Search Results for author:
Found 51 papers, 34 papers with code
Learning from Missing Relations: Contrastive Learning with Commonsense Knowledge Graphs for Commonsense Inference
Commonsense inference poses a unique challenge to reason and generate the physical, social, and causal conditions of a given event.
DECOR:Decomposition and Projection of Text Embeddings for Text-to-Image Customization
However, fine-tuning with a limited number of reference images often leads to overfitting, resulting in issues such as prompt misalignment or content leakage.
Look Every Frame All at Once: Video-Ma$^2$mba for Efficient Long-form Video Understanding with Multi-Axis Gradient Checkpointing
With the growing scale and complexity of video data, efficiently processing long video sequences poses significant challenges due to the quadratic increase in memory and computational demands associated with existing transformer-based Large Multi-modal Models (LMMs).
SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis
Despite advances in Large Multi-modal Models, applying them to long and untrimmed video content remains challenging due to limitations in context length and substantial memory overhead.
D-Cube: Exploiting Hyper-Features of Diffusion Model for Robust Medical Classification
The integration of deep learning technologies in medical imaging aims to enhance the efficiency and accuracy of cancer diagnosis, particularly for pancreatic and breast cancers, which present significant diagnostic challenges due to their high mortality rates and complex imaging characteristics.
CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models
Our approach sets a new state-of-the-art on the MP-100 benchmark in the challenging 1-shot setting, marking a significant advancement in the field of category-agnostic pose estimation.
Ranked #1 on
2D Pose Estimation
on MP-100
C2A: Client-Customized Adaptation for Parameter-Efficient Federated Learning
Despite the versatility of pre-trained language models (PLMs) across domains, their large memory footprints pose significant challenges in federated learning (FL), where the training model has to be distributed between a server and clients.
CleaR: Towards Robust and Generalized Parameter-Efficient Fine-Tuning for Noisy Label Learning
However, as datasets in such environments often contain noisy labels that adversely affect performance, PEFT methods are inevitably exposed to noisy labels.
HiPPO-KAN: Efficient KAN Model for Time Series Analysis
In this study, we introduces a parameter-efficient model that outperforms traditional models in time series forecasting, by integrating High-order Polynomial Projection (HiPPO) theory into the Kolmogorov-Arnold network (KAN) framework.
MELT: Materials-aware Continued Pre-training for Language Model Adaptation to Materials Science
We introduce a novel continued pre-training method, MELT (MatEriaLs-aware continued pre-Training), specifically designed to efficiently adapt the pre-trained language models (PLMs) for materials science.
Mentor-KD: Making Small Language Models Better Multi-step Reasoners
Large Language Models (LLMs) have displayed remarkable performances across various complex tasks by leveraging Chain-of-Thought (CoT) prompting.
Direct Unlearning Optimization for Robust and Safe Text-to-Image Models
In this paper, we propose Direct Unlearning Optimization (DUO), a novel framework for removing Not Safe For Work (NSFW) content from T2I models while preserving their performance on unrelated topics.
CODE: Contrasting Self-generated Description to Combat Hallucination in Large Multi-modal Models
Large Multi-modal Models (LMMs) have recently demonstrated remarkable abilities in visual context understanding and coherent response generation.
Fully Geometric Panoramic Localization
We introduce a lightweight and accurate localization method that only utilizes the geometry of 2D-3D lines.
What if...?: Thinking Counterfactual Keywords Helps to Mitigate Hallucination in Large Multi-modal Models
This paper presents a way of enhancing the reliability of Large Multi-modal Models (LMMs) in addressing hallucination, where the models generate cross-modal inconsistent responses.
Visual Style Prompting with Swapping Self-Attention
Despite their remarkable capability, existing models still face challenges in achieving controlled generation with a consistent style, requiring costly fine-tuning or often inadequately transferring the visual elements due to content leakage.
Causal Unsupervised Semantic Segmentation
Unsupervised semantic segmentation aims to achieve high-quality semantic grouping without human-labeled annotations.
Ranked #1 on
Unsupervised Semantic Segmentation
on COCO-Stuff-81
Sequential Data Generation with Groupwise Diffusion Process
We present the Groupwise Diffusion Model (GDM), which divides data into multiple groups and diffuses one group at one time interval in the forward diffusion process.
LDL: Line Distance Functions for Panoramic Localization
We introduce LDL, a fast and robust algorithm that localizes a panorama to a 3D map using line segments.
Calibrating Panoramic Depth Estimation for Practical Localization and Mapping
While panoramic images can easily capture the surrounding context from commodity devices, the estimated depth shares the limitations of conventional image-based depth estimation; the performance deteriorates under large domain shifts and the absolute values are still ambiguous to infer from 2D observations.
Mitigating Adversarial Vulnerability through Causal Parameter Estimation by Adversarial Double Machine Learning
Adversarial examples derived from deliberately crafted perturbations on visual inputs can easily harm decision process of deep neural networks.
User-friendly Image Editing with Minimal Text Input: Leveraging Captioning and Injection Techniques
From the users' standpoint, prompt engineering is a labor-intensive process, and users prefer to provide a target word for editing instead of a full sentence.
Context-Preserving Two-Stage Video Domain Translation for Portrait Stylization
Portrait stylization, which translates a real human face image into an artistically stylized image, has attracted considerable interest and many prior works have shown impressive quality in recent years.
Custom-Edit: Text-Guided Image Editing with Customized Diffusion Models
Text-to-image diffusion models can generate diverse, high-fidelity images based on user-provided text prompts.
Panoramic Image-to-Image Translation
This task is difficult due to the geometric distortion of panoramic images and the lack of a panoramic image dataset with diverse conditions, like weather or time.
Dynamic Structure Pruning for Compressing CNNs
In this work, we introduce a novel structure pruning method, termed as dynamic structure pruning, to identify optimal pruning granularities for intra-channel pruning.
Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation
Text-to-3D generation has shown rapid progress in recent days with the advent of score distillation, a methodology of using pretrained text-to-2D diffusion models to optimize neural radiance field (NeRF) in the zero-shot setting.
Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regression
The origin of adversarial examples is still inexplicable in research fields, and it arouses arguments from various viewpoints, albeit comprehensive investigations.
Learning Input-agnostic Manipulation Directions in StyleGAN with Text Guidance
With the advantages of fast inference and human-friendly flexible manipulation, image-agnostic style manipulation via text guidance enables new applications that were not previously available.
Efficient Pre-training of Masked Language Model via Concept-based Curriculum Masking
Masked language modeling (MLM) has been widely used for pre-training effective bidirectional representations, but incurs substantial training costs.
Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding
Inspired by the impressive performance of recent face image editing methods, several studies have been naturally proposed to extend these methods to the face video editing task.
Privacy-Preserving Visual Localization with Event Cameras
We present a robust, privacy-preserving visual localization algorithm using event cameras.
MoDA: Map style transfer for self-supervised Domain Adaptation of embodied agents
We propose a domain adaptation method, MoDA, which adapts a pretrained embodied agent to a new, noisy environment without ground-truth supervision.
Generator Knows What Discriminator Should Learn in Unconditional GANs
Here we explore the efficacy of dense supervision in unconditional generation and find generator feature maps can be an alternative of cost-expensive semantic label maps.
CPO: Change Robust Panorama to Point Cloud Localization
By utilizing the unique equivariance of spherical projections, we propose very fast color histogram generation for a large number of camera poses without explicitly rendering images for all candidate poses.
Ev-NeRF: Event Based Neural Radiance Field
We present Ev-NeRF, a Neural Radiance Field derived from event data.
Rarity Score : A New Metric to Evaluate the Uncommonness of Synthesized Images
In this work, we propose a new evaluation metric, called `rarity score', to measure the individual rarity of each image synthesized by generative models.
Distilling Robust and Non-Robust Features in Adversarial Examples by Information Bottleneck
Adversarial examples, generated by carefully crafted perturbation, have attracted considerable attention in research fields.
Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse Network
Adversarial examples provoke weak reliability and potential security issues in deep neural networks.
Ev-TTA: Test-Time Adaptation for Event-Based Object Recognition
We introduce Ev-TTA, a simple, effective test-time adaptation algorithm for event-based object recognition.
Ranked #1 on
Robust classification
on N-ImageNet
Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks
In this paper, we found that the recent emerging paradigm of implicit neural representations (INRs) that encodes a continuous signal into a parameterized neural network effectively mitigates the issue.
Ranked #33 on
Video Generation
on UCF-101
Feature Statistics Mixing Regularization for Generative Adversarial Networks
In generative adversarial networks, improving discriminators is one of the key components for generation performance.
N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras
We introduce N-ImageNet, a large-scale dataset targeted for robust, fine-grained object recognition with event cameras.
Ranked #1 on
Classification
on N-ImageNet (mini)
SGoLAM: Simultaneous Goal Localization and Mapping for Multi-Object Goal Navigation
We present SGoLAM, short for simultaneous goal localization and mapping, which is a simple and efficient algorithm for Multi-Object Goal navigation.
Self-Supervised Domain Adaptation for Visual Navigation with Global Map Consistency
We propose a light-weight, self-supervised adaptation for a visual navigation agent to generalize to unseen environment.
CTRL-C: Camera calibration TRansformer with Line-Classification
In this work, we propose Camera calibration TRansformer with Line-Classification (CTRL-C), an end-to-end neural network-based approach to single image camera calibration, which directly estimates the camera parameters from an image and a set of line segments.
PICCOLO: Point Cloud-Centric Omnidirectional Localization
Our loss function, called sampling loss, is point cloud-centric, evaluated at the projected location of every point in the point cloud.
Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing
Although manipulating the latent vectors controls the synthesized outputs, editing real images with GANs suffers from i) time-consuming optimization for projecting real images to the latent vectors, ii) or inaccurate embedding through an encoder.
A StyleMap-Based Generator for Real-Time Image Projection and Local Editing
State-of-the-art GAN-based methods for editing real images suffer from time-consuming operations in projecting real images to latent vectors.
Neural Geometric Parser for Single Image Camera Calibration
With the supervision of datasets consisting of the horizontal line and focal length of the images, our networks can be trained to estimate the same camera parameters.
U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation
We propose a novel method for unsupervised image-to-image translation, which incorporates a new attention module and a new learnable normalization function in an end-to-end manner.
Ranked #1 on
Image-to-Image Translation
on photo2vangogh
