Research map / Vision-language and multimodal / CLIP and zero-shot
UniCLIP: Unified Framework for Contrastive Language-Image Pre-training
Janghyeon Lee, Jongsuk Kim, Hyounguk Shon, Bumsoo Kim, Seung Hwan Kim, Honglak Lee, Junmo Kim
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 |
|---|---|---|---|
| add augmentation embedding to the image projection head (ablation) | UniCLIP (3 ResBlocks) · ImageNet-1k zero-shot, CC3M 50 ep, ViT-B/16 | accuracy: 24.46 -> 27.84 | Improved |
| use residual blocks instead of MLP head with augmentation embedding (ablation) | UniCLIP · ImageNet-1k zero-shot, CC3M 50 ep, ViT-B/16 | accuracy: 24.15 -> 27.84 | Improved |
| use 3 ResBlocks instead of 1 ResBlock (ablation) | UniCLIP · ImageNet-1k zero-shot, CC3M 50 ep, ViT-B/16 | accuracy: 27.67 -> 27.84 | No clear effect |
| replace 3 weak augmentations by 1 weak + 2 strong (with augmentation embedding) (ablation) | UniCLIP · ImageNet-1k zero-shot, CC3M 50 ep, ViT-B/16 | accuracy: 23.40 -> 27.84 | Improved |
| use 3 strong augmentations without augmentation embedding instead of 1 weak 2 strong (ablation) | UniCLIP · ImageNet-1k zero-shot, CC3M 50 ep, ViT-B/16 | accuracy: 24.76 -> 22.60 | Hurt |
| domain-dependent temperature and offset instead of shared (ablation) | UniCLIP · ImageNet-1k zero-shot, CC3M 50 ep, ViT-B/16 | accuracy: 25.51 -> 27.84 | Improved |
| unified supervision instead of separated supervision (ablation) | UniCLIP · ImageNet-1k zero-shot, CC3M 50 ep, ViT-B/16 | accuracy: 26.59 -> 27.84 | Improved |
| MP-NCE instead of SupCon loss (ablation) | UniCLIP · ImageNet-1k zero-shot, CC3M 50 ep, ViT-B/16 | accuracy: 23.04 -> 27.84 | Improved |
| SupCon instead of MIL-NCE (ablation) | UniCLIP · ImageNet-1k zero-shot, CC3M 50 ep, ViT-B/16 | accuracy: 22.23 -> 23.04 | Improved |
| add domain balancing weights w to MP-NCE (ablation) | UniCLIP · ImageNet-1k zero-shot, CC3M 50 ep, ViT-B/16 | accuracy: 26.41 -> 27.84 | Improved |
| add trivial pair (z_i, z_i) to positive set (ablation) | UniCLIP MP-NCE · ImageNet-1k zero-shot, CC3M 50 ep, ViT-B/16 | accuracy: 24.60 -> 26.41 | Improved |
| UniCLIP versus SLIP and DeCLIP on pre-training | ViT-B/32 YFCC15M · 11-dataset linear probing | average accuracy: 71.8 -> 75.2 | Improved |
Later papers that compared with this method
1 later accepted paper reports UniCLIP as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- MLIP: Efficient Multi-Perspective Language-Image Pretraining with Exhaustive Data Utilization (ICML 2024 · better on 2 of 2 shared results)
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
- FFF: Fixing Flawed Foundations in Contrastive Pre-Training Results in Very Strong Vision-Language Models (CVPR 2024 · similarity 0.90)
- AmorLIP: Efficient Language-Image Pretraining via Amortization (NeurIPS 2025 · similarity 0.89)
- Post-pre-training for Modality Alignment in Vision-Language Foundation Models (CVPR 2025 · similarity 0.89)
- MLIP: Efficient Multi-Perspective Language-Image Pretraining with Exhaustive Data Utilization (ICML 2024 · similarity 0.88)
- Rethinking Contrastive Loss in CLIP Post-training: A Complementary Framework with Frozen Text Encoder (NeurIPS 2026 · similarity 0.88)
- Building Vision-Language Models on Solid Foundations with Masked Distillation (CVPR 2024 · similarity 0.88)
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.
