323 citations · 2.1k across the 141 of their papers we have counts for
32 papers · 1 filter
Mutual-modality Adversarial Attack with Semantic Perturbation
Jingwen Ye, Ruonan Yu, Songhua Liu +1
Adversarial attacks constitute a notable threat to machine learning systems, given their potential to induce erroneous predictions and classifications. However, within real-world c…
DeepCache: Accelerating Diffusion Models for Free
Xinyin Ma, Gongfan Fang, Xinchao Wang
Diffusion models have recently gained unprecedented attention in the field of image synthesis due to their remarkable generative capabilities. Notwithstanding their prowess, these…
Generator Born from Classifier
Runpeng Yu, Xinchao Wang
In this paper, we make a bold attempt toward an ambitious task: given a pre-trained classifier, we aim to reconstruct an image generator, without relying on any data samples. From…
DreamDrone: Text-to-Image Diffusion Models are Zero-shot Perpetual View Generators
Hanyang Kong, Dongze Lian, Michael Bi Mi +1
We introduce DreamDrone, a novel zero-shot and training-free pipeline for generating unbounded flythrough scenes from textual prompts. Different from other methods that focus on wa…
SlimSAM: 0.1% Data Makes Segment Anything Slim
Zigeng Chen, Gongfan Fang, Xinyin Ma +1
Current approaches for compressing the Segment Anything Model (SAM) yield commendable results, yet necessitate extensive data to train a new network from scratch. Employing convent…
Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Models
Zhihe Lu, Jiawang Bai, Xin Li +2
Fine-tuning pre-trained vision-language models (VLMs), e.g., CLIP, for the open-world generalization has gained increasing popularity due to its practical value. However, performan…
GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph
Xin Li, Dongze Lian, Zhihe Lu +3
Adapter-style efficient transfer learning (ETL) has shown excellent performance in the tuning of vision-language models (VLMs) under the low-data regime, where only a few additiona…
Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction
Chenxin Xu, Robby T. Tan, Yuhong Tan +3
Exploring spatial-temporal dependencies from observed motions is one of the core challenges of human motion prediction. Previous methods mainly focus on dedicated network structure…
Priority-Centric Human Motion Generation in Discrete Latent Space
Hanyang Kong, Kehong Gong, Dongze Lian +2
Text-to-motion generation is a formidable task, aiming to produce human motions that align with the input text while also adhering to human capabilities and physical laws. While th…
SG-Former: Self-guided Transformer with Evolving Token Reallocation
Sucheng Ren, Xingyi Yang, Songhua Liu +1
Vision Transformer has demonstrated impressive success across various vision tasks. However, its heavy computation cost, which grows quadratically with respect to the token sequenc…
Diffusion Model as Representation Learner
Xingyi Yang, Xinchao Wang
Diffusion Probabilistic Models (DPMs) have recently demonstrated impressive results on various generative tasks.Despite its promises, the learned representations of pre-trained DPM…
Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey
Xin Li, Yulin Ren, Xin Jin +5
Image restoration (IR) has been an indispensable and challenging task in the low-level vision field, which strives to improve the subjective quality of images distorted by various…
PARTNER: Level up the Polar Representation for LiDAR 3D Object Detection
Ming Nie, Yujing Xue, Chunwei Wang +7
Recently, polar-based representation has shown promising properties in perceptual tasks. In addition to Cartesian-based approaches, which separate point clouds unevenly, representi…
MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities
Weihao Yu, Zhengyuan Yang, Linjie Li +5
We propose MM-Vet, an evaluation benchmark that examines large multimodal models (LMMs) on complicated multimodal tasks. Recent LMMs have shown various intriguing abilities, such a…
PseudoCal: A Source-Free Approach to Unsupervised Uncertainty Calibration in Domain Adaptation
Dapeng Hu, Jian Liang, Xinchao Wang +1
Unsupervised domain adaptation (UDA) has witnessed remarkable advancements in improving the accuracy of models for unlabeled target domains. However, the calibration of predictive…
Distribution Shift Inversion for Out-of-Distribution Prediction
Runpeng Yu, Songhua Liu, Xingyi Yang +1
Machine learning society has witnessed the emergence of a myriad of Out-of-Distribution (OoD) algorithms, which address the distribution shift between the training and the testing…
Evolving Knowledge Mining for Class Incremental Segmentation
Zhihe Lu, Shuicheng Yan, Xinchao Wang
Class Incremental Semantic Segmentation (CISS) has been a trend recently due to its great significance in real-world applications. Although the existing CISS methods demonstrate re…
Can SAM Boost Video Super-Resolution?
Zhihe Lu, Zeyu Xiao, Jiawang Bai +2
The primary challenge in video super-resolution (VSR) is to handle large motions in the input frames, which makes it difficult to accurately aggregate information from multiple fra…
LLM-Pruner: On the Structural Pruning of Large Language Models
Xinyin Ma, Gongfan Fang, Xinchao Wang
Large language models (LLMs) have shown remarkable capabilities in language understanding and generation. However, such impressive capability typically comes with a substantial mod…
Structural Pruning for Diffusion Models
Gongfan Fang, Xinyin Ma, Xinchao Wang
Generative modeling has recently undergone remarkable advancements, primarily propelled by the transformative implications of Diffusion Probabilistic Models (DPMs). The impressive…
Deep Graph Reprogramming
Yongcheng Jing, Chongbin Yuan, Li Ju +3
In this paper, we explore a novel model reusing task tailored for graph neural networks (GNNs), termed as "deep graph reprogramming". We strive to reprogram a pre-trained GNN, with…
Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer
Hao Tang, Songhua Liu, Tianwei Lin +4
Transformer-based models achieve favorable performance in artistic style transfer recently thanks to its global receptive field and powerful multi-head/layer attention operations.…
Segment Anything in Non-Euclidean Domains: Challenges and Opportunities
Yongcheng Jing, Xinchao Wang, Dacheng Tao
The recent work known as Segment Anything (SA) has made significant strides in pushing the boundaries of semantic segmentation into the era of foundation models. The impact of SA h…
Any-to-Any Style Transfer: Making Picasso and Da Vinci Collaborate
Songhua Liu, Jingwen Ye, Xinchao Wang
Style transfer aims to render the style of a given image for style reference to another given image for content reference, and has been widely adopted in artistic generation and im…