Search Results for author:
Found 36 papers, 26 papers with code
Experience-driven Networking: A Deep Reinforcement Learning based Approach
Modern communication networks have become very complicated and highly dynamic, which makes them hard to model, predict and control.
Deep Residual Correction Network for Partial Domain Adaptation
Deep domain adaptation methods have achieved appealing performance by learning transferable representations from a well-labeled source domain to a different but related unlabeled target domain.
Curiosity-Driven Energy-Efficient Worker Scheduling in Vehicular Crowdsourcing: A Deep Reinforcement Learning Approach
Spatial crowdsourcing (SC) utilizes the potential of a crowd to accomplish certain location based tasks.
Domain Conditioned Adaptation Network
Most existing deep DA models only focus on aligning feature representations of task-specific layers across domains while integrating a totally shared convolutional architecture for source and target.
Simultaneous Semantic Alignment Network for Heterogeneous Domain Adaptation
In this paper, we propose a Simultaneous Semantic Alignment Network (SSAN) to simultaneously exploit correlations among categories and align the centroids for each category across domains.
Social-Aware Incentive Mechanism for VehicularCrowdsensing by Deep Reinforcement Learning
Vehicular crowdsensing (VCS) takes the advantage of vehicles’ mobility and exploits both the crowd wisdom and sensing abilities offered by vehicle drivers’ carried smart mobile devices and on-board sensors to accomplish challenging sensing tasks.
Bi-Classifier Determinacy Maximization for Unsupervised Domain Adaptation
Motivated by the observation that target samples cannot always be separated distinctly by the decision boundary, here in the proposed BCDM, we design a novel classifier determinacy disparity (CDD) metric, which formulates classifier discrepancy as the class relevance of distinct target predictions and implicitly introduces constraint on the target feature discriminability.
Generalized Domain Conditioned Adaptation Network
Domain Adaptation (DA) attempts to transfer knowledge learned in the labeled source domain to the unlabeled but related target domain without requiring large amounts of target supervision.
Transferable Semantic Augmentation for Domain Adaptation
To remedy this, we propose a Transferable Semantic Augmentation (TSA) approach to enhance the classifier adaptation ability through implicitly generating source features towards target semantics.
MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition
Real-world training data usually exhibits long-tailed distribution, where several majority classes have a significantly larger number of samples than the remaining minority classes.
Ranked #2 on
Long-tail Learning
on CIFAR-100-LT (ρ=200)
Dynamic Domain Adaptation for Efficient Inference
Domain adaptation (DA) enables knowledge transfer from a labeled source domain to an unlabeled target domain by reducing the cross-domain distribution discrepancy.
Semantic Distribution-aware Contrastive Adaptation for Semantic Segmentation
Specifically, we first design a pixel-wise contrastive loss by considering the correspondences between semantic distributions and pixel-wise representations from both domains.
Embedded Discriminative Attention Mechanism for Weakly Supervised Semantic Segmentation
In inference, we directly use the activation masks from the DA layer as pseudo-labels for segmentation.
I2V-GAN: Unpaired Infrared-to-Visible Video Translation
Human vision is often adversely affected by complex environmental factors, especially in night vision scenarios.
Semantic Concentration for Domain Adaptation
To tackle this issue, we propose Semantic Concentration for Domain Adaptation (SCDA), which encourages the model to concentrate on the most principal features via the pair-wise adversarial alignment of prediction distributions.
Exploiting Both Domain-specific and Invariant Knowledge via a Win-win Transformer for Unsupervised Domain Adaptation
Unsupervised Domain Adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain.
Towards Fewer Annotations: Active Learning via Region Impurity and Prediction Uncertainty for Domain Adaptive Semantic Segmentation
Self-training has greatly facilitated domain adaptive semantic segmentation, which iteratively generates pseudo labels on unlabeled target data and retrains the network.
Active Learning for Domain Adaptation: An Energy-Based Approach
Unsupervised domain adaptation has recently emerged as an effective paradigm for generalizing deep neural networks to new target domains.
Pareto Domain Adaptation
Domain adaptation (DA) attempts to transfer the knowledge from a labeled source domain to an unlabeled target domain that follows different distribution from the source.
LegoDNN: Block-grained Scaling of Deep Neural Networks for Mobile Vision
The prior art sheds light on exploring the accuracy-resource tradeoff by scaling the model sizes in accordance to resource dynamics.
CADRE: A Cascade Deep Reinforcement Learning Framework for Vision-based Autonomous Urban Driving
Vision-based autonomous urban driving in dense traffic is quite challenging due to the complicated urban environment and the dynamics of the driving behaviors.
Causality Inspired Representation Learning for Domain Generalization
Specifically, we assume that each input is constructed from a mix of causal factors (whose relationship with the label is invariant across domains) and non-causal factors (category-independent), and only the former cause the classification judgments.
SePiCo: Semantic-Guided Pixel Contrast for Domain Adaptive Semantic Segmentation
Domain adaptive semantic segmentation attempts to make satisfactory dense predictions on an unlabeled target domain by utilizing the supervised model trained on a labeled source domain.
Ranked #4 on
Semantic Segmentation
on GTAV-to-Cityscapes Labels
ROMA: Cross-Domain Region Similarity Matching for Unpaired Nighttime Infrared to Daytime Visible Video Translation
To be specific, ROMA could efficiently translate the unpaired nighttime infrared videos into fine-grained daytime visible ones, meanwhile maintain the spatiotemporal consistency via matching the cross-domain region similarity.
Improving Transferability for Domain Adaptive Detection Transformers
We implement the findings and the alignment modules into our adaptation method, and it benchmarks the DETR-style detector on the domain shift settings.
Making the Best of Both Worlds: A Domain-Oriented Transformer for Unsupervised Domain Adaptation
To alleviate these issues, we propose to simultaneously conduct feature alignment in two individual spaces focusing on different domains, and create for each space a domain-oriented classifier tailored specifically for that domain.
VBLC: Visibility Boosting and Logit-Constraint Learning for Domain Adaptive Semantic Segmentation under Adverse Conditions
However, previous methods often reckon on additional reference images of the same scenes taken from normal conditions, which are quite tough to collect in reality.
Ranked #7 on
Domain Adaptation
on Cityscapes to ACDC
FedKNOW: Federated Continual Learning with Signature Task Knowledge Integration at Edge
Upon training for a new task, the gradient integrator ensures the prevention of catastrophic forgetting and mitigation of negative knowledge transfer by effectively combining signature tasks identified from the past local tasks and other clients' current tasks through the global model.
On the Difficulty of Unpaired Infrared-to-Visible Video Translation: Fine-Grained Content-Rich Patches Transfer
Explicit visible videos can provide sufficient visual information and facilitate vision applications.
Borrowing Knowledge From Pre-trained Language Model: A New Data-efficient Visual Learning Paradigm
To address this issue, this paper presents a novel approach that seeks to leverage linguistic knowledge for data-efficient visual learning.
Hierarchical Memory Pool Based Edge Semi-Supervised Continual Learning Method
In addition, in order to further reduce the computational overhead for unlabeled samples, EdgeHML leverages a progressive learning method.
Dirichlet-based Uncertainty Calibration for Active Domain Adaptation
Active domain adaptation (DA) aims to maximally boost the model adaptation on a new target domain by actively selecting limited target data to annotate, whereas traditional active learning methods may be less effective since they do not consider the domain shift issue.
CoinSeg: Contrast Inter- and Intra- Class Representations for Incremental Segmentation
However, most state-of-the-art methods use the freeze strategy for stability, which compromises the model's plasticity. In contrast, releasing parameter training for plasticity could lead to the best performance for all categories, but this requires discriminative feature representation. Therefore, we prioritize the model's plasticity and propose the Contrast inter- and intra-class representations for Incremental Segmentation (CoinSeg), which pursues discriminative representations for flexible parameter tuning.
HiBid: A Cross-Channel Constrained Bidding System with Budget Allocation by Hierarchical Offline Deep Reinforcement Learning
Online display advertising platforms service numerous advertisers by providing real-time bidding (RTB) for the scale of billions of ad requests every day.
An Efficient Generalizable Framework for Visuomotor Policies via Control-aware Augmentation and Privilege-guided Distillation
Visuomotor policies, which learn control mechanisms directly from high-dimensional visual observations, confront challenges in adapting to new environments with intricate visual variations.
Benchmarking the Text-to-SQL Capability of Large Language Models: A Comprehensive Evaluation
Then we formulate five evaluation tasks to comprehensively assess the performance of diverse methods across various LLMs throughout the Text-to-SQL process. Our study highlights the performance disparities among LLMs and proposes optimal in-context learning solutions tailored to each task.
