Research map / Video / Action recognition
Vi2CLR: Video and Image for Visual Contrastive Learning of Representation
Ali Diba, Vivek Sharma, Reza Safdari, Dariush Lotfi, Saquib Sarfraz, Rainer Stiefelhagen, Luc Van Gool
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 |
|---|---|---|---|
| use FINCH clustering instead of K-means (ablation) | Vi2CLR · ImageNet linear eval, 200 epochs | top-1 accuracy (%): 73.7 -> 74.3 | Improved |
| use FINCH instead of K-means (ablation) | Vi2CLR · ImageNet linear eval, 50 epochs | top-1 accuracy (%): 64.3 -> 65.5 | Improved |
| add video and CenterNCE losses to image-only loss (full Vi2CLR) (ablation) | Vi2CLR · ImageNet linear eval | top-1 accuracy (%): 71.2 -> 74.6 | Improved |
| add image and video losses to CenterNCE only (ablation) | Vi2CLR · ImageNet linear eval | top-1 accuracy (%): 72.7 -> 74.6 | Improved |
| add CenterNCE and image loss to video-only loss (ablation) | Vi2CLR · UCF101 | accuracy (%): 86.6 -> 89.1 | Improved |
| add full objective vs CenterNCE only (ablation) | Vi2CLR · UCF101 | accuracy (%): 87.8 -> 89.1 | Improved |
| add full objective vs video loss only (ablation) | Vi2CLR · HMDB51 | accuracy (%): 51.2 -> 55.7 | Improved |
| add full objective vs CenterNCE only (ablation) | Vi2CLR · VOC07 | accuracy (%): 88 -> 89.4 | Improved |
| use Vi2CLR instead of SwAV | Vi2CLR · ImageNet linear eval | top-1 accuracy (%): 74.2 -> 74.6 | Improved |
| use Vi2CLR with 300 epochs instead of SwAV 800 epochs | Vi2CLR · ImageNet 10% labels | top-1 accuracy (%): 70.2 -> 69.7 | Hurt |
| use Vi2CLR instead of PCL | Vi2CLR · VOC07 few-shot k=16 | accuracy (%): 78.3 -> 80.6 | Improved |
| use Vi2CLR instead of PCL | Vi2CLR · ImageNet 10% labels | top-1 accuracy (%): 75.3 -> 69.7 | Hurt |
Closest papers by meaning
- A Simple Framework for Contrastive Learning of Visual Representations (ICML 2020 · similarity 0.90)
- Cross-Architecture Self-Supervised Video Representation Learning (CVPR 2022 · similarity 0.89)
- Cycle-Contrast for Self-Supervised Video Representation Learning (NeurIPS 2020 · similarity 0.88)
- Revisiting Self-Supervised Visual Representation Learning (CVPR 2019 · similarity 0.88)
- Self-Supervised Video Representation Learning in a Heuristic Decoupled Perspective (IJCV 2026 · similarity 0.88)
- Contrastive Learning of Image Representations With Cross-Video Cycle-Consistency (ICCV 2021 · similarity 0.87)
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.
