Search Results for author:
Found 31 papers, 7 papers with code
Fast Adversarial Training with Weak-to-Strong Spatial-Temporal Consistency in the Frequency Domain on Videos
Second, existing methods struggle with the trade-off between clean accuracy and adversarial robustness.
Anti-Aesthetics: Protecting Facial Privacy against Customized Text-to-Image Synthesis
The rise of customized diffusion models has spurred a boom in personalized visual content creation, but also poses risks of malicious misuse, severely threatening personal privacy and copyright protection.
Exploring Adversarial Transferability between Kolmogorov-arnold Networks
To explore this critical safety issue, we conduct an analysis and find that due to overfitting to the specific basis functions of KANs, they possess poor adversarial transferability among different KANs.
Concept Corrector: Erase concepts on the fly for text-to-image diffusion models
In this paper, motivated by the notion that concept erasure on the output side, i. e. generated images, may be more direct and effective, we propose to check concepts based on intermediate-generated images and correct them in the remainder of the generation process.
Fast Direct: Query-Efficient Online Black-box Guidance for Diffusion-model Target Generation
In this work, we propose a novel and simple algorithm, $\textbf{Fast Direct}$, for query-efficient online black-box target generation.
Imitation from Diverse Behaviors: Wasserstein Quality Diversity Imitation Learning with Single-Step Archive Exploration
Learning diverse and high-performance behaviors from a limited set of demonstrations is a grand challenge.
Sharpness-Aware Black-Box Optimization
To address those problems in black-box optimization, we propose a novel Sharpness-Aware Black-box Optimization (SABO) algorithm, which applies a sharpness-aware minimization strategy to improve the model generalization.
Quality Diversity Imitation Learning
Imitation learning (IL) has shown great potential in various applications, such as robot control.
Diversified Batch Selection for Training Acceleration
The remarkable success of modern machine learning models on large datasets often demands extensive training time and resource consumption.
Covariance-Adaptive Sequential Black-box Optimization for Diffusion Targeted Generation
Diffusion models have demonstrated great potential in generating high-quality content for images, natural language, protein domains, etc.
RS-Corrector: Correcting the Racial Stereotypes in Latent Diffusion Models
Extensive empirical evaluations demonstrate that the introduced \themodel effectively corrects the racial stereotypes of the well-trained Stable Diffusion model while leaving the original model unchanged.
DeltaSpace: A Semantic-aligned Feature Space for Flexible Text-guided Image Editing
Based on DeltaSpace, we propose a novel framework called DeltaEdit, which maps the CLIP visual feature differences to the latent space directions of a generative model during the training phase, and predicts the latent space directions from the CLIP textual feature differences during the inference phase.
InfoStyler: Disentanglement Information Bottleneck for Artistic Style Transfer
InfoStyler formulates the disentanglement representation learning as an information compression problem by eliminating style statistics from the content image and removing the content structure from the style image.
3D-Aware Adversarial Makeup Generation for Facial Privacy Protection
The privacy and security of face data on social media are facing unprecedented challenges as it is vulnerable to unauthorized access and identification.
Earning Extra Performance from Restrictive Feedbacks
Unlike existing model tuning methods where the target data is always ready for calculating model gradients, the model providers in EXPECTED only see some feedbacks which could be as simple as scalars, such as inference accuracy or usage rate.
Unfolded Self-Reconstruction LSH: Towards Machine Unlearning in Approximate Nearest Neighbour Search
This need requires the ANN search algorithm to support fast online data deletion and insertion.
Adversary-Aware Partial label learning with Label distillation
However, conventional partial-label learning (PLL) methods are still vulnerable to the high ratio of noisy partial labels, especially in a large labelling space.
DeltaEdit: Exploring Text-free Training for Text-Driven Image Manipulation
Our key idea is to investigate and identify a space, namely delta image and text space that has well-aligned distribution between CLIP visual feature differences of two images and CLIP textual embedding differences of source and target texts.
DRAN: Detailed Region-Adaptive Normalization for Conditional Image Synthesis
To evaluate the effectiveness and show the general use of our method, we conduct a set of experiments on makeup transfer and semantic image synthesis.
Fine-Tuning from Limited Feedbacks
Instead of learning from scratch, fine-tuning a pre-trained model to fit a related target dataset of interest or downstream tasks has been a handy trick to achieve the desired performance.
Neural Optimization Kernel: Towards Robust Deep Learning
We further establish a new generalization bound of our deep structured approximated NOK architecture.
SOGAN: 3D-Aware Shadow and Occlusion Robust GAN for Makeup Transfer
Since human faces are symmetrical in the UV space, we can conveniently remove the undesired shadow and occlusion from the reference image by carefully designing a Flip Attention Module (FAM).
A Simple Sparse Denoising Layer for Robust Deep Learning
In this work, we take an initial step to designing a simple robust layer as a lightweight plug-in for vanilla deep models.
Learning Efficient Planning-based Rewards for Imitation Learning
Our method learns useful planning computations with a meaningful reward function that focuses on the resulting region of an agent executing an action.
Subgroup-based Rank-1 Lattice Quasi-Monte Carlo
We theoretically prove a lower and an upper bound of the minimum pairwise distance of any non-degenerate rank-1 lattice.
Intrinsic Reward Driven Imitation Learning via Generative Model
Thus, our module provides the imitation agent both the intrinsic intention of the demonstrator and a better exploration ability, which is critical for the agent to outperform the demonstrator.
Black-box Optimizer with Implicit Natural Gradient
Empirically, our method with full matrix update achieves competitive performance compared with one of the state-of-the-art method CMA-ES on benchmark test problems.
Curriculum Loss: Robust Learning and Generalization against Label Corruption
Although the 0-1 loss has some robust properties, it is difficult to optimize.
Efficient Batch Black-box Optimization with Deterministic Regret Bounds
In this work, we investigate black-box optimization from the perspective of frequentist kernel methods.
Marginalized Average Attentional Network for Weakly-Supervised Learning
The MAAN employs a novel marginalized average aggregation (MAA) module and learns a set of latent discriminative probabilities in an end-to-end fashion.
Ranked #14 on
Weakly Supervised Action Localization
on ActivityNet-1.3
(mAP@0.5 metric)
Weakly Supervised Action Localization
Weakly-supervised Learning
+2
Spherical Structured Feature Maps for Kernel Approximation
According to (Brauchart \& Grabner, 2015), optimizing the discrete Riesz s-energy can generate asymptotically uniformly distributed point set on $\mathbb{S}^{d-1}$.
