Pith. sign in

REVIEW 9 cited by

SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation

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 2209.08575 v1 pith:U3K3W4DI submitted 2022-09-18 cs.CV

Meng-Hao Guo , Cheng-Ze Lu , Qibin Hou , Zhengning Liu , Ming-Ming Cheng , Shi-Min Hu This is my paper · ORCID
classification cs.CV
keywords segnextconvolutionalsegmentationattentionmodelspascalsemanticachieves
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present SegNeXt, a simple convolutional network architecture for semantic segmentation. Recent transformer-based models have dominated the field of semantic segmentation due to the efficiency of self-attention in encoding spatial information. In this paper, we show that convolutional attention is a more efficient and effective way to encode contextual information than the self-attention mechanism in transformers. By re-examining the characteristics owned by successful segmentation models, we discover several key components leading to the performance improvement of segmentation models. This motivates us to design a novel convolutional attention network that uses cheap convolutional operations. Without bells and whistles, our SegNeXt significantly improves the performance of previous state-of-the-art methods on popular benchmarks, including ADE20K, Cityscapes, COCO-Stuff, Pascal VOC, Pascal Context, and iSAID. Notably, SegNeXt outperforms EfficientNet-L2 w/ NAS-FPN and achieves 90.6% mIoU on the Pascal VOC 2012 test leaderboard using only 1/10 parameters of it. On average, SegNeXt achieves about 2.0% mIoU improvements compared to the state-of-the-art methods on the ADE20K datasets with the same or fewer computations. Code is available at https://github.com/uyzhang/JSeg (Jittor) and https://github.com/Visual-Attention-Network/SegNeXt (Pytorch).

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

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

  1. MetaScope: Optics-Driven Neural Network for Ultra-Micro Metalens Endoscopy

    cs.CV 2025-08 unverdicted novelty 6.0 of 10

    MetaScope, an optics-driven network, corrects metalens endoscope images and outperforms prior methods on segmentation and restoration.

  2. UNet--: Memory-Efficient and Feature-Enhanced Network Architecture based on U-Net with Reduced Skip-Connections

    cs.CV 2024-12 conditional novelty 6.0 of 10

    UNet-- replaces U-Net's four skip connections with a single compact multi-scale feature map plus an expansion module, reducing skip-connection memory by 93.3% while slightly improving restoration accuracy.

  3. ROSE: Revolutionizing Open-Set Dense Segmentation with Patch-Wise Perceptual Large Multimodal Model

    cs.CV 2024-11 conditional novelty 6.0 of 10

    ROSE uses patch-wise perception in a large multimodal model to predict dense masks and generate open-set category names without predefined prompts.

  4. 2K Retrofit: Entropy-Guided Efficient Sparse Refinement for High-Resolution 3D Geometry Prediction

    cs.CV 2026-03 conditional novelty 5.5 of 10

    Entropy-guided sparse refinement upgrades frozen low-resolution geometric foundation models to accurate 2K depth and pointmap outputs at a fraction of full-resolution cost.

  5. CarboFormer: A Lightweight Semantic Segmentation Architecture for Efficient Carbon Dioxide Detection Using Optical Gas Imaging

    cs.CV 2025-05 conditional novelty 4.0 of 10

    CarboFormer, a 5.07M-parameter transformer-based model, segments CO2 plumes in optical gas images with up to 92.98% mIoU at 84.68 FPS.

  6. Dedicated Inference Engine and Binary-Weight Neural Networks for Lightweight Instance Segmentation

    cs.CV 2025-01 conditional novelty 4.0 of 10

    A dual-mode XNOR/AND bitwise MAC architecture for 8-bit activation, 1-bit weight inference reduces gate count to about 52% of prior designs, alongside binary-weight instance segmentation networks that claim higher Per...

  7. RecConv: Efficient Recursive Convolutions for Multi-Frequency Representations

    cs.CV 2024-12 conditional novelty 4.0 of 10

    RecConv recursively decomposes feature maps into multiple scales with shared small-kernel depthwise convolutions to grow the effective receptive field to k times 2^ell at roughly constant FLOPs, yielding the RecNeXt b...

  8. Heuristical Comparison of Vision Transformers Against Convolutional Neural Networks for Semantic Segmentation on Remote Sensing Imagery

    cs.CV 2024-11 reject novelty 4.0 of 10

    A 42.9M-parameter UNet with a weighted IoU-Dice-cross-entropy loss is compared against a 200M-parameter MaskFormer on iSAID aerial segmentation, reporting mIoU 73.4 and 82.48 respectively.

  9. Data-driven Detection and Evaluation of Damages in Concrete Structures: Using Deep Learning and Computer Vision

    cs.CV 2025-01 conditional novelty 3.0 of 10

    On an augmented 400-image concrete damage dataset, YOLO-v7 instance segmentation reached 96.1% mAP@0.5 at 40 FPS, outperforming Mask R-CNN at 92.1% mAP@0.5 and 18 FPS.

Pith tools