{"ID":2829695,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.11260","arxiv_id":"2512.11260","title":"Do We Need Reformer for Vision? An Experimental Comparison with Vision Transformers","abstract":"Transformers have recently demonstrated strong performance in computer vision, with Vision Transformers (ViTs) leveraging self-attention to capture both low-level and high-level image features. However, standard ViTs remain computationally expensive, since global self-attention scales quadratically with the number of tokens, which limits their practicality for high-resolution inputs and resource-constrained settings. In this work, we investigate the Reformer architecture as an alternative vision backbone. By combining patch-based tokenization with locality-sensitive hashing (LSH) attention, our model approximates global self-attention while reducing its theoretical time complexity from $\\mathcal{O}(n^2)$ to $\\mathcal{O}(n \\log n)$ in the sequence length $n$. We evaluate the proposed Reformer-based vision model on CIFAR-10 to assess its behavior on small-scale datasets, on ImageNet-100 to study its accuracy--efficiency trade-off in a more realistic setting, and on a high-resolution medical imaging dataset to evaluate the model under longer token sequences. While the Reformer achieves higher accuracy on CIFAR-10 compared to our ViT-style baseline, the ViT model consistently outperforms the Reformer in our experiments in terms of practical efficiency and end-to-end computation time across the larger and higher-resolution settings. These results suggest that, despite the theoretical advantages of LSH-based attention, meaningful computation gains require sequence lengths substantially longer than those produced by typical high-resolution images.","short_abstract":"Transformers have recently demonstrated strong performance in computer vision, with Vision Transformers (ViTs) leveraging self-attention to capture both low-level and high-level image features. However, standard ViTs remain computationally expensive, since global self-attention scales quadratically with the number of t...","url_abs":"https://arxiv.org/abs/2512.11260","url_pdf":"https://arxiv.org/pdf/2512.11260v2","authors":"[\"Ali El Bellaj\",\"Mohammed-Amine Cheddadi\",\"Rhassan Berber\"]","published":"2025-12-12T03:49:55Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Vision Transformer\",\"Transformer\"]","has_code":false}