Imagen de Portada

Sa2VA-i: Improving Sa2VA Results with Consistent Training and Inference

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Nekrasov, Alexey, Athar, Ali, de Geus, Daan, Hermans, Alexander, Leibe, Bastian
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

How Important are Videos for Training Video LLMs?
por: Lydakis, George, et al.
Publicado: (2025)

DONUT: A Decoder-Only Model for Trajectory Prediction
por: Knoche, Markus, et al.
Publicado: (2025)

SaSaSaSa2VA: 2nd Place of the 5th PVUW MeViS-Text Track
por: Gong, Dengxian, et al.
Publicado: (2026)

DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation
por: Knaebel, Karim, et al.
Publicado: (2025)

2nd of the 5th PVUW MeViS-Audio Track: ASR-SaSaSa2VA
por: Wang, Zhiyu, et al.
Publicado: (2026)

Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think
por: Garcia, Gonzalo Martin, et al.
Publicado: (2024)

OoDIS: Anomaly Instance Segmentation and Detection Benchmark
por: Nekrasov, Alexey, et al.
Publicado: (2024)

The 1st Solution for 7th LSVOS RVOS Track: SaSaSa2VA
por: Niu, Quanzhu, et al.
Publicado: (2025)

Mask4Former: Mask Transformer for 4D Panoptic Segmentation
por: Yilmaz, Kadir, et al.
Publicado: (2023)

Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
por: Yuan, Haobo, et al.
Publicado: (2025)

Your ViT is Secretly an Image Segmentation Model
por: Kerssies, Tommie, et al.
Publicado: (2025)

Volume Transformer: Revisiting Vanilla Transformers for 3D Scene Understanding
por: Yilmaz, Kadir, et al.
Publicado: (2026)

Point2Vec for Self-Supervised Representation Learning on Point Clouds
por: Knaebel, Karim, et al.
Publicado: (2023)

MaskTerial: A Foundation Model for Automated 2D Material Flake Detection
por: Uslu, Jan-Lucas, et al.
Publicado: (2024)

SurGe: Improved Surface Geometry in Point Maps
por: Knaebel, Karim, et al.
Publicado: (2026)

OCCUQ: Exploring Efficient Uncertainty Quantification for 3D Occupancy Prediction
por: Heidrich, Severin, et al.
Publicado: (2025)

4th PVUW MeViS 3rd Place Report: Sa2VA
por: Yuan, Haobo, et al.
Publicado: (2025)

Spotting the Unexpected (STU): A 3D LiDAR Dataset for Anomaly Segmentation in Autonomous Driving
por: Nekrasov, Alexey, et al.
Publicado: (2025)

Enhancing Sa2VA for Referent Video Object Segmentation: 2nd Solution for 7th LSVOS RVOS Track
por: Hong, Ran, et al.
Publicado: (2025)

VidEoMT: Your ViT is Secretly Also a Video Segmentation Model
por: Norouzi, Narges, et al.
Publicado: (2026)

Query2Uncertainty: Robust Uncertainty Quantification and Calibration for 3D Object Detection under Distribution Shift
por: Beemelmanns, Till, et al.
Publicado: (2026)

Task-aligned Part-aware Panoptic Segmentation through Joint Object-Part Representations
por: de Geus, Daan, et al.
Publicado: (2024)

OpenSplat3D: Open-Vocabulary 3D Instance Segmentation using Gaussian Splatting
por: Piekenbrinck, Jens, et al.
Publicado: (2025)

Panoptic-CUDAL: Rural Australia Point Cloud Dataset in Rainy Conditions
por: Tseng, Tzu-Yun, et al.
Publicado: (2025)

MoSa: Motion Generation with Scalable Autoregressive Modeling
por: Liu, Mengyuan, et al.
Publicado: (2025)

An Ordinal Regression Framework for a Deep Learning Based Severity Assessment for Chest Radiographs
por: Wienholt, Patrick, et al.
Publicado: (2024)

Look Gauss, No Pose: Novel View Synthesis using Gaussian Splatting without Accurate Pose Initialization
por: Schmidt, Christian, et al.
Publicado: (2024)

ALGM: Adaptive Local-then-Global Token Merging for Efficient Semantic Segmentation with Plain Vision Transformers
por: Norouzi, Narges, et al.
Publicado: (2024)

PMT: Plain Mask Transformer for Image and Video Segmentation with Frozen Vision Encoders
por: Cavagnero, Niccolò, et al.
Publicado: (2026)

SaENeRF: Suppressing Artifacts in Event-based Neural Radiance Fields
por: Wang, Yuanjian, et al.
Publicado: (2025)

DiSa: Directional Saliency-Aware Prompt Learning for Generalizable Vision-Language Models
por: Talemi, Niloufar Alipour, et al.
Publicado: (2025)

SaMam: Style-aware State Space Model for Arbitrary Image Style Transfer
por: Liu, Hongda, et al.
Publicado: (2025)

SaLF: Sparse Local Fields for Multi-Sensor Rendering in Real-Time
por: Chen, Yun, et al.
Publicado: (2025)

DiSa: Saliency-Aware Foreground-Background Disentangled Framework for Open-Vocabulary Semantic Segmentation
por: Yao, Zhen, et al.
Publicado: (2026)

MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos
por: Li, Zhengqi, et al.
Publicado: (2024)

Point-VOS: Pointing Up Video Object Segmentation
por: Zulfikar, Idil Esen, et al.
Publicado: (2024)

How to Benchmark Vision Foundation Models for Semantic Segmentation?
por: Kerssies, Tommie, et al.
Publicado: (2024)

First Place Solution to the ECCV 2024 BRAVO Challenge: Evaluating Robustness of Vision Foundation Models for Semantic Segmentation
por: Kerssies, Tommie, et al.
Publicado: (2024)

SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation
por: Hu, Teng, et al.
Publicado: (2024)

SaSR-Net: Source-Aware Semantic Representation Network for Enhancing Audio-Visual Question Answering
por: Yang, Tianyu, et al.
Publicado: (2024)