{"ID":3050007,"CreatedAt":"2026-06-04T02:13:16.786527022Z","UpdatedAt":"2026-06-06T14:07:05.414468951Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.04920","arxiv_id":"2606.04920","title":"Toward Multi-Domain and Long-Tailed Quantization via Feature Alignment and Scaling","abstract":"Quantizing deep neural networks is essential for efficient inference on resource-constrained devices. However, most existing methods are designed for single-domain and class-balanced data, leaving practical settings with domain shifts or severe class imbalance underexplored. We address these challenges with Efficient Multi-Domain Alignment Quantization (EmaQ), which aligns domain distributions through a CDF-based projection and uses sensitivity-aware weight aggregation to stabilize multi-domain quantization. We further extend EmaQ to EmaQ-LT for long-tailed quantization by introducing class-conditioned variance scaling and confidence-based logit adjustment to mitigate majority-class overconfidence. Theoretical analyses establish convergence guarantees and motivate the proposed sensitivity and scaling mechanisms. Experiments on standard, multi-domain (Office-31, Digits), and long-tailed (SynDigits-LT, CIFAR-10-LT, CIFAR-100-LT) benchmarks show that EmaQ and EmaQ-LT achieve strong low-bit performance under domain shift and class imbalance.","short_abstract":"Quantizing deep neural networks is essential for efficient inference on resource-constrained devices. However, most existing methods are designed for single-domain and class-balanced data, leaving practical settings with domain shifts or severe class imbalance underexplored. We address these challenges with Efficient M...","url_abs":"https://arxiv.org/abs/2606.04920","url_pdf":"https://arxiv.org/pdf/2606.04920v1","authors":"[\"Chin-Yuan Yeh\",\"Ting-An Chen\",\"De-Nian Yang\",\"Ming-Syan Chen\"]","published":"2026-06-03T14:16:58Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.CV\"]","methods":"[]","has_code":false}