Loading the SOTA2 catalog…
SOTA2 Research · papers
Find papers, implementations, and the benchmark evidence behind state-of-the-art AI systems.
| CanViT: Toward Active-Vision Foundation Models |
|---|
| Yohaï-Eliel Berreby, Sabrina Du, Audrey Durand |
| 2026 |
| arxiv 2603.22570 |
| PixCon: Clean-Positive Contrastive Learning for Foundation-Model Semi-Supervised Segmentation | Ebenezer Tarubinga | 2026 | arxiv 2607.03068 |
|---|
| Sparse Spatial Attention Network for Semantic Segmentation | Mengyu Liu, Hujun Yin | 2021 | arxiv 2109.01915 |
|---|
| Attention to Refine through Multi-Scales for Semantic Segmentation | Shiqi Yang, Gang Peng | 2018 | arxiv 1807.02917 |
|---|
| Transformer Scale Gate for Semantic Segmentation | Hengcan Shi, Munawar Hayat, Jianfei Cai | 2022 | arxiv 2205.07056 |
|---|
| Cluster and Predict Latent Patches for Improved Masked Image Modeling | Timothée Darcet, Federico Baldassarre, Maxime Oquab | 2025 | arxiv 2502.08769 |
|---|
| Activation-Free Backbones for Image Recognition: Polynomial Alternatives within MetaFormer-Style Vision Models | Jeffrey Wang, Jonathan Gregory, Grigorios G. Chrysos | 2026 | arxiv 2605.20839 |
|---|
| A Simple Framework for Open-Vocabulary Segmentation and Detection | Hao Zhang, Feng Li, Xueyan Zou | 2023 | arxiv 2303.08131 |
|---|
| Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios | Jiashi Li, Xin Xia, Wei Li | 2022 | arxiv 2207.05501 |
|---|
| Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP | Qihang Yu, Ju He, Xueqing Deng | 2023 | arxiv 2308.02487 |
|---|