Picture for Wayne Zhang

Wayne Zhang

Revisiting the Integration of Convolution and Attention for Vision Backbone

Add code
Nov 21, 2024
Viaarxiv icon

GeoGround: A Unified Large Vision-Language Model. for Remote Sensing Visual Grounding

Add code
Nov 16, 2024
Figure 1 for GeoGround: A Unified Large Vision-Language Model. for Remote Sensing Visual Grounding
Figure 2 for GeoGround: A Unified Large Vision-Language Model. for Remote Sensing Visual Grounding
Figure 3 for GeoGround: A Unified Large Vision-Language Model. for Remote Sensing Visual Grounding
Figure 4 for GeoGround: A Unified Large Vision-Language Model. for Remote Sensing Visual Grounding
Viaarxiv icon

Text4Seg: Reimagining Image Segmentation as Text Generation

Add code
Oct 13, 2024
Viaarxiv icon

ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation

Add code
Aug 09, 2024
Viaarxiv icon

ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference

Add code
Jul 17, 2024
Figure 1 for ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference
Figure 2 for ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference
Figure 3 for ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference
Figure 4 for ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference
Viaarxiv icon

Towards Vision-Language Geo-Foundation Model: A Survey

Add code
Jun 13, 2024
Figure 1 for Towards Vision-Language Geo-Foundation Model: A Survey
Figure 2 for Towards Vision-Language Geo-Foundation Model: A Survey
Figure 3 for Towards Vision-Language Geo-Foundation Model: A Survey
Figure 4 for Towards Vision-Language Geo-Foundation Model: A Survey
Viaarxiv icon

RelayAttention for Efficient Large Language Model Serving with Long System Prompts

Add code
Feb 29, 2024
Figure 1 for RelayAttention for Efficient Large Language Model Serving with Long System Prompts
Figure 2 for RelayAttention for Efficient Large Language Model Serving with Long System Prompts
Figure 3 for RelayAttention for Efficient Large Language Model Serving with Long System Prompts
Figure 4 for RelayAttention for Efficient Large Language Model Serving with Long System Prompts
Viaarxiv icon

Panoptic Video Scene Graph Generation

Add code
Nov 28, 2023
Viaarxiv icon

SmooSeg: Smoothness Prior for Unsupervised Semantic Segmentation

Add code
Oct 27, 2023
Figure 1 for SmooSeg: Smoothness Prior for Unsupervised Semantic Segmentation
Figure 2 for SmooSeg: Smoothness Prior for Unsupervised Semantic Segmentation
Figure 3 for SmooSeg: Smoothness Prior for Unsupervised Semantic Segmentation
Figure 4 for SmooSeg: Smoothness Prior for Unsupervised Semantic Segmentation
Viaarxiv icon

Diverse Cotraining Makes Strong Semi-Supervised Segmentor

Add code
Aug 18, 2023
Figure 1 for Diverse Cotraining Makes Strong Semi-Supervised Segmentor
Figure 2 for Diverse Cotraining Makes Strong Semi-Supervised Segmentor
Figure 3 for Diverse Cotraining Makes Strong Semi-Supervised Segmentor
Figure 4 for Diverse Cotraining Makes Strong Semi-Supervised Segmentor
Viaarxiv icon