AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Unicom: Universal and Compact Representation Learning for Image Retrieval

Xiang An, Jiankang Deng, Kaicheng Yang, Jaiwei Li, Ziyong Feng, Jia Guo, Jing Yang, Tongliang Liu

ICLR 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 17 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use cluster discrimination on LAION 400M instead of instance discrimination pre-trainingCLIP/OPEN-CLIP visual encoders · Unsupervised retrieval (average across 7 datasets)average retrieval score: 64.5 -> 69.9Improved
Use joint image-text features rather than image features alone for clustering (ablation)UNICOM · Linear probe (average, 13 datasets)top-1 accuracy: 84.4 -> 85.7Improved
Use joint image-text features rather than image features alone for clustering (ablation)UNICOM · Unsupervised retrieval (average)retrieval score: 61.8 -> 62.8Improved
Use 1M clusters rather than 100K clusters (ablation)UNICOM · Linear probe (average, 13 datasets)top-1 accuracy: 75.9 -> 85.7Improved
Use 1M clusters rather than 10M clusters (ablation)UNICOM · Linear probe (average, 13 datasets)top-1 accuracy: 83.6 -> 85.7Improved
Sample only a subset of negative classes (r1=0.1) rather than use all classes (ablation)UNICOM · Linear probe (average, 13 datasets)top-1 accuracy: 77.9 -> 85.7Improved
Lower the random class ratio from 0.1 to 0.05 (ablation)UNICOM · Linear probe (average, 13 datasets)top-1 accuracy: 85.7 -> 85.1Hurt
Apply shared random feature selection with r2=0.5 instead of full dimensions (ablation)UNICOM · Unsupervised retrieval at 256 dimensionsretrieval score: 61.4 -> 61.8Improved
Replace shared random feature selection with Dropout (ablation)UNICOM · Unsupervised retrieval at 256 dimensionsretrieval score: 61.8 -> 60.7Hurt
Train from scratch rather than fine-tune from CLIP (ablation)UNICOM ViT B/32 · 13-dataset linear probe (average)top-1 accuracy: 85.0 -> 85.7Improved
Add random feature selection at full 512-dimensional representation (ablation)UNICOM · Linear probe and full-dimension unsupervised retrievalperformanceNo clear effect

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy