AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

SpectralGCD: Spectral Concept Selection and Cross-modal Representation Learning for Generalized Category Discovery

Lorenzo Caselli, Marco Mistretta, Simone Magistri, Andrew D. Bagdanov

ICLR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Unimodal-to-multimodal representation transfer · 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 forward and reverse distillation from frozen teacher (ablation)SpectralGCD · Stanford Cars (All)clustering accuracy: 77.4 -> 89.1Improved
add reverse distillation to forward distillation (ablation)SpectralGCD · Stanford Cars (All)clustering accuracy: 86.0 -> 89.1Improved
add forward distillation to reverse distillation (ablation)SpectralGCD · CUB (All)clustering accuracy: 79.3 -> 79.2No clear effect
train classifier on cross-modal representation instead of image features (ablation)SpectralGCD · CUB (All)clustering accuracy: 76.3 -> 79.2Improved
train classifier on cross-modal representation instead of image features (ablation)SpectralGCD · CIFAR-100 (Old)clustering accuracy (Old): 88.7 -> 87.2Hurt
apply Spectral Filtering to the concept dictionary (ablation)SpectralGCD · Stanford Cars / CIFAR-100clustering accuracy (All)Improved
use stronger teacher (DFN-5B H/14 vs ViT-B/16) (ablation)SpectralGCD · CIFAR-100 (All)clustering accuracy: 78.5 -> 88.8Improved
use Tags dictionary instead of OpenImagesV7 (ablation)SpectralGCD · Stanford Cars (All)clustering accuracy: 85.8 -> 89.1Improved
use ViT-H/14 student instead of ViT-B/16 (ablation)SpectralGCD · CUB (All)clustering accuracy: 79.2 -> 80.0Improved
compute spectral filtering from Old samples only (ablation)SpectralGCD · CUB (All)clustering accuracy: 79.2 -> 77.8Hurt
use SpectralGCD instead of TextGCD (Tags+Attributes)TextGCD · Stanford Cars (All)clustering accuracy: 86.9 -> 89.1Improved
use SpectralGCD instead of TextGCDTextGCD · CIFAR-10/100 (All)clustering accuracy: 98.2 -> 98.5; 85.7 -> 86.1No clear effect

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