Search Results for author:
Found 42 papers, 19 papers with code
Model-Based Offline Reinforcement Learning with Adversarial Data Augmentation
To address these challenges, we introduce Model-based Offline Reinforcement learning with AdversariaL data augmentation (MORAL).
Robust Dataset Distillation by Matching Adversarial Trajectories
To address this limitation, we introduce the task of ``robust dataset distillation", a novel paradigm that embeds adversarial robustness into the synthetic datasets during the distillation process.
SafeDialBench: A Fine-Grained Safety Benchmark for Large Language Models in Multi-Turn Dialogues with Diverse Jailbreak Attacks
With the rapid advancement of Large Language Models (LLMs), the safety of LLMs has been a critical concern requiring precise assessment.
Causal Information Prioritization for Efficient Reinforcement Learning
Current Reinforcement Learning (RL) methods often suffer from sample-inefficiency, resulting from blind exploration strategies that neglect causal relationships among states, actions, and rewards.
Towards Empowerment Gain through Causal Structure Learning in Model-Based RL
To improve learning efficiency and controllability, we propose a novel framework, Empowerment through Causal Learning (ECL), where an agent with the awareness of causal dynamics models achieves empowerment-driven exploration and optimizes its causal structure for task learning.
Distractor-free Generalizable 3D Gaussian Splatting
To achieve these objectives, DGGS introduces a scene-agnostic reference-based mask prediction and refinement methodology during training phase, coupled with a training view selection strategy, effectively improving distractor prediction accuracy and training stability.
Magnetic Preference Optimization: Achieving Last-iterate Convergence for Language Model Alignment
Self-play methods have demonstrated remarkable success in enhancing model capabilities across various domains.
3D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunities
3D Gaussian Splatting (3DGS) has emerged as a prominent technique with the potential to become a mainstream method for 3D representations.
Zero-Shot Video Editing through Adaptive Sliding Score Distillation
To address these challenges, this study proposes a novel paradigm of video-based score distillation, facilitating direct manipulation of original video content.
Analogist: Out-of-the-box Visual In-Context Learning with Image Diffusion Model
For visual prompting, we propose a self-attention cloning (SAC) method to guide the fine-grained structural-level analogy between image examples.
ONNXPruner: ONNX-Based General Model Pruning Adapter
However, the practical application of these algorithms across various models and platforms remains a significant challenge.
Exploiting Inter-sample and Inter-feature Relations in Dataset Distillation
However, these methods face two primary limitations: the dispersed feature distribution within the same class in synthetic datasets, reducing class discrimination, and an exclusive focus on mean feature consistency, lacking precision and comprehensiveness.
Stitching, Fine-tuning, Re-training: A SAM-enabled Framework for Semi-supervised 3D Medical Image Segmentation
To reduce the annotation cost and maintain satisfactory performance, in this work, we leverage the capabilities of SAM for establishing semi-supervised medical image segmentation models.
CasIL: Cognizing and Imitating Skills via a Dual Cognition-Action Architecture
Heuristically, we extend the usual notion of action to a dual Cognition (high-level)-Action (low-level) architecture by introducing intuitive human cognitive priors, and propose a novel skill IL framework through human-robot interaction, called Cognition-Action-based Skill Imitation Learning (CasIL), for the robotic agent to effectively cognize and imitate the critical skills from raw visual demonstrations.
InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules
By utilizing multiple plug-and-play HyperNet modules, InsertNeRF dynamically tailors NeRF's weights to specific reference scenes, transforming multi-scale sampling-aware features into scene-specific representations.
Where and How: Mitigating Confusion in Neural Radiance Fields from Sparse Inputs
Neural Radiance Fields from Sparse input} (NeRF-S) have shown great potential in synthesizing novel views with a limited number of observed viewpoints.
A Unified Framework for Contrastive Learning from a Perspective of Affinity Matrix
In this study, we present a new unified contrastive learning representation framework (named UniCLR) suitable for all the above four kinds of methods from a novel perspective of basic affinity matrix.
Modeling Inter-Class and Intra-Class Constraints in Novel Class Discovery
Specifically, we propose an inter-class sKLD constraint to effectively exploit the disjoint relationship between labelled and unlabelled classes, enforcing the separability for different classes in the embedding space.
Playing Lottery Tickets in Style Transfer Models
(2) Using iterative magnitude pruning, we find the matching subnetworks at 89. 2% sparsity in AdaIN and 73. 7% sparsity in SANet, which demonstrates that style transfer models can play lottery tickets too.
Attention-based Interpretation and Response to The Trade-Off of Adversarial Training
To boost the robustness of a model against adversarial examples, adversarial training has been regarded as a benchmark method.
LibFewShot: A Comprehensive Library for Few-shot Learning
Furthermore, based on LibFewShot, we provide comprehensive evaluations on multiple benchmarks with various backbone architectures to evaluate common pitfalls and effects of different training tricks.
Trip-ROMA: Self-Supervised Learning with Triplets and Random Mappings
However, in small data regimes, we can not obtain a sufficient number of negative pairs or effectively avoid the over-fitting problem when negatives are not used at all.
Cross-Modality Brain Tumor Segmentation via Bidirectional Global-to-Local Unsupervised Domain Adaptation
Specifically, a bidirectional image synthesis and segmentation module is proposed to segment the brain tumor using the intermediate data distributions generated for the two domains, which includes an image-to-image translator and a shared-weighted segmentation network.
LoFGAN: Fusing Local Representations for Few-Shot Image Generation
Given only a few available images for a novel unseen category, few-shot image generation aims to generate more data for this category.
CariMe: Unpaired Caricature Generation with Multiple Exaggerations
Previous caricature generation methods are obsessed with predicting definite image warping from a given photo while ignoring the intrinsic representation and distribution for exaggerations in caricatures.
Unsupervised Domain Attention Adaptation Network for Caricature Attribute Recognition
The implementation of the proposed method is available at https://github. com/KeleiHe/DAAN.
Manifold Alignment for Semantically Aligned Style Transfer
In this paper, we make a new assumption that image features from the same semantic region form a manifold and an image with multiple semantic regions follows a multi-manifold distribution.
MetricUNet: Synergistic Image- and Voxel-Level Learning for Precise CT Prostate Segmentation via Online Sampling
Therefore, the proposed network has a dual-branch architecture that tackles two tasks: 1) a segmentation sub-network aiming to generate the prostate segmentation, and 2) a voxel-metric learning sub-network aiming to improve the quality of the learned feature space supervised by a metric loss.
Asymmetric Distribution Measure for Few-shot Learning
Given the natural asymmetric relation between a query image and a support class, we argue that an asymmetric measure is more suitable for metric-based few-shot learning.
MW-GAN: Multi-Warping GAN for Caricature Generation with Multi-Style Geometric Exaggeration
Given an input face photo, the goal of caricature generation is to produce stylized, exaggerated caricatures that share the same identity as the photo.
Defensive Few-shot Learning
(2) how to narrow the distribution gap between clean and adversarial examples under the few-shot setting?
Progressive Cross-camera Soft-label Learning for Semi-supervised Person Re-identification
In this paper, we focus on the semi-supervised person re-identification (Re-ID) case, which only has the intra-camera (within-camera) labels but not inter-camera (cross-camera) labels.
GreyReID: A Two-stream Deep Framework with RGB-grey Information for Person Re-identification
Moreover, in the training process, we adopt the joint learning scheme to simultaneously train each branch by the independent loss function, which can enhance the generalization ability of each branch.
Adversarial Camera Alignment Network for Unsupervised Cross-camera Person Re-identification
To achieve the camera alignment, we develop a Multi-Camera Adversarial Learning (MCAL) to map images of different cameras into a shared subspace.
A Novel Unsupervised Camera-aware Domain Adaptation Framework for Person Re-identification
For the first issue, we highlight the presence of camera-level sub-domains as a unique characteristic of person Re-ID, and develop camera-aware domain adaptation to reduce the discrepancy not only between source and target domains but also across these sub-domains.
Ranked #20 on
Unsupervised Domain Adaptation
on Market to Duke
Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learning
Its key difference from the literature is the replacement of the image-level feature based measure in the final layer by a local descriptor based image-to-class measure.
CariGAN: Caricature Generation through Weakly Paired Adversarial Learning
Furthermore, an attention mechanism is introduced to encourage our model to focus on the key facial parts so that more vivid details in these regions can be generated.
A Multilayer Framework for Online Metric Learning
Furthermore, in a progressively and nonlinearly learning way, MLOML has a stronger learning ability than traditional online metric learning in the case of limited available training data.
Cross-Domain Adversarial Auto-Encoder
This makes the proposed framework different from the current work of cross-domain transformation.
MaskReID: A Mask Based Deep Ranking Neural Network for Person Re-identification
Lastly, considering person retrieval is a special image retrieval task, we propose a novel ranking loss to optimize the whole network.
WebCaricature: a benchmark for caricature recognition
In this paper, a new caricature dataset is built, with the objective to facilitate research in caricature recognition.
OPML: A One-Pass Closed-Form Solution for Online Metric Learning
To achieve a low computational cost when performing online metric learning for large-scale data, we present a one-pass closed-form solution namely OPML in this paper.
