, we first train a diffusion model as a teacher and then train a student by distillation, in which we achieve differential privacy by adding noise to the gradients from other models to the student.
Learning Natural Consistency Representation for Face Forgery Video Detection
To this end, we propose to learn the Natural Consistency representation (NACO) of real face videos in a self-supervised manner, which is inspired by the observation that fake videos struggle to maintain the natural spatiotemporal consistency even under unknown forgery methods and different perturbations.
DANCE: Dual-View Distribution Alignment for Dataset Condensation
Specifically, from the inner-class view, we construct multiple "middle encoders" to perform pseudo long-term distribution alignment, making the condensed set a good proxy of the real one during the whole training process; while from the inter-class view, we use the expert models to perform distribution calibration, ensuring the synthetic data remains in the real class region during condensing.
Masked Face Recognition with Generative-to-Discriminative Representations
First, we leverage a generative encoder pretrained for face inpainting and finetune it to represent masked faces into category-aware descriptors.
M3D: Dataset Condensation by Minimizing Maximum Mean Discrepancy
Nowadays, optimization-oriented methods have been the primary method in the field of dataset condensation for achieving SOTA results.
Coupled Confusion Correction: Learning from Crowds with Sparse Annotations
Moreover, we cluster the ``annotator groups'' who share similar expertise so that their confusion matrices could be corrected together.
Multi-Label Noise Transition Matrix Estimation with Label Correlations: Theory and Algorithm
However, estimating multi-label noise transition matrices remains a challenging task, as most existing estimators in noisy multi-class learning rely on anchor points and accurate fitting of noisy class posteriors, which is hard to satisfy in noisy multi-label learning.
Latent Spatiotemporal Adaptation for Generalized Face Forgery Video Detection
Specifically, we first model the spatiotemporal patterns of face videos by incorporating a lightweight CNN to extract local spatial features of each frame and then cascading a vision transformer to learn the long-term spatiotemporal representations in latent space, which should contain more clues than in pixel space.
Transferring Annotator- and Instance-dependent Transition Matrix for Learning from Crowds
In real-world crowd-sourcing scenarios, noise transition matrices are both annotator- and instance-dependent.
Private Gradient Estimation is Useful for Generative Modeling
In this work, we present a new private generative modeling approach where samples are generated via Hamiltonian dynamics with gradients of the private dataset estimated by a well-trained network.
Deepfake Video Detection with Spatiotemporal Dropout Transformer
Existing image-level approaches often focus on single frame and ignore the spatiotemporal cues hidden in deepfake videos, resulting in poor generalization and robustness.
Bootstrapping Multi-view Representations for Fake News Detection
Representations from each view are separately used to coarsely predict the fidelity of the whole news, and the multimodal representations are able to predict the cross-modal consistency.
Robust Weight Perturbation for Adversarial Training
Based on these observations, we propose a robust perturbation strategy to constrain the extent of weight perturbation.
Trustable Co-label Learning from Multiple Noisy Annotators
This raises the following important question: how can we effectively use a small amount of trusted data to facilitate robust classifier learning from multiple annotators?
Selective-Supervised Contrastive Learning with Noisy Labels
In the selection process, by measuring the agreement between learned representations and given labels, we first identify confident examples that are exploited to build confident pairs.
Ranked #11 on
Image Classification
on mini WebVision 1.0
WebUAV-3M: A Benchmark for Unveiling the Power of Million-Scale Deep UAV Tracking
In this work, we propose WebUAV-3M, the largest public UAV tracking benchmark to date, to facilitate both the development and evaluation of deep UAV trackers.
The 2nd Anti-UAV Workshop & Challenge: Methods and Results
The 2nd Anti-UAV Workshop \& Challenge aims to encourage research in developing novel and accurate methods for multi-scale object tracking.
Interpretable Face Manipulation Detection via Feature Whitening
The approach could make the face manipulation detection process transparent by embedding the feature whitening module.
Student Network Learning via Evolutionary Knowledge Distillation
Inspired by that, we propose an evolutionary knowledge distillation approach to improve the transfer effectiveness of teacher knowledge.
Receptive Multi-granularity Representation for Person Re-Identification
Current stripe-based feature learning approaches have delivered impressive accuracy, but do not make a proper trade-off between diversity, locality, and robustness, which easily suffers from part semantic inconsistency for the conflict between rigid partition and misalignment.
Accurate Temporal Action Proposal Generation with Relation-Aware Pyramid Network
Accurate temporal action proposals play an important role in detecting actions from untrimmed videos.
Focusing and Diffusion: Bidirectional Attentive Graph Convolutional Networks for Skeleton-based Action Recognition
A collection of approaches based on graph convolutional networks have proven success in skeleton-based action recognition by exploring neighborhood information and dense dependencies between intra-frame joints.
Ranked #47 on
Skeleton Based Action Recognition
on NTU RGB+D
Aesthetic Attributes Assessment of Images
This is a new formula of image aesthetic assessment, which predicts aesthetic attributes captions together with the aesthetic score of each attribute.
Domain Adaptive Attention Learning for Unsupervised Person Re-Identification
In this approach, a domain adaptive attention model is learned to separate the feature map into domain-shared part and domain-specific part.
Spatiotemporal Knowledge Distillation for Efficient Estimation of Aerial Video Saliency
In this approach, five components are involved, including two teachers, two students and the desired spatiotemporal model.
Ultrafast Video Attention Prediction with Coupled Knowledge Distillation
To address these issues, we design an extremely light-weight network with ultrafast speed, named UVA-Net.
Low-resolution Face Recognition in the Wild via Selective Knowledge Distillation
In this approach, a two-stream convolutional neural network (CNN) is first initialized to recognize high-resolution faces and resolution-degraded faces with a teacher stream and a student stream, respectively.
Single Reference Image based Scene Relighting via Material Guided Filtering
We propose a novel outdoor scene relighting method, which needs only a single reference image and is based on material constrained layer decomposition.
Predicting Aesthetic Score Distribution through Cumulative Jensen-Shannon Divergence
Thus, a novel CNN based on the Cumulative distribution with Jensen-Shannon divergence (CJS-CNN) is presented to predict the aesthetic score distribution of human ratings, with a new reliability-sensitive learning method based on the kurtosis of the score distribution, which eliminates the requirement of the original full data of human ratings (without normalization).
Privacy Preserving Face Retrieval in the Cloud for Mobile Users
The experimental results reveal that our protocol can successfully retrieve the proper photos from the cloud server and protect the user photos and the face detector.
Detecting Masked Faces in the Wild With LLE-CNNs
Detecting masked faces (i. e., faces with occlusions) is a challenging task due to two main reasons: 1)the absence of large datasets of masked faces, and 2)the absence of facial cues from the masked regions.
Efficient Privacy Preserving Viola-Jones Type Object Detection via Random Base Image Representation
Only the base images are submitted randomly to the cloud server.
ILGNet: Inception Modules with Connected Local and Global Features for Efficient Image Aesthetic Quality Classification using Domain Adaptation
Thus, it is easy to use a pre-trained GoogLeNet for large-scale image classification problem and fine tune our connected layers on an large scale database of aesthetic related images: AVA, i. e. \emph{domain adaptation}.
