Search Results for author:
Found 24 papers, 7 papers with code
Adversarial Training with Bi-directional Likelihood Regularization for Visual Classification
We call such a new robust training strategy the adversarial training with bi-directional likelihood regularization (ATBLR) method.
DHCP: Detecting Hallucinations by Cross-modal Attention Pattern in Large Vision-Language Models
Large vision-language models (LVLMs) have demonstrated exceptional performance on complex multimodal tasks.
Exploring Information-Theoretic Metrics Associated with Neural Collapse in Supervised Training
Experiments show that matrix entropy cannot solely describe the interaction of the information content of data representation and classification head weights but it can effectively reflect the similarity and clustering behavior of the data.
PIP: Detecting Adversarial Examples in Large Vision-Language Models via Attention Patterns of Irrelevant Probe Questions
We propose an unconventional method named PIP, which utilizes the attention patterns of one randomly selected irrelevant probe question (e. g., "Is there a clock?")
UrbanWorld: An Urban World Model for 3D City Generation
Toward this problem, we propose UrbanWorld, the first generative urban world model that can automatically create a customized, realistic and interactive 3D urban world with flexible control conditions.
Strictly-ID-Preserved and Controllable Accessory Advertising Image Generation
Customized generative text-to-image models have the ability to produce images that closely resemble a given subject.
Isolated Diffusion: Optimizing Multi-Concept Text-to-Image Generation Training-Freely with Isolated Diffusion Guidance
This paper presents a general approach for text-to-image diffusion models to address the mutual interference between different subjects and their attachments in complex scenes, pursuing better text-image consistency.
Advancing Out-of-Distribution Detection through Data Purification and Dynamic Activation Function Design
Our work addresses this challenge by enhancing the detection and management of OOD samples in neural networks.
RhythmFormer: Extracting rPPG Signals Based on Hierarchical Temporal Periodic Transformer
Due to the periodicity nature of rPPG, the long-range dependency capturing capacity of the Transformer was assumed to be advantageous for such signals.
Learning a Graph Neural Network with Cross Modality Interaction for Image Fusion
Finally, we merge all graph features to get the fusion result.
DomainStudio: Fine-Tuning Diffusion Models for Domain-Driven Image Generation using Limited Data
Typical diffusion models and modern large-scale conditional generative models like text-to-image generative models are vulnerable to overfitting when fine-tuned on extremely limited data.
Few-shot 3D Shape Generation
Our approach only needs the silhouettes of few-shot target samples as training data to learn target geometry distributions and achieve generated shapes with diverse topology and textures.
MotionVideoGAN: A Novel Video Generator Based on the Motion Space Learned from Image Pairs
We present MotionVideoGAN, a novel video generator synthesizing videos based on the motion space learned by pre-trained image pair generators.
Gestalt-Guided Image Understanding for Few-Shot Learning
Due to the scarcity of available data, deep learning does not perform well on few-shot learning tasks.
Distribution Aligned Feature Clustering for Zero-Shot Sketch-Based Image Retrieval
Zero-Shot Sketch-Based Image Retrieval (ZS-SBIR) is a challenging cross-modal retrieval task.
Few-shot Image Generation via Masked Discrimination
It strengthens global image discrimination and guides adapted GANs to preserve more information learned from source domains for higher image quality.
Defending Against Universal Adversarial Patches by Clipping Feature Norms
Physical-world adversarial attacks based on universal adversarial patches have been proved to be able to mislead deep convolutional neural networks (CNNs), exposing the vulnerability of real-world visual classification systems based on CNNs.
Shaping Deep Feature Space towards Gaussian Mixture for Visual Classification
In this work, we propose a Gaussian mixture (GM) loss function for deep neural networks for visual classification.
Teacher-Critical Training Strategies for Image Captioning
To effectively learn from the teacher model, we propose Teacher-Critical Training Strategies (TCTS) for both XE and RL training to facilitate better learning processes for the caption model.
Rethinking Feature Distribution for Loss Functions in Image Classification
We propose a large-margin Gaussian Mixture (L-GM) loss for deep neural networks in classification tasks.
Towards End-to-End Face Recognition through Alignment Learning
Although these methods differ essentially in many aspects, a common practice of them is to specifically align the facial area based on the prior knowledge of human face structure before feature extraction.
Automatic Image Cropping : A Computational Complexity Study
Attention based automatic image cropping aims at preserving the most visually important region in an image.
Superpixel Segmentation Using Linear Spectral Clustering
We present in this paper a superpixel segmentation algorithm called Linear Spectral Clustering (LSC), which produces compact and uniform superpixels with low computational costs.
