144 citations · 865 across the 49 of their papers we have counts for
28 papers · 1 filter
Topology-Aware Layer Pruning for Large Vision-Language Models
Pengcheng Zheng, Chaoning Zhang, Ya Wen +10
Large Language Models (LLMs) have demonstrated strong capabilities in natural language understanding and reasoning, while recent extensions that incorporate visual inputs enable th…
Exploring Kernel Transformations for Implicit Neural Representations
Sheng Zheng, Chaoning Zhang, Dongshen Han +4
Implicit neural representations (INRs), which leverage neural networks to represent signals by mapping coordinates to their corresponding attributes, have garnered significant atte…
FedCCL: Federated Dual-Clustered Feature Contrast Under Domain Heterogeneity
Yu Qiao, Huy Q. Le, Mengchun Zhang +3
Federated learning (FL) facilitates a privacy-preserving neural network training paradigm through collaboration between edge clients and a central server. One significant challenge…
Towards Robust Federated Learning via Logits Calibration on Non-IID Data
Yu Qiao, Apurba Adhikary, Chaoning Zhang +1
Federated learning (FL) is a privacy-preserving distributed management framework based on collaborative model training of distributed devices in edge networks. However, recent stud…
Interpreting and Improving Attention From the Perspective of Large Kernel Convolution
Chenghao Li, Chaoning Zhang, Boheng Zeng +7
Attention mechanisms have significantly advanced visual models by capturing global context effectively. However, their reliance on large-scale datasets and substantial computationa…
MobileSAMv2: Faster Segment Anything to Everything
Chaoning Zhang, Dongshen Han, Sheng Zheng +3
Segment anything model (SAM) addresses two practical yet challenging segmentation tasks: \textbf{segment anything (SegAny)}, which utilizes a certain point to predict the mask for…
Single Image Reflection Removal with Patch Reflectance Prior
Dongshen Han, Heechan Yoon, Hyukmin Kwon +4
Single Image Reflection Removal (SIRR) in real-world images is a challenging task due to diverse image degradations occurring on the glass surface during light transmission and ref…
Understanding Segment Anything Model: SAM is Biased Towards Texture Rather than Shape
Chaoning Zhang, Yu Qiao, Shehbaz Tariq +5
In contrast to the human vision that mainly depends on the shape for recognizing the objects, deep image recognition models are widely known to be biased toward texture. Recently,…
Toward a Deeper Understanding: RetNet Viewed through Convolution
Chenghao Li, Chaoning Zhang
The success of Vision Transformer (ViT) has been widely reported on a wide range of image recognition tasks. ViT can learn global dependencies superior to CNN, yet CNN's inherent l…
SAM Meets UAP: Attacking Segment Anything Model With Universal Adversarial Perturbation
Dongshen Han, Chaoning Zhang, Sheng Zheng +3
As Segment Anything Model (SAM) becomes a popular foundation model in computer vision, its adversarial robustness has become a concern that cannot be ignored. This works investigat…
Black-box Targeted Adversarial Attack on Segment Anything (SAM)
Sheng Zheng, Chaoning Zhang, Xinhong Hao
Deep recognition models are widely vulnerable to adversarial examples, which change the model output by adding quasi-imperceptible perturbation to the image input. Recently, Segmen…
DimCL: Dimensional Contrastive Learning For Improving Self-Supervised Learning
Thanh Nguyen, Trung Pham, Chaoning Zhang +3
Self-supervised learning (SSL) has gained remarkable success, for which contrastive learning (CL) plays a key role. However, the recent development of new non-CL frameworks has ach…
Internal-External Boundary Attention Fusion for Glass Surface Segmentation
Dongshen Han, Seungkyu Lee, Chaoning Zhang +4
Glass surfaces of transparent objects and mirrors are not able to be uniquely and explicitly characterized by their visual appearances because they contain the visual appearance of…
Faster Segment Anything: Towards Lightweight SAM for Mobile Applications
Chaoning Zhang, Dongshen Han, Yu Qiao +4
Segment Anything Model (SAM) has attracted significant attention due to its impressive zero-shot transfer performance and high versatility for numerous vision applications (like im…
Robustness of Segment Anything Model (SAM) for Autonomous Driving in Adverse Weather Conditions
Xinru Shan, Chaoning Zhang
Segment Anything Model (SAM) has gained considerable interest in recent times for its remarkable performance and has emerged as a foundational model in computer vision. It has been…
Segment Anything Meets Semantic Communication
Shehbaz Tariq, Brian Estadimas Arfeto, Chaoning Zhang +1
In light of the diminishing returns of traditional methods for enhancing transmission rates, the domain of semantic communication presents promising new frontiers. Focusing on imag…
Robustness of SAM: Segment Anything Under Corruptions and Beyond
Yu Qiao, Chaoning Zhang, Taegoo Kang +3
Segment anything model (SAM), as the name suggests, is claimed to be capable of cutting out any object and demonstrates impressive zero-shot transfer performance with the guidance…
A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineering
Chaoning Zhang, Joseph Cho, Fachrina Dewi Puspitasari +11
The Segment Anything Model (SAM), developed by Meta AI Research, represents a significant breakthrough in computer vision, offering a robust framework for image and video segmentat…
When ChatGPT for Computer Vision Will Come? From 2D to 3D
Chenghao Li, Chaoning Zhang
ChatGPT and its improved variant GPT4 have revolutionized the NLP field with a single model solving almost all text related tasks. However, such a model for computer vision does no…
Attack-SAM: Towards Attacking Segment Anything Model With Adversarial Examples
Chenshuang Zhang, Chaoning Zhang, Taegoo Kang +3
Segment Anything Model (SAM) has attracted significant attention recently, due to its impressive performance on various downstream tasks in a zero-short manner. Computer vision (CV…
Generative AI meets 3D: A Survey on Text-to-3D in AIGC Era
Chenghao Li, Chaoning Zhang, Joseph Cho +6
Generative AI has made significant progress in recent years, with text-guided content generation being the most practical as it facilitates interaction between human instructions a…
Segment Anything Model (SAM) Meets Glass: Mirror and Transparent Objects Cannot Be Easily Detected
Dongsheng Han, Chaoning Zhang, Yu Qiao +5
Meta AI Research has recently released SAM (Segment Anything Model) which is trained on a large segmentation dataset of over 1 billion masks. As a foundation model in the field of…
Text-to-image Diffusion Models in Generative AI: A Survey
Chenshuang Zhang, Chaoning Zhang, Mengchun Zhang +2
This survey reviews the progress of diffusion models in generating images from text, ~\textit{i.e.} text-to-image diffusion models. As a self-contained work, this survey starts wit…
Test-time Adaptation in the Dynamic World with Compound Domain Knowledge Management
Junha Song, Kwanyong Park, InKyu Shin +3
Prior to the deployment of robotic systems, pre-training the deep-recognition models on all potential visual cases is infeasible in practice. Hence, test-time adaptation (TTA) allo…