# Sparsity Hurts: Simple Linear Adapter Can Boost Generalized Category Discovery

arXiv: https://arxiv.org/abs/2605.08183 · HTML: https://mlsanity.com/paper/2605.08183/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 57 references that are in the map.
- First posted on arXiv 5 May 2026.

## Builds on (most cited first, 30 of 42)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)](https://mlsanity.com/paper/1511.07289/) (2015)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition](https://mlsanity.com/paper/2205.13535/) (2022)
- [Empirical Evaluation of Rectified Activations in Convolutional Network](https://mlsanity.com/paper/1505.00853/) (2015)
- [Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning](https://mlsanity.com/paper/1908.02983/) (2019)
- [Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning](https://mlsanity.com/paper/1606.04586/) (2016)
- [Open-Set Recognition: a Good Closed-Set Classifier is All You Need?](https://mlsanity.com/paper/2110.06207/) (2021)
- [Masked Siamese Networks for Label-Efficient Learning](https://mlsanity.com/paper/2204.07141/) (2022)
- [Generalized Category Discovery](https://mlsanity.com/paper/2201.02609/) (2022)
- [Open-World Semi-Supervised Learning](https://mlsanity.com/paper/2102.03526/) (2021)
- [A Unified Objective for Novel Class Discovery](https://mlsanity.com/paper/2108.08536/) (2021)
- [AutoNovel: Automatically Discovering and Learning Novel Visual Categories](https://mlsanity.com/paper/2106.15252/) (2021)
- [Parametric Classification for Generalized Category Discovery: A Baseline Study](https://mlsanity.com/paper/2211.11727/) (2022)
- [Dynamic Conceptional Contrastive Learning for Generalized Category Discovery](https://mlsanity.com/paper/2303.17393/) (2023)
- [PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery](https://mlsanity.com/paper/2212.05590/) (2022)
- [Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discovery](https://mlsanity.com/paper/2305.06144/) (2023)
- [No Representation Rules Them All in Category Discovery](https://mlsanity.com/paper/2311.17055/) (2023)
- [The Herbarium Challenge 2019 Dataset](https://mlsanity.com/paper/1906.05372/) (2019)
- [Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts](https://mlsanity.com/paper/2309.10019/) (2023)

## Built on by (most cited first, 1 of 1)

- [CoGe-GCD: Reframing Generalized Category Discovery with Compositional Generalization](https://mlsanity.com/paper/2609.10158/) (2026)

## Abstract (arXiv)

Generalized Category Discovery (GCD) seeks to identify novel categories from unlabeled data while retaining the classification ability of seen categories. Prior GCD methods commonly leverage transferable representations from pre-trained models, adapting to downstream datasets via partial fine-tuning (updating only the final ViT block) and visual prompt tuning (appending learnable vectors to inputs). However, conventional partial fine-tuning offers limited flexibility, as it fails to adapt the entire model; meanwhile, visual prompt tuning is prone to overfitting, due to its sensitivity to initialization and inherently constrained capacity. To address these limitations, we propose LAGCD, a simple yet effective GCD approach that embeds a residual linear adapter into each ViT block. From the perspective of feature sparsity, we systematically show that non-linearity in conventional adapters impairs performance, whereas our linear adapter enhances it by enabling more flexible model capacity. We further introduce an auxiliary distribution alignment loss to mitigate the negative impact of biased predictions between seen and novel categories. Extensive experiments on both generic and fine-grained datasets confirm that LAGCD consistently improves performance over many sophisticated baselines. The source code is available at https://github.com/yebo0216best/LAGCD