Research map / Label-efficient and robust learning / Recognition and long-tail
Deep Adaptive Image Clustering
Jianlong Chang, Lingfeng Wang, Gaofeng Meng, Shiming Xiang, Chunhong Pan
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 Adaptive Learning sample selection (versus training on all samples, DAC*) (ablation) | DAC · MNIST | ACC: 0.9660 -> 0.9775 | Improved |
| add Adaptive Learning sample selection (versus training on all samples, DAC*) (ablation) | DAC · CIFAR-10 | ACC: 0.4982 -> 0.5218 | Improved |
| add Adaptive Learning sample selection (versus training on all samples, DAC*) (ablation) | DAC · CIFAR-100 | ACC: 0.2189 -> 0.2375 | Improved |
| add Adaptive Learning sample selection (versus training on all samples, DAC*) (ablation) | DAC · STL-10 | ACC: 0.4337 -> 0.4699 | Improved |
| add Adaptive Learning sample selection (versus training on all samples, DAC*) (ablation) | DAC · ImageNet-10 | ACC: 0.5026 -> 0.5272 | Improved |
| add Adaptive Learning sample selection (versus training on all samples, DAC*) (ablation) | DAC · ImageNet-Dog | ACC: 0.2455 -> 0.2748 | Improved |
| cluster by argmax of label features instead of K-means on the learned features (ablation) | DAC · MNIST | ACC: 0.9761 -> 0.9775 | Improved |
| cluster by argmax of label features instead of K-means on the learned features (ablation) | DAC · CIFAR-10 | ACC: 0.5106 -> 0.5218 | Improved |
| cluster by argmax of label features instead of K-means on the learned features (ablation) | DAC · ImageNet-Dog | ACC: 0.2709 -> 0.2748 | Improved |
| single-stage DAC versus multi-stage DEC | DAC · CIFAR-10 | ACC: 0.3010 -> 0.5218 | Improved |
| single-stage DAC versus JULE | DAC · CIFAR-10 | ACC: 0.2715 -> 0.5218 | Improved |
| use learned representation (AE) before K-means instead of raw pixel K-means | K-means · MNIST | ACC: 0.5723 -> 0.8123 | Improved |
Closest papers by meaning
- Deep Clustering via Joint Convolutional Autoencoder Embedding and Relative Entropy Minimization (ICCV 2017 · similarity 0.88)
- Deep Clustering for Unsupervised Learning of Visual Features (ECCV 2018 · similarity 0.88)
- Samples Are Not Equal: A Sample Selection Approach for Deep Clustering (ICLR 2026 · similarity 0.88)
- Language-Assisted Image Clustering Guided by Discriminative Relational Signals and Adaptive Semantic Centers (NeurIPS 2026 · similarity 0.87)
- Image Clustering via the Principle of Rate Reduction in the Age of Pretrained Models (ICLR 2024 · similarity 0.86)
- Dynamic Clustering Convolutional Neural Network (AAAI 2025 · 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.
