AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Global and Local Entailment Learning for Natural World Imagery

Srikumar Sastry, Aayush Dhakal, Eric Xing, Subash Khanal, Nathan Jacobs

ICCV 2025 · Vision-language and multimodal › CLIP and zero-shot · approach: Recaptioning and text-supervised pretraining · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add global entailment loss L_GE to local entailment loss (ablation)RCME · iNaturalist-2021 zero-shot classificationaverage accuracy: 41.50 -> 62.97Improved
replace prior preservation loss with cross-modal alignment loss (ablation)RCME · iNaturalist-2021 zero-shot classificationaverage accuracy: 62.97 -> 65.09Improved
add cross-modal alignment loss to local entailment loss alone (ablation)L_LE · iNaturalist-2021 zero-shot classificationaverage accuracy: 41.50 -> 43.65Improved
add hard negative mining (ablation)RCME · iNaturalist-2021 zero-shot classificationaverage accuracy: 62.22 -> 65.09Improved
add hard negative mining (ablation)RCME · BioCLIP-Rare zero-shot classificationaverage accuracy: 59.12 -> 62.64Improved
use RCME instead of Radial Embeddings for ordering of taxonomic labelsRCME · iNaturalist-2021 hierarchical retrievalKendall's tau_d: 0.521 -> 0.993Improved
use RCME instead of ATMG for zero-shot classificationRCME · iNaturalist-2021 zero-shot classificationaverage accuracy: 61.89 -> 65.09Improved
train from OpenCLIP initialization instead of fine-tuning from BioCLIPRCME · iNaturalist-2021 zero-shot classificationaverage accuracy: 57.71 -> 65.09Improved
use RCME for image-to-image retrieval versus ATMGRCME · iNaturalist-2021 image-to-image retrievalaverage R@1: 84.08 -> 86.88Improved
apply RCME objective on HierarCaps with CLIP ViT-B/16 versus Radial Emb.RCME · HierarCapsF1: 0.229 -> 0.241Improved
vary margin alpha of global entailment loss from 0 to pi/2 (ablation)RCME · HierarCapsF1: 0.226 -> 0.241Improved
reduce number of retrieval steps from 50 to 10 (ablation)RCME · iNaturalist-2021 hierarchical retrievalprecision and recall: 0.458 -> 0.527 precision; 0.572 -> 0.472 recallMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy