Research map / Detection and segmentation / CNN features
k-Means Mask Transformer
Qihang Yu, Huiyu Wang, Siyuan Qiao, Maxwell Collins, Yukun Zhu, Hartwig Adam, Alan Yuille, Liang-Chieh Chen
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace spatial-wise softmax cross-attention with k-means cluster-wise argmax cross-attention (ablation) | kMaX-DeepLab (ResNet-50) · COCO val | PQ: 5.2% PQ | Improved |
| double object queries to 256 with drop query regularization (ablation) | kMaX-DeepLab (ConvNeXt-L) · COCO val | PQ: 57.9 -> 58.0 | Improved |
| double object queries to 256 without drop query regularization (ablation) | kMaX-DeepLab (ConvNeXt-L) · COCO val | PQ | Hurt |
| add pseudo labels on COCO unlabeled set to training data | kMaX-DeepLab (ConvNeXt-L) · COCO val | PQ: 57.9 -> 58.1 | Improved |
| use Gumbel-Softmax instead of deep supervision to train through the non-differentiable argmax (ablation) | kMaX-DeepLab · COCO val | PQ | Hurt |
| scale backbone from ConvNeXt-B to ConvNeXt-L | kMaX-DeepLab · COCO val | PQ: +0.7% for kMaX-DeepLab but +1.4% for Mask2Former | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 on most shared results.
- CMT-DeepLab — CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation (CVPR 2022) · better on 4 of 4 shared results
- Panoptic SegFormer — Panoptic SegFormer: Delving Deeper Into Panoptic Segmentation With Transformers (CVPR 2022) · better on 3 of 3 shared results
- K-Net — K-Net: Towards Unified Image Segmentation (NeurIPS 2021) · better on 2 of 2 shared results
- Panoptic-DeepLab — Panoptic-DeepLab: A Simple, Strong, and Fast Baseline for Bottom-Up Panoptic Segmentation (CVPR 2020) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- FeedFormer: Revisiting Transformer Decoder for Efficient Semantic Segmentation (AAAI 2023 · similarity 0.87)
- Training Object Detectors From Scratch: An Empirical Study in the Era of Vision Transformer (CVPR 2022 · similarity 0.87)
- Rethinking Decoders for Transformer-based Semantic Segmentation: A Compression Perspective (NeurIPS 2024 · similarity 0.87)
- KVT: k-NN Attention for Boosting Vision Transformers (ECCV 2022 · similarity 0.87)
- ClusterFomer: Clustering As A Universal Visual Learner (NeurIPS 2023 · similarity 0.87)
- Masked-Attention Mask Transformer for Universal Image Segmentation (CVPR 2022 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
