A Hidden Stumbling Block in Generalized Category Discovery: Distracted Attention

• URL: http://arxiv.org/abs/2507.14315v1
• Date: Fri, 18 Jul 2025 18:39:16 GMT
• Title: A Hidden Stumbling Block in Generalized Category Discovery: Distracted Attention
• Authors: Qiyu Xu, Zhanxuan Hu, Yu Duan, Ercheng Pei, Yonghang Tai,
• Abstract summary: Generalized Category Discovery (GCD) aims to classify unlabeled data from both known and unknown categories.<n>Models tend to focus not only on key objects in the image but also on task-irrelevant background regions.<n>We propose Attention Focusing (AF), an adaptive mechanism designed to sharpen the model's focus by pruning non-informative tokens.
• Score: 3.491141037235349
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generalized Category Discovery (GCD) aims to classify unlabeled data from both known and unknown categories by leveraging knowledge from labeled known categories. While existing methods have made notable progress, they often overlook a hidden stumbling block in GCD: distracted attention. Specifically, when processing unlabeled data, models tend to focus not only on key objects in the image but also on task-irrelevant background regions, leading to suboptimal feature extraction. To remove this stumbling block, we propose Attention Focusing (AF), an adaptive mechanism designed to sharpen the model's focus by pruning non-informative tokens. AF consists of two simple yet effective components: Token Importance Measurement (TIME) and Token Adaptive Pruning (TAP), working in a cascade. TIME quantifies token importance across multiple scales, while TAP prunes non-informative tokens by utilizing the multi-scale importance scores provided by TIME. AF is a lightweight, plug-and-play module that integrates seamlessly into existing GCD methods with minimal computational overhead. When incorporated into one prominent GCD method, SimGCD, AF achieves up to 15.4% performance improvement over the baseline with minimal computational overhead. The implementation code is provided in https://github.com/Afleve/AFGCD.

Related papers

• VLAD-BuFF: Burst-aware Fast Feature Aggregation for Visual Place Recognition [23.173085268845384]
  This paper introduces VLAD-BuFF, a self-similarity based feature discounting mechanism to learn Burst-aware features within end-to-end VPR training. We benchmark our method on 9 public datasets, where VLAD-BuFF sets a new state of the art. Our method is able to maintain its high recall even for 12x reduced local feature dimensions, thus enabling fast feature aggregation without compromising on recall.
  arXiv  Detail & Related papers  (2024-09-28T09:44:08Z)
• Agglomerative Token Clustering [61.0477253613511]
  Agglomerative Token Clustering (ATC) is a novel token merging method that consistently outperforms previous methods. We find that ATC achieves state-of-the-art performance across all tasks, and can even perform on par with prior state-of-the-art when applied off-the-shelf.
  arXiv  Detail & Related papers  (2024-09-18T12:37:58Z)
• SCAPE: A Simple and Strong Category-Agnostic Pose Estimator [6.705257644513057]
  Category-Agnostic Pose Estimation (CAPE) aims to localize keypoints on an object of any category given few exemplars in an in-context manner. We introduce two key modules: a global keypoint feature perceptor to inject global semantic information into support keypoints, and a keypoint attention refiner to enhance inter-node correlation between keypoints. SCAPE outperforms prior arts by 2.2 and 1.3 PCK under 1-shot and 5-shot settings with faster inference speed and lighter model capacity.
  arXiv  Detail & Related papers  (2024-07-18T13:02:57Z)
• Open-Vocabulary Animal Keypoint Detection with Semantic-feature Matching [74.75284453828017]
  Open-Vocabulary Keypoint Detection (OVKD) task is innovatively designed to use text prompts for identifying arbitrary keypoints across any species. We have developed a novel framework named Open-Vocabulary Keypoint Detection with Semantic-feature Matching (KDSM) This framework combines vision and language models, creating an interplay between language features and local keypoint visual features.
  arXiv  Detail & Related papers  (2023-10-08T07:42:41Z)
• PDiscoNet: Semantically consistent part discovery for fine-grained recognition [62.12602920807109]
  We propose PDiscoNet to discover object parts by using only image-level class labels along with priors encouraging the parts to be. Our results on CUB, CelebA, and PartImageNet show that the proposed method provides substantially better part discovery performance than previous methods.
  arXiv  Detail & Related papers  (2023-09-06T17:19:29Z)
• Less is More: Focus Attention for Efficient DETR [23.81282650112188]
  We propose Focus-DETR, which focuses attention on more informative tokens for a better trade-off between computation efficiency and model accuracy. Specifically, we reconstruct the encoder with dual attention, which includes a token scoring mechanism. Compared with the state-of-the-art sparse DETR-like detectors under the same setting, our Focus-DETR gets comparable complexity while achieving 50.4AP (+2.2) on COCO.
  arXiv  Detail & Related papers  (2023-07-24T08:39:11Z)
• Focus for Free in Density-Based Counting [56.961229110268036]
  We introduce two methods that repurpose the available point annotations to enhance counting performance. The first is a counting-specific augmentation that leverages point annotations to simulate occluded objects in both input and density images. The second method, foreground distillation, generates foreground masks from the point annotations, from which we train an auxiliary network on images with blacked-out backgrounds.
  arXiv  Detail & Related papers  (2023-06-08T11:54:37Z)
• Weakly Supervised Semantic Segmentation using Out-of-Distribution Data [50.45689349004041]
  Weakly supervised semantic segmentation (WSSS) methods are often built on pixel-level localization maps. We propose a novel source of information to distinguish foreground from the background: Out-of-Distribution (OoD) data.
  arXiv  Detail & Related papers  (2022-03-08T05:33:35Z)
• Channel DropBlock: An Improved Regularization Method for Fine-Grained Visual Classification [58.07257910065007]
  Existing approaches mainly tackle this problem by introducing attention mechanisms to locate the discriminative parts or feature encoding approaches to extract the highly parameterized features in a weakly-supervised fashion. In this work, we propose a lightweight yet effective regularization method named Channel DropBlock (CDB) in combination with two alternative correlation metrics, to address this problem.
  arXiv  Detail & Related papers  (2021-06-07T09:03:02Z)

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.