Pith. sign in

REVIEW 6 cited by

Query2Label: A Simple Transformer Way to Multi-Label Classification

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 2107.10834 v1 pith:HYJIGEIC submitted 2021-07-22 cs.CV

Shilong Liu , Lei Zhang , Xiao Yang , Hang Su , Jun Zhu This is my paper · ORCID
classification cs.CV
keywords classificationmulti-labelsimpletransformereffectiveapproachexistencefeatures
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

This paper presents a simple and effective approach to solving the multi-label classification problem. The proposed approach leverages Transformer decoders to query the existence of a class label. The use of Transformer is rooted in the need of extracting local discriminative features adaptively for different labels, which is a strongly desired property due to the existence of multiple objects in one image. The built-in cross-attention module in the Transformer decoder offers an effective way to use label embeddings as queries to probe and pool class-related features from a feature map computed by a vision backbone for subsequent binary classifications. Compared with prior works, the new framework is simple, using standard Transformers and vision backbones, and effective, consistently outperforming all previous works on five multi-label classification data sets, including MS-COCO, PASCAL VOC, NUS-WIDE, and Visual Genome. Particularly, we establish $91.3\%$ mAP on MS-COCO. We hope its compact structure, simple implementation, and superior performance serve as a strong baseline for multi-label classification tasks and future studies. The code will be available soon at https://github.com/SlongLiu/query2labels.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

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

  1. SenBen: Sensitive Scene Graphs for Explainable Content Moderation

    cs.CV 2026-04 unverdicted novelty 7.0 of 10

    SenBen is the first large-scale scene graph benchmark for sensitive content, paired with a 241M distilled model that outperforms most VLMs and safety APIs on grounded detection while running much faster.

  2. PatchDEMUX: A Certifiably Robust Framework for Multi-label Classifiers Against Adversarial Patches

    cs.CR 2025-05 conditional novelty 6.0 of 10

    PatchDEMUX extends any certified single-label patch defense to multi-label classifiers by per-class certification and a location-aware procedure that tightens bounds when the attacker can plant only one patch.

  3. Prompt-CAM: Making Vision Transformers Interpretable for Fine-Grained Analysis

    cs.CV 2025-01 conditional novelty 6.0 of 10

    Learning class-specific prompts on a frozen ViT yields attention maps that localize the discriminative traits used in fine-grained image classification.

  4. Multi-label Classification using Deep Multi-order Context-aware Kernel Networks

    cs.CV 2024-12 conditional novelty 6.0 of 10

    Proposes DMCKN, a deep kernel network that aggregates multi-order spatial context via attention and random walks, showing modest gains on two multi-label benchmarks.

  5. FISHER: Gradient-Decoupled Hierarchical Multi-Task Learning for Fine-Grained Aquatic Species Recognition

    q-bio.QM 2026-07 conditional novelty 5.0 of 10

    FISHER improves fine-grained fish recognition by detaching gradients between hierarchical tasks, raising ultra-rare species accuracy from 50.4% to 63.8% on Fish-Vista.

  6. Image Classification with Deep Reinforcement Active Learning

    cs.CV 2024-12 conditional novelty 4.0 of 10

    An active learning method that uses deep reinforcement learning (DDPG) to decide which unlabeled images to query, after pre-ranking images by margin uncertainty, reports modest accuracy improvements on CIFAR-10, SVHN,...

Pith tools