Pith. sign in

REVIEW 10 cited by

MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions

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 2403.19651 v2 pith:JJJMBZNL submitted 2024-03-28 cs.CV cs.AIcs.CLcs.IRcs.MM

MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions

Kai Zhang , Yi Luan , Hexiang Hu , Kenton Lee , Siyuan Qiao , Wenhu Chen , Yu Su , Ming-Wei Chang This is my paper
classification cs.CV cs.AIcs.CLcs.IRcs.MM
keywords imagemagiclensinstructionsrelationsretrievalintentsmodelssearch
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Image retrieval, i.e., finding desired images given a reference image, inherently encompasses rich, multi-faceted search intents that are difficult to capture solely using image-based measures. Recent works leverage text instructions to allow users to more freely express their search intents. However, they primarily focus on image pairs that are visually similar and/or can be characterized by a small set of pre-defined relations. The core thesis of this paper is that text instructions can enable retrieving images with richer relations beyond visual similarity. To show this, we introduce MagicLens, a series of self-supervised image retrieval models that support open-ended instructions. MagicLens is built on a key novel insight: image pairs that naturally occur on the same web pages contain a wide range of implicit relations (e.g., inside view of), and we can bring those implicit relations explicit by synthesizing instructions via foundation models. Trained on 36.7M (query image, instruction, target image) triplets with rich semantic relations mined from the web, MagicLens achieves results comparable with or better than prior best on eight benchmarks of various image retrieval tasks, while maintaining high parameter efficiency with a significantly smaller model size. Additional human analyses on a 1.4M-image unseen corpus further demonstrate the diversity of search intents supported by MagicLens. Code and models are publicly available at https://open-vision-language.github.io/MagicLens/.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 10 Pith papers

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

  1. SLQ: Bridging Modalities via Shared Latent Queries for Retrieval with Frozen MLLMs

    cs.CV 2026-04 unverdicted novelty 7.0

    SLQ turns frozen MLLMs into retrievers via shared latent queries appended to inputs, outperforming fine-tuning on COCO and Flickr30K while introducing KARR-Bench for knowledge-aware evaluation.

  2. PLUME: Latent Reasoning Based Universal Multimodal Embedding

    cs.CV 2026-04 unverdicted novelty 7.0

    PLUME uses latent-state autoregressive rollouts and a progressive training curriculum to deliver efficient reasoning for universal multimodal embeddings without generating explicit rationales.

  3. VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks

    cs.CV 2024-10 conditional novelty 7.0

    VLM2Vec converts state-of-the-art vision-language models into universal multimodal embedders via contrastive training on the new MMEB benchmark, delivering 10-20% absolute gains over prior models on both in-distributi...

  4. Illuminating Visual Identity in Universal Multimodal Embeddings

    cs.CV 2026-08 conditional novelty 6.0

    By adding identity-aware sampling and a contrastive loss on a new 28-dataset benchmark, the authors build multimodal embeddings that are far better at visual identity matching without losing general retrieval accuracy.

  5. ReLoop-UME: Recurrent Depth with Learnable Retrieval Registers for Universal Multimodal Embedding

    cs.CV 2026-07 conditional novelty 6.0

    Recurrently reusing the middle retrieval-forming layers of a multimodal encoder, plus small learnable registers as persistent state, improves universal embedding retrieval at much lower latency than autoregressive rea...

  6. Language-Instructed Vision Embeddings for Controllable and Generalizable Perception

    cs.CV 2026-06 unverdicted novelty 6.0

    LIVE uses language to generate task-centric vision embeddings at inference, reducing hallucinations by 34 points on MMVP, outperforming larger VLMs on VQA, and generalizing to unseen tasks.

  7. STiTch: Semantic Transition and Transportation in Collaboration for Training-Free Zero-Shot Composed Image Retrieval

    cs.CV 2026-05 unverdicted novelty 6.0

    STiTch refines LLM captions via embedding transition and uses set-to-set bidirectional transportation alignment to improve training-free zero-shot composed image retrieval.

  8. SLQ: Bridging Modalities via Shared Latent Queries for Retrieval with Frozen MLLMs

    cs.CV 2026-04 conditional novelty 6.0

    SLQ adapts frozen MLLMs for multimodal retrieval by appending shared latent queries to text and image tokens and introduces KARR-Bench to test knowledge-aware reasoning retrieval.

  9. Combating Visual Neglect and Semantic Drift in Large Multimodal Models for Enhanced Cross-Modal Retrieval

    cs.CV 2026-04 unverdicted novelty 5.0

    SSA-ME uses saliency-aware modeling to reduce visual neglect and semantic drift, achieving SOTA results on the MMEB benchmark for multimodal retrieval.

  10. Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs

    cs.CV 2026-02 conditional novelty 5.0

    Visual token compression (4x fewer tokens) plus a three-stage generative/contrastive/judge-curated training pipeline yields state-of-the-art MLLM-based retrieval accuracy at lower inference cost.