arXiv Computer Vision
SCMerge: Spatial-Consistency-Aware Token Pair Merging for Efficient Semantic Segmentation
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
Hugging Face Trending Papers
3d ago
SCMerge: Spatial-Consistency-Aware Token Pair Merging for Efficient Semantic Segmentation
Vision Transformer architectures have showcased impressive performance on semantic segmentation, yet their quadratic attention complexity hinders practical applications. Recent works have focused on m...
arXiv Computer Vision
Sep 17
Decoder-Agnostic Token Merging for Vision Transformers: A Systematic Study of G2TM
The paper studies Graph-Guided Token Merging (G2TM), a module that reduces token count in Vision Transformers. It evaluates G2TM across multiple segmentation frameworks and decoder types, finding that its performance gains are tied to the encoder rather than the decoder. The authors report consistent reductions in GFLOPs (22‑47%) and throughput improvements (up to 74%) on ADE20K, with optimal hyperparameters depending mainly on backbone pre‑training and target dataset.
arXiv AI
3d ago
Scaling Vision Transformers Without Training: Prune-and-Merge Token Compression
The paper introduces Prune-and-Merge ViT, a training‑free token compression framework for Vision Transformers that combines class‑attention pruning with similarity‑based merging to reduce computational cost while preserving semantic information. It evaluates robustness using two new metrics—Relative Accuracy Drop (RAD) and Prediction Flip Rate (PFR)—and shows that the method maintains or improves accuracy on pretrained ViT and DeiT models compared to existing token reduction techniques. The authors also argue that the hybrid approach does not induce hallucination‑like behavior and keeps predictions stable under common image transformations.
arXiv AI
Jun 9
RAPID: Layer-Wise Redundancy-Aware Pruning and Importance-Driven Token Merging for Efficient ViT
arXiv:2606. 08156v1 Announce Type: cross Abstract: Vision Transformers (ViTs) achieve strong performance but suffer from high computational costs due to quadratic self-attention complexity.
arXiv Computer Vision
2d ago
SpaceCache: Intermediate Feature Reuse for Efficient Semantic Segmentation on Point Cloud Streams
arXiv:2610.21207v1 Announce Type: new Abstract: Point-cloud streams are central to autonomous driving and robotics, yet existing segmentation networks process every frame from scratch, although conse...
arXiv Computer Vision
Sep 15
Token-Space Mask Prediction for Efficient Vision Transformer Segmentation
arXiv:2605.18177v2 Announce Type: replace Abstract: Query-based Vision Transformer segmentation models typically reconstruct dense spatial feature maps to predict masks, inheriting design patterns fr...