Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shi, Yuheng, Dong, Minjing, Xu, Chang
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916479975292928
author Shi, Yuheng
Dong, Minjing
Xu, Chang
author_facet Shi, Yuheng
Dong, Minjing
Xu, Chang
contents While Contrastive Language-Image Pre-training (CLIP) has advanced open-vocabulary predictions, its performance on semantic segmentation remains suboptimal. This shortfall primarily stems from its spatial-invariant semantic features and constrained resolution. While previous adaptations addressed spatial invariance semantic by modifying the self-attention in CLIP's image encoder, the issue of limited resolution remains unexplored. Different from previous segment-then-splice methods that segment sub-images via a sliding window and splice the results, we introduce a splice-then-segment paradigm that incorporates Segment-Anything Model (SAM) to tackle the resolution issue since SAM excels at extracting fine-grained semantic correlations from high-resolution images. Specifically, we introduce Trident, a training-free framework that first splices features extracted by CLIP and DINO from sub-images, then leverages SAM's encoder to create a correlation matrix for global aggregation, enabling a broadened receptive field for effective segmentation. Besides, we propose a refinement strategy for CLIP's coarse segmentation outputs by transforming them into prompts for SAM, further enhancing the segmentation performance. Trident achieves a significant improvement in the mIoU across eight benchmarks compared with the current SOTA, increasing from 44.4 to 48.6.Code is available at https://github.com/YuHengsss/Trident.
format Preprint
id arxiv_https___arxiv_org_abs_2411_09219
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation
Shi, Yuheng
Dong, Minjing
Xu, Chang
Computer Vision and Pattern Recognition
While Contrastive Language-Image Pre-training (CLIP) has advanced open-vocabulary predictions, its performance on semantic segmentation remains suboptimal. This shortfall primarily stems from its spatial-invariant semantic features and constrained resolution. While previous adaptations addressed spatial invariance semantic by modifying the self-attention in CLIP's image encoder, the issue of limited resolution remains unexplored. Different from previous segment-then-splice methods that segment sub-images via a sliding window and splice the results, we introduce a splice-then-segment paradigm that incorporates Segment-Anything Model (SAM) to tackle the resolution issue since SAM excels at extracting fine-grained semantic correlations from high-resolution images. Specifically, we introduce Trident, a training-free framework that first splices features extracted by CLIP and DINO from sub-images, then leverages SAM's encoder to create a correlation matrix for global aggregation, enabling a broadened receptive field for effective segmentation. Besides, we propose a refinement strategy for CLIP's coarse segmentation outputs by transforming them into prompts for SAM, further enhancing the segmentation performance. Trident achieves a significant improvement in the mIoU across eight benchmarks compared with the current SOTA, increasing from 44.4 to 48.6.Code is available at https://github.com/YuHengsss/Trident.
title Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.09219