REVIEW 7 cited by
CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion
Not yet reviewed by Pith; the record is open.
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
read the original abstract
This paper proposes a novel diffusion-based model, CompoDiff, for solving zero-shot Composed Image Retrieval (ZS-CIR) with latent diffusion. This paper also introduces a new synthetic dataset, named SynthTriplets18M, with 18.8 million reference images, conditions, and corresponding target image triplets to train CIR models. CompoDiff and SynthTriplets18M tackle the shortages of the previous CIR approaches, such as poor generalizability due to the small dataset scale and the limited types of conditions. CompoDiff not only achieves a new state-of-the-art on four ZS-CIR benchmarks, including FashionIQ, CIRR, CIRCO, and GeneCIS, but also enables a more versatile and controllable CIR by accepting various conditions, such as negative text, and image mask conditions. CompoDiff also shows the controllability of the condition strength between text and image queries and the trade-off between inference speed and performance, which are unavailable with existing CIR methods. The code and dataset are available at https://github.com/navervision/CompoDiff
Forward citations
Cited by 7 Pith papers
-
DeliCIR: Memory-Guided Test-Time Deliberation via Multi-Agent Collaboration for Composed Image Retrieval
Proposes PDF, a hierarchical multi-agent Perception-to-Deliberation Framework that adds experience self-evolution and test-time scaling to composed image retrieval, claiming SOTA on CIRR, CIRCO, and FashionIQ.
-
CoVR-R:Reason-Aware Composed Video Retrieval
Zero-shot LMM reasoning over edit after-effects (states, phases, camera, tempo) plus a new CoVR-R benchmark yields large recall gains on implicit-effect composed video retrieval without task-specific training.
-
Beyond Simple Edits: Composed Video Retrieval with Dense Modifications
A new benchmark with much longer, denser modification texts, plus a single-encoder fusion model, raises composed video retrieval Recall@1 by 3.4 points on its own test set.
-
Composed Object Retrieval: Object-level Retrieval via Composed Expressions
Introduces Composed Object Retrieval, a masked object-level retrieval task with the COR127K benchmark and CORE model, claiming large gains over untuned CIR baselines.
-
FACap: A Large-scale Fashion Dataset for Fine-grained Composed Image Retrieval
FACap contributes 227,680 fashion CIR triplets with VLM/LLM-generated modification texts, and FashionBLIP-2 trained on it reaches 44.63 average Recall on FashionIQ without downstream fine-tuning and 65.97 with fine-tuning.
-
MOON2.0: Dynamic Modality-balanced Multimodal Representation Learning for E-commerce Product Understanding
MOON2.0 combines modality-routed experts, intra-product image-text alignment, MLLM-generated data augmentation, and dynamic sample filtering to reach state-of-the-art zero-shot e-commerce product understanding.
-
Zero Shot Composed Image Retrieval
Fine-tuning BLIP-2 with a Q-Former raises FashionIQ validation Recall@10 to roughly 45%, but the zero-shot framing is inaccurate and the DPO variant omits the reference image.
Discussion (0). Sign in to comment.