Papers › Harnessing Vision Foundation Models for High-Performance, Training-Free Open...

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

14 Nov 2024arXiv:2411.09219archive 2025-07-28

Yuheng Shi, Minjing Dong, Chang Xu

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

YuHengsss/Trident officialmentioned in papermentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

SegmentationSemantic SegmentationUnsupervised Semantic Segmentation with Language-image Pre-training

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Semantic Segmentation with Language-image Pre-training ADE20K Trident Mean IoU (val) 26.7 #3 of 13 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training COCO-Object Trident mIoU 42.2 #2 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training COCO-Stuff-171 Trident mIoU 28.6 #3 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training Cityscapes val Trident mIoU 47.6 #2 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training PASCAL Context-59 Trident mIoU 44.3 #3 of 12 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training PASCAL Context-60 Trident mIoU 40.1 #3 of 4 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training PASCAL VOC Trident mIoU 70.8 #3 of 10 Archive leaderboard report
Unsupervised Semantic Segmentation with Language-image Pre-training PascalVOC-20 Trident mIoU 88.7 #3 of 10 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AttentionCLIPDINODense ConnectionsLayer NormalizationLinear LayerMulti-Head AttentionResidual ConnectionSAMSoftmaxVision Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections