Pith. sign in

REVIEW 8 cited by

Dilated Neighborhood Attention Transformer

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2209.15001 v3 pith:CVYYHVVP submitted 2022-09-29 cs.CV cs.AIcs.LG

Ali Hassani , Humphrey Shi This is my paper
classification cs.CVcs.AIcs.LG
keywords attentionsegmentationade20kneighborhoodtransformercocodilatedglobal
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Transformers are quickly becoming one of the most heavily applied deep learning architectures across modalities, domains, and tasks. In vision, on top of ongoing efforts into plain transformers, hierarchical transformers have also gained significant attention, thanks to their performance and easy integration into existing frameworks. These models typically employ localized attention mechanisms, such as the sliding-window Neighborhood Attention (NA) or Swin Transformer's Shifted Window Self Attention. While effective at reducing self attention's quadratic complexity, local attention weakens two of the most desirable properties of self attention: long range inter-dependency modeling, and global receptive field. In this paper, we introduce Dilated Neighborhood Attention (DiNA), a natural, flexible and efficient extension to NA that can capture more global context and expand receptive fields exponentially at no additional cost. NA's local attention and DiNA's sparse global attention complement each other, and therefore we introduce Dilated Neighborhood Attention Transformer (DiNAT), a new hierarchical vision transformer built upon both. DiNAT variants enjoy significant improvements over strong baselines such as NAT, Swin, and ConvNeXt. Our large model is faster and ahead of its Swin counterpart by 1.6% box AP in COCO object detection, 1.4% mask AP in COCO instance segmentation, and 1.4% mIoU in ADE20K semantic segmentation. Paired with new frameworks, our large variant is the new state of the art panoptic segmentation model on COCO (58.5 PQ) and ADE20K (49.4 PQ), and instance segmentation model on Cityscapes (45.1 AP) and ADE20K (35.4 AP) (no extra data). It also matches the state of the art specialized semantic segmentation models on ADE20K (58.1 mIoU), and ranks second on Cityscapes (84.5 mIoU) (no extra data).

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. A2Mamba: Attention-augmented State Space Models for Visual Recognition

    cs.CV 2025-07 conditional novelty 7.0 of 10

    A2Mamba combines multi-scale attention and a state space model into a single mixer, achieving 86.1% top-1 accuracy on ImageNet-1K and gains on dense prediction tasks.

  2. iFAN: Inference-Aware Learning for Plain Mask Transformers

    cs.CV 2026-08 conditional novelty 6.0 of 10

    iFAN improves query-based mask transformers by training a mask-quality head for score ranking and distilling better intermediate-layer predictions into the final layer, yielding consistent gains at no inference-time cost.

  3. RAT+: Train Dense, Infer Sparse -- Recurrence Augmented Attention for Dilated Inference

    cs.LG 2026-02 unverdicted novelty 6.0 of 10

    RAT+ pretrains a single dense recurrent-augmented attention model that supports flexible dilated sparse inference after short adaptation, matching dense accuracy at moderate dilation and losing only 1-3 points at high...

  4. Gaussian Belief Propagation Network for Depth Completion

    cs.CV 2026-01 conditional novelty 6.0 of 10

    Depth completion via a learned Markov random field solved with Gaussian belief propagation reports state-of-the-art RMSE on NYUv2 and best iRMSE on KITTI, plus better robustness at extreme sparsity.

  5. DPFormer: Dynamic Prompt Transformer for Continual Learning

    cs.CV 2025-06 conditional novelty 6.0 of 10

    A transformer with class and task prototype prompts, trained with three losses, reports state-of-the-art class-incremental accuracy on three image benchmarks.

  6. ScratNet: A Swin-Based Multi-Scale Dilated Network with Precision Refinement for Semiconductor Scratch Segmentation

    cs.CV 2026-07 conditional novelty 5.5 of 10

    A modified Swin-Base backbone with MDA+SIM+PR decoder modules yields higher IoU/Dice and tighter boundaries than FCN/FPN/UPerNet on semiconductor scratch segmentation.

  7. NABLA: Neighborhood Adaptive Block-Level Attention

    cs.CV 2025-07 conditional novelty 5.0 of 10

    NABLA builds content-aware block-sparse attention masks by pooling queries and keys and thresholding their softmax CDF, giving near-baseline video quality at up to 2.7x inference speedup and 1.46x pretraining speedup.

  8. DFYP: A Dynamic Fusion Framework with Spectral Channel Attention and Adaptive Operator learning for Crop Yield Prediction

    cs.CV 2025-07 reject novelty 3.0 of 10

    DFYP is a crop yield prediction framework combining resolution-aware channel attention, validation-driven edge operator selection, and CNN-ViT fusion, but the method's internal contradictions and test-set-tuned evalua...

Pith tools