Pith. sign in

REVIEW 4 cited by

ResNeSt: Split-Attention Networks

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 2004.08955 v2 pith:XULHWQPF submitted 2020-04-19 cs.CV

Hang Zhang , Chongruo Wu , Zhongyue Zhang , Yi Zhu , Haibin Lin , Zhi Zhang , Yue Sun , Tong He
show 4 more authors
Jonas Mueller R. Manmatha Mu Li Alexander Smola
This is my paper · ORCID
classification cs.CV
keywords resnestattentionlearningresultsaccuracyachievedadditionadopted
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

It is well known that featuremap attention and multi-path representation are important for visual recognition. In this paper, we present a modularized architecture, which applies the channel-wise attention on different network branches to leverage their success in capturing cross-feature interactions and learning diverse representations. Our design results in a simple and unified computation block, which can be parameterized using only a few variables. Our model, named ResNeSt, outperforms EfficientNet in accuracy and latency trade-off on image classification. In addition, ResNeSt has achieved superior transfer learning results on several public benchmarks serving as the backbone, and has been adopted by the winning entries of COCO-LVIS challenge. The source code for complete system and pretrained models are publicly available.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. TSRec: Enhancing Repeat-Aware Recommendation from a Temporal-Sequential Perspective

    cs.IR 2025-06 conditional novelty 6.0 of 10

    TSRec improves repeat-aware recommendation by jointly modeling repeat time intervals and sequence similarity between current and prior repeat behavior, outperforming ten baselines on three public benchmarks.

  2. Towards Counterfactual and Contrastive Explainability and Transparency of DCNN Image Classifiers

    cs.CV 2025-01 conditional novelty 5.0 of 10

    The paper learns sparse masks over a DCNN's top-layer filters that preserve the inferred class (contrastive) or flip it to an alter class (counterfactual), evaluated on CUB bird classification.

  3. Large scale cross-regional remote sensing flood monitoring framework for operative mapping and impact analysis

    cs.CV 2026-07 conditional novelty 4.0 of 10

    Under limited Russian flood labels, multimodal U-Net++ (F1 0.84) outperforms fine-tuned AnySat for water mapping, and the masks feed an EMERCOM-style damage pipeline that matches Tulun 2019 official area and exposure ...

  4. Navigating limitations with precision: A fine-grained ensemble approach to wrist pathology recognition on a limited x-ray dataset

    cs.CV 2024-12 conditional novelty 4.0 of 10

    An ensemble of three plug-in module variants with majority voting reports 87.34% and 83.75% accuracy on two curated wrist X-ray test sets, ahead of all compared models.

Pith tools