Picture for Zelin Peng

Zelin Peng

OphCLIP: Hierarchical Retrieval-Augmented Learning for Ophthalmic Surgical Video-Language Pretraining

Add code
Nov 23, 2024
Viaarxiv icon

Parameter-efficient Fine-tuning in Hyperspherical Space for Open-vocabulary Semantic Segmentation

Add code
May 29, 2024
Viaarxiv icon

S$^2$Mamba: A Spatial-spectral State Space Model for Hyperspectral Image Classification

Add code
Apr 28, 2024
Viaarxiv icon

Parameter Efficient Fine-tuning via Cross Block Orchestration for Segment Anything Model

Add code
Nov 28, 2023
Viaarxiv icon

SAM-PARSER: Fine-tuning SAM Efficiently by Parameter Space Reconstruction

Add code
Aug 31, 2023
Viaarxiv icon

USAGE: A Unified Seed Area Generation Paradigm for Weakly Supervised Semantic Segmentation

Add code
Mar 14, 2023
Viaarxiv icon

A Survey on Label-efficient Deep Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction

Add code
Jul 04, 2022
Figure 1 for A Survey on Label-efficient Deep Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction
Figure 2 for A Survey on Label-efficient Deep Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction
Figure 3 for A Survey on Label-efficient Deep Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction
Figure 4 for A Survey on Label-efficient Deep Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction
Viaarxiv icon

Absolute Wrong Makes Better: Boosting Weakly Supervised Object Detection via Negative Deterministic Information

Add code
Apr 21, 2022
Figure 1 for Absolute Wrong Makes Better: Boosting Weakly Supervised Object Detection via Negative Deterministic Information
Figure 2 for Absolute Wrong Makes Better: Boosting Weakly Supervised Object Detection via Negative Deterministic Information
Figure 3 for Absolute Wrong Makes Better: Boosting Weakly Supervised Object Detection via Negative Deterministic Information
Figure 4 for Absolute Wrong Makes Better: Boosting Weakly Supervised Object Detection via Negative Deterministic Information
Viaarxiv icon

Adaptive Affinity Loss and Erroneous Pseudo-Label Refinement for Weakly Supervised Semantic Segmentation

Add code
Aug 03, 2021
Figure 1 for Adaptive Affinity Loss and Erroneous Pseudo-Label Refinement for Weakly Supervised Semantic Segmentation
Figure 2 for Adaptive Affinity Loss and Erroneous Pseudo-Label Refinement for Weakly Supervised Semantic Segmentation
Figure 3 for Adaptive Affinity Loss and Erroneous Pseudo-Label Refinement for Weakly Supervised Semantic Segmentation
Figure 4 for Adaptive Affinity Loss and Erroneous Pseudo-Label Refinement for Weakly Supervised Semantic Segmentation
Viaarxiv icon