Pith. sign in

REVIEW 2 cited by

Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2406.00670 v2 pith:VWDYEMZZ submitted 2024-06-02 cs.CV

classification cs.CV
keywords cascade-clipfeatureszero-shotembeddingssegmentationvisualalignsemantic
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Pre-trained vision-language models, e.g., CLIP, have been successfully applied to zero-shot semantic segmentation. Existing CLIP-based approaches primarily utilize visual features from the last layer to align with text embeddings, while they neglect the crucial information in intermediate layers that contain rich object details. However, we find that directly aggregating the multi-level visual features weakens the zero-shot ability for novel classes. The large differences between the visual features from different layers make these features hard to align well with the text embeddings. We resolve this problem by introducing a series of independent decoders to align the multi-level visual features with the text embeddings in a cascaded way, forming a novel but simple framework named Cascade-CLIP. Our Cascade-CLIP is flexible and can be easily applied to existing zero-shot semantic segmentation methods. Experimental results show that our simple Cascade-CLIP achieves superior zero-shot performance on segmentation benchmarks, like COCO-Stuff, Pascal-VOC, and Pascal-Context. Our code is available at: https://github.com/HVision-NKU/Cascade-CLIP

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. CROSS: Cascaded Distillation and Dual-Constraint Grounding for Remote Sensing Referring Segmentation

    cs.CV 2026-08 conditional novelty 6.0 of 10

    CROSS improves remote sensing referring segmentation by combining cascaded SAM distillation with contrastive learning, reporting state-of-the-art cIoU on RefSegRS and RRSIS-D.

  2. FIX-CLIP: Dual-Branch Hierarchical Contrastive Learning via Synthetic Captions for Better Understanding of Long Text

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A dual-branch CLIP training pipeline with regional prompts and hierarchical feature alignment reaches state-of-the-art on long- and short-text retrieval.

Pith tools