InfoSculpt: Sculpting the Latent Space for Generalized Category Discovery
Generalized Category Discovery (GCD) aims to classify instances from both known and novel categories within a large-scale unlabeled dataset, a critical yet challenging task for real-world, open-world applications. However, existing methods often rely on pseudo-labeling, or two-stage clustering, which lack a principled mechanism to explicitly disentangle essential, category-defining signals from instance-specific noise. In this paper, we address this fundamental limitation by re-framing GCD from an information-theoretic perspective, grounded in the Information Bottleneck (IB) principle. We introduce InfoSculpt, a novel framework that systematically sculpts the representation space by minimizing a dual Conditional Mutual Information (CMI) objective. InfoSculpt uniquely combines a Category-Level CMI on labeled data to learn compact and discriminative representations for known classes, and a complementary Instance-Level CMI on all data to distill invariant features by compressing augmentation-induced noise. These two objectives work synergistically at different scales to produce a disentangled and robust latent space where categorical information is preserved while noisy, instance-specific details are discarded. Extensive experiments on 8 benchmarks demonstrate that InfoSculpt validating the effectiveness of our information-theoretic approach.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Sculpting priors
Bayesian priors are investigated for detecting targets of known spectral signature (but unknown strength) in cluttered backgrounds. A specific problem is the construction (or ``sculpting'') of a Bayesian prior that unifo…
Image Sculpting: Precise Object Editing with 3D Geometry Control
We present Image Sculpting, a new framework for editing 2D images by incorporating tools from 3D geometry and graphics. This approach differs markedly from existing methods, which are confined to 2D spaces and typically …
3D geometryObjectOmniGCD: Abstracting Generalized Category Discovery for Modality Agnosticism
Generalized Category Discovery (GCD) challenges methods to identify known and novel classes using partially labeled data, mirroring human category learning. Unlike prior GCD methods, which operate within a single modalit…
Representation LearningGeneralized Category Discovery in Hyperspectral Images via Prototype Subspace Modeling
Generalized category discovery~(GCD) seeks to jointly identify both known and novel categories in unlabeled data. While prior works have mainly focused on RGB images, their assumptions and modeling strategies do not gene…
Sculpting Latent Spaces With MMD: Disentanglement With Programmable Priors
Learning disentangled representations, where distinct factors of variation are captured by independent latent variables, is a central goal in machine learning. The dominant approach has been the Variational Autoencoder (…