InfoSculpt: Sculpting the Latent Space for Generalized Category Discovery

• URL: http://arxiv.org/abs/2601.10098v1
• Date: Thu, 15 Jan 2026 06:00:13 GMT
• Title: InfoSculpt: Sculpting the Latent Space for Generalized Category Discovery
• Abstract summary: Generalized Category Discovery (GCD) aims to classify instances from both known and novel categories within a large-scale unlabeled dataset.<n>We introduce InfoSculpt, a novel framework that systematically sculpts the representation space by minimizing a dual Conditional Mutual Information (CMI) objective.
• Score: 7.797804082289705
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• STAR-IOD: Scale-decoupled Topology Alignment with Pseudo-label Refinement for Remote Sensing Incremental Object Detection [26.581594459769363]
  Traditional detectors often forget previously learned categories when learning new ones.<n>Existing methods largely overlook the intra-class scale variations prevalent in remote sensing scenes.<n>We propose a novel framework, STAR-IOD, to address these challenges.
  arXiv  Detail & Related papers  (2026-05-20T05:43:09Z)
• Sharpness-aware Dynamic Anchor Selection for Generalized Category Discovery [61.694524826522205]
  Given some labeled data of known classes, GCD aims to cluster unlabeled data that contain both known and unknown classes.<n>Large pre-trained models have a preference for some specific visual patterns, resulting in encoding spurious correlation for unlabeled data.<n>We propose a novel method, which contains two modules: Loss Sharpness Penalty (LSP) and Dynamic Anchor Selection (DAS)
  arXiv  Detail & Related papers  (2025-12-15T02:24:06Z)
• Generalized Fine-Grained Category Discovery with Multi-Granularity Conceptual Experts [81.68203255687051]
  Generalized Category Discovery is an open-world problem that clusters unlabeled data by leveraging knowledge from partially labeled categories.<n>Existing approaches fail to exploit multi-granularity conceptual information in visual data.<n>We propose a Multi-Granularity Experts framework that integrates multi-granularity knowledge for accurate category discovery.
  arXiv  Detail & Related papers  (2025-09-30T13:25:11Z)
• Component Adaptive Clustering for Generalized Category Discovery [13.322393552334063]
  We propose a cluster-centric contrastive learning framework that incorporates Adaptive Slot Attention (AdaSlot) into the Generalized Category Discovery (GCD) framework.<n>AdaSlot dynamically determines the optimal number of slots based on data complexity, removing the need for predefined slot counts.<n>Our method captures both instance-specific and spatially clustered features, improving class discovery in open-world scenarios.
  arXiv  Detail & Related papers  (2025-07-02T13:41:30Z)
• Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detection [52.490375806093745]
  The objective of few-shot object detection (FSOD) is to detect novel objects with few training samples.<n>We introduce the side information to alleviate the negative influences derived from the feature space and sample viewpoints.<n>Our model outperforms the previous state-of-the-art methods, significantly improving the ability of FSOD in most shots/splits.
  arXiv  Detail & Related papers  (2025-04-09T17:24:05Z)
• Learning Part Knowledge to Facilitate Category Understanding for Fine-Grained Generalized Category Discovery [10.98097145569408]
  Generalized Category Discovery (GCD) aims to classify unlabeled data containing both seen and novel categories.<n>We propose incorporating part knowledge to address fine-grained GCD, which introduces two key challenges.
  arXiv  Detail & Related papers  (2025-03-21T01:37:51Z)
• When Segmentation Meets Hyperspectral Image: New Paradigm for Hyperspectral Image Classification [4.179738334055251]
  Hyperspectral image (HSI) classification is a cornerstone of remote sensing, enabling precise material and land-cover identification through rich spectral information.<n>While deep learning has driven significant progress in this task, small patch-based classifiers, which account for over 90% of the progress, face limitations.<n>We propose a novel paradigm and baseline, HSIseg, for HSI classification that leverages segmentation techniques combined with a novel Dynamic Shifted Regional Transformer (DSRT) to overcome these challenges.
  arXiv  Detail & Related papers  (2025-02-18T05:04:29Z)
• Sampling-enabled scalable manifold learning unveils the discriminative cluster structure of high-dimensional data [17.411028691739897]
  We propose a sampling-based Scalable manifold learning technique that enables Uniform and Discriminative Embedding, namely SUDE, for large-scale and high-dimensional data.<n>We empirically validated the effectiveness of SUDE on synthetic datasets and real-world benchmarks, and applied it to analyze single-cell data and detect anomalies in electrocardiogram (ECG) signals.
  arXiv  Detail & Related papers  (2024-01-02T08:43:06Z)
• Robust Saliency-Aware Distillation for Few-shot Fine-grained Visual Recognition [57.08108545219043]
  Recognizing novel sub-categories with scarce samples is an essential and challenging research topic in computer vision. Existing literature addresses this challenge by employing local-based representation approaches. This article proposes a novel model, Robust Saliency-aware Distillation (RSaD), for few-shot fine-grained visual recognition.
  arXiv  Detail & Related papers  (2023-05-12T00:13:17Z)
• Dynamic Conceptional Contrastive Learning for Generalized Category Discovery [76.82327473338734]
  Generalized category discovery (GCD) aims to automatically cluster partially labeled data. Unlabeled data contain instances that are not only from known categories of the labeled data but also from novel categories. One effective way for GCD is applying self-supervised learning to learn discriminate representation for unlabeled data. We propose a Dynamic Conceptional Contrastive Learning framework, which can effectively improve clustering accuracy.
  arXiv  Detail & Related papers  (2023-03-30T14:04:39Z)
• Unveiling the Potential of Structure-Preserving for Weakly Supervised Object Localization [71.79436685992128]
  We propose a two-stage approach, termed structure-preserving activation (SPA), towards fully leveraging the structure information incorporated in convolutional features for WSOL. In the first stage, a restricted activation module (RAM) is designed to alleviate the structure-missing issue caused by the classification network. In the second stage, we propose a post-process approach, termed self-correlation map generating (SCG) module to obtain structure-preserving localization maps.
  arXiv  Detail & Related papers  (2021-03-08T03:04:14Z)
• Capturing scattered discriminative information using a deep architecture in acoustic scene classification [49.86640645460706]
  In this study, we investigate various methods to capture discriminative information and simultaneously mitigate the overfitting problem. We adopt a max feature map method to replace conventional non-linear activations in a deep neural network. Two data augment methods and two deep architecture modules are further explored to reduce overfitting and sustain the system's discriminative power.
  arXiv  Detail & Related papers  (2020-07-09T08:32:06Z)
• Fuzziness-based Spatial-Spectral Class Discriminant Information Preserving Active Learning for Hyperspectral Image Classification [0.456877715768796]
  This work proposes a novel fuzziness-based spatial-spectral within and between for both local and global class discriminant information preserving method. Experimental results on benchmark HSI datasets demonstrate the effectiveness of the FLG method on Generative, Extreme Learning Machine and Sparse Multinomial Logistic Regression.
  arXiv  Detail & Related papers  (2020-05-28T18:58:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.