AI Paper Atlas

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

Let's Split Up: Zero-Shot Classifier Edits for Fine-Grained Video Understanding

Kaiting Liu, Hazel Doughty

ICLR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 0 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
use modifier retrieval on classifier weights instead of a VLM text-similarity baseline (ablation)zero-shot category splitting · SSv2-Split subset Agenerality: 27.6 -> 45.0Improved
add modifier alignment on top of modifier retrieval (ablation)zero-shot category splitting · SSv2-Split subset Agenerality: 45.0 -> 46.3Improved
finetune the full backbone with one example per subcategory (ablation)one-shot finetuning · SSv2-Split subset Alocality: 98.4 -> 0.0Hurt
restrict finetuning to the new head only (ablation)one-shot finetuning · SSv2-Split subset Alocality: 0.0 -> 98.4Improved
initialize new head with modifier alignment instead of coarse weight (ablation)one-shot finetuning · SSv2-Split subset Agenerality: 48.4 -> 52.8Improved
use one-shot head finetuning instead of full-data finetuning (ablation)category splitting · SSv2-Split subset Amean of generality and locality: 54.4 -> 75.5Improved
use stronger pretraining (MVD) instead of training from scratch (ablation)modifier alignment · SSv2-Split subset Agenerality: 37.0 -> 46.3Improved
use video-text text encoders (VideoPrism) instead of CLIP (ablation)modifier alignment · SSv2-Split subset Agenerality: 46.3 -> 46.5No clear effect
use InternVideo2 text encoder instead of CLIP (ablation)modifier alignment · SSv2-Split subset Agenerality: 46.3 -> 36.9Hurt
scale backbone from ViT-Small to ViT-Base/Large (ablation)modifier alignment · SSv2-Split subset Agenerality: 46.3 -> 43.6 (Base), 45.0 (Large)No clear effect
add category and pseudo-coarse pairs to alignment training (ablation)modifier alignment · FineGym-Split subset Agenerality: 27.6 -> 34.2Improved
add category and pseudo-coarse pairs to alignment training (ablation)modifier alignment · SSv2-Split subset Bgenerality: 40.2 -> 38.4Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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