Pith. sign in

REVIEW 7 cited by

UniCat: Crafting a Stronger Fusion Baseline for Multimodal Re-Identification

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 2310.18812 v1 pith:YBYBBGX7 submitted 2023-10-28 cs.CV

Jennifer Crawford , Haoli Yin , Luke McDermott , Daniel Cummings This is my paper · ORCID
classification cs.CV
keywords modalitiesfusionmodalitymultimodalwhenacrossdatalate-fusion
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Multimodal Re-Identification (ReID) is a popular retrieval task that aims to re-identify objects across diverse data streams, prompting many researchers to integrate multiple modalities into a unified representation. While such fusion promises a holistic view, our investigations shed light on potential pitfalls. We uncover that prevailing late-fusion techniques often produce suboptimal latent representations when compared to methods that train modalities in isolation. We argue that this effect is largely due to the inadvertent relaxation of the training objectives on individual modalities when using fusion, what others have termed modality laziness. We present a nuanced point-of-view that this relaxation can lead to certain modalities failing to fully harness available task-relevant information, and yet, offers a protective veil to noisy modalities, preventing them from overfitting to task-irrelevant data. Our findings also show that unimodal concatenation (UniCat) and other late-fusion ensembling of unimodal backbones, when paired with best-known training techniques, exceed the current state-of-the-art performance across several multimodal ReID benchmarks. By unveiling the double-edged sword of "modality laziness", we motivate future research in balancing local modality strengths with global representations.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

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

  1. Multi-Modal Object Re-Identification with Prompt-S6 and Semantic-Aware Knowledge Guidance

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Prompt-S6 plus semantic token pruning and progressive tri-modal fusion improves multi-spectral object ReID accuracy and efficiency on four benchmarks.

  2. ICPL-ReID: Identity-Conditional Prompt Learning for Multi-Spectral Object Re-Identification

    cs.CV 2025-05 conditional novelty 6.0 of 10

    An identity-conditioned, online prompt learning framework with low-rank adapters sets new state-of-the-art results on five multi-spectral person and vehicle re-identification benchmarks.

  3. Modality Unified Attack for Omni-Modality Person Re-Identification

    cs.CV 2025-01 conditional novelty 6.0 of 10

    Modality-specific adversarial generators trained with metric disruption, simulated cross-modal, and collaborative multi-modal losses transfer to black-box single-, cross-, and multi-modality person re-id models, reach...

  4. MambaPro: Multi-Modal Object Re-Identification with Mamba Aggregation and Synergistic Prompt

    cs.CV 2024-12 conditional novelty 6.0 of 10

    MambaPro combines CLIP with a parallel adapter, synergistic residual prompts, and Mamba aggregation to achieve state-of-the-art mAP on RGBNT201, RGBNT100, and MSVR310.

  5. DeMo: Decoupled Feature-Based Mixture of Experts for Multi-Modal Object Re-Identification

    cs.CV 2024-12 conditional novelty 6.0 of 10

    DeMo improves multi-modal object re-identification by decoupling RGB, NIR, and TIR features into seven attention-derived streams and weighting them with an attention-triggered mixture of experts.

  6. Blurring Modal Boundaries: A Unified Survey from Single- to Multi-Modal Person Re-ldentification

    cs.CV 2026-07 conditional novelty 5.0 of 10

    A unified taxonomy and survey of single- to multi-modal person ReID, plus a Transformer-based VI-ReID baseline that is solid but not state-of-the-art.

  7. Multi-Modal Object Re-Identification with Dual Semantic Guidance and Global-Local Mutual Modulation

    cs.CV 2026-07 conditional novelty 4.0 of 10

    A dual-semantic (text + soft mask) global-local mutual modulation framework reports SOTA mAP/Rank-1 on RGBNT201, RGBNT100, and MSVR310.

Pith tools