Search Results for author:
Found 38 papers, 16 papers with code
Fix-Filter-Fix: Intuitively Connect Any Models for Effective Bug Fixing
Obviously, unchanged fix is not the correct fix because it is the same as the buggy code that needs to be fixed.
StyleBooth: Image Style Editing with Multimodal Instruction
We integrate encoded textual instruction and image exemplar as a unified condition for diffusion model, enabling the editing of original image following multimodal instructions.
Locate, Assign, Refine: Taming Customized Image Inpainting with Text-Subject Guidance
The process involves (i) Locate: concatenating the noise with masked scene image to achieve precise regional editing, (ii) Assign: employing decoupled cross-attention mechanism to accommodate multi-modal guidance, and (iii) Refine: using a novel RefineNet to supplement subject details.
Make Me Happier: Evoking Emotions Through Image Diffusion Models
For the first time, we present a novel challenge of emotion-evoked image generation, aiming to synthesize images that evoke target emotions while retaining the semantics and structures of the original scenes.
Privacy-Preserving Low-Rank Adaptation for Latent Diffusion Models
To mitigate this issue, we propose Stable PrivateLoRA that adapts the LDM by minimizing the ratio of the adaptation loss to the MI gain, which implicitly rescales the gradient and thus stabilizes the optimization.
SCEdit: Efficient and Controllable Image Diffusion Generation via Skip Connection Editing
Image diffusion models have been utilized in various tasks, such as text-to-image generation and controllable image synthesis.
Fair Text-to-Image Diffusion via Fair Mapping
In this paper, we address the limitations of existing text-to-image diffusion models in generating demographically fair results when given human-related descriptions.
AutoLoRa: A Parameter-Free Automated Robust Fine-Tuning Framework
To mitigate this issue, we propose a low-rank (LoRa) branch that disentangles RFT into two distinct components: optimizing natural objectives via the LoRa branch and adversarial objectives via the FE.
BadLabel: A Robust Perspective on Evaluating and Enhancing Label-noise Learning
To address the challenge posed by BadLabel, we further propose a robust LNL method that perturbs the labels in an adversarial manner at each epoch to make the loss values of clean and noisy labels again distinguishable.
Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularization
To improve transferability, the existing work introduced the standard invariant regularization (SIR) to impose style-independence property to SCL, which can exempt the impact of nuisance style factors in the standard representation.
Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selection
Adversarial contrastive learning (ACL) does not require expensive data annotations but outputs a robust representation that withstands adversarial attacks and also generalizes to a wide range of downstream tasks.
GAT: Guided Adversarial Training with Pareto-optimal Auxiliary Tasks
While leveraging additional training data is well established to improve adversarial robustness, it incurs the unavoidable cost of data collection and the heavy computation to train models.
Adversarial Training with Complementary Labels: On the Benefit of Gradually Informative Attacks
Adversarial training (AT) with imperfect supervision is significant but receives limited attention.
FuncFooler: A Practical Black-box Attack Against Learning-based Binary Code Similarity Detection Methods
The binary code similarity detection (BCSD) method measures the similarity of two binary executable codes.
Accelerating Score-based Generative Models for High-Resolution Image Synthesis
To ensure stability of convergence in sampling and generation quality, however, this sequential sampling process has to take a small step size and many sampling iterations (e. g., 2000).
Diverse Instance Discovery: Vision-Transformer for Instance-Aware Multi-Label Image Recognition
Finally, we propose a weakly supervised object localization-based approach to extract multi-scale local features, to form a multi-view pipeline.
On the Effectiveness of Adversarial Training against Backdoor Attacks
To explore whether adversarial training could defend against backdoor attacks or not, we conduct extensive experiments across different threat models and perturbation budgets, and find the threat model in adversarial training matters.
Adversarial Attack and Defense for Non-Parametric Two-Sample Tests
Furthermore, we theoretically find that the adversary can also degrade the lower bound of a TST's test power, which enables us to iteratively minimize the test criterion in order to search for adversarial pairs.
Towards Adversarially Robust Deep Image Denoising
Secondly, to robustify DIDs, we propose an adversarial training strategy, hybrid adversarial training ({\sc HAT}), that jointly trains DIDs with adversarial and non-adversarial noisy data to ensure that the reconstruction quality is high and the denoisers around non-adversarial data are locally smooth.
Collaborate to Defend Against Adversarial Attacks
However, an ensemble still wastes the limited capacity of multiple models.
Does Adversarial Robustness Really Imply Backdoor Vulnerability?
Based on thorough experiments, we find that such trade-off ignores the interactions between the perturbation budget of adversarial training and the magnitude of the backdoor trigger.
DRDF: Determining the Importance of Different Multimodal Information with Dual-Router Dynamic Framework
In multimodal tasks, we find that the importance of text and image modal information is different for different input cases, and for this motivation, we propose a high-performance and highly general Dual-Router Dynamic Framework (DRDF), consisting of Dual-Router, MWF-Layer, experts and expert fusion unit.
RAMS-Trans: Recurrent Attention Multi-scale Transformer forFine-grained Image Recognition
We propose the recurrent attention multi-scale transformer (RAMS-Trans), which uses the transformer's self-attention to recursively learn discriminative region attention in a multi-scale manner.
Ranked #7 on
Fine-Grained Image Classification
on Stanford Dogs
Fine-Grained Image Classification
Fine-Grained Image Recognition
Reliable Adversarial Distillation with Unreliable Teachers
However, when considering adversarial robustness, teachers may become unreliable and adversarial distillation may not work: teachers are pretrained on their own adversarial data, and it is too demanding to require that teachers are also good at every adversarial data queried by students.
NoiLIn: Improving Adversarial Training and Correcting Stereotype of Noisy Labels
First, we thoroughly investigate noisy labels (NLs) injection into AT's inner maximization and outer minimization, respectively and obtain the observations on when NL injection benefits AT.
Guided Interpolation for Adversarial Training
To enhance adversarial robustness, adversarial training learns deep neural networks on the adversarial variants generated by their natural data.
CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection
By comparing \textit{non-robust} (normally trained) and \textit{robustified} (adversarially trained) models, we observe that adversarial training (AT) robustifies CNNs by aligning the channel-wise activations of adversarial data with those of their natural counterparts.
Understanding the Interaction of Adversarial Training with Noisy Labels
A recent adversarial training (AT) study showed that the number of projected gradient descent (PGD) steps to successfully attack a point (i. e., find an adversarial example in its proximity) is an effective measure of the robustness of this point.
Learning Diverse-Structured Networks for Adversarial Robustness
In adversarial training (AT), the main focus has been the objective and optimizer while the model has been less studied, so that the models being used are still those classic ones in standard training (ST).
Maximum Mean Discrepancy Test is Aware of Adversarial Attacks
However, it has been shown that the MMD test is unaware of adversarial attacks -- the MMD test failed to detect the discrepancy between natural and adversarial data.
Geometry-aware Instance-reweighted Adversarial Training
The belief was challenged by recent studies where we can maintain the robustness and improve the accuracy.
Robust Federated Recommendation System
We argue that the key to Byzantine detection is monitoring of gradients of the model parameters of clients.
Hierarchically Fair Federated Learning
When the federated learning is adopted among competitive agents with siloed datasets, agents are self-interested and participate only if they are fairly rewarded.
Attacks Which Do Not Kill Training Make Adversarial Learning Stronger
Adversarial training based on the minimax formulation is necessary for obtaining adversarial robustness of trained models.
Where is the Bottleneck of Adversarial Learning with Unlabeled Data?
Deep neural networks (DNNs) are incredibly brittle due to adversarial examples.
Towards Robust ResNet: A Small Step but A Giant Leap
Our analytical studies reveal that the step factor h in the Euler method is able to control the robustness of ResNet in both its training and generalization.
Smooth Inter-layer Propagation of Stabilized Neural Networks for Classification
Recent work has studied the reasons for the remarkable performance of deep neural networks in image classification.
