Attention Normalization Impacts Cardinality Generalization in Slot Attention

• URL: http://arxiv.org/abs/2407.04170v2
• Date: Sun, 10 Nov 2024 11:27:34 GMT
• Title: Attention Normalization Impacts Cardinality Generalization in Slot Attention
• Authors: Markus Krimmel, Jan Achterhold, Joerg Stueckler,
• Abstract summary: We propose and investigate alternatives to the original normalization scheme which increase the capabilities of Slot Attention to varying slot and object counts. The newly proposed normalizations represent minimal and easy to implement modifications of the usual Slot Attention module.
• Score: 6.9099729240700825
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Object-centric scene decompositions are important representations for downstream tasks in fields such as computer vision and robotics. The recently proposed Slot Attention module, already leveraged by several derivative works for image segmentation and object tracking in videos, is a deep learning component which performs unsupervised object-centric scene decomposition on input images. It is based on an attention architecture, in which latent slot vectors, which hold compressed information on objects, attend to localized perceptual features from the input image. In this paper, we demonstrate that design decisions on normalizing the aggregated values in the attention architecture have considerable impact on the capabilities of Slot Attention to generalize to a higher number of slots and objects as seen during training. We propose and investigate alternatives to the original normalization scheme which increase the generalization capabilities of Slot Attention to varying slot and object counts, resulting in performance gains on the task of unsupervised image segmentation. The newly proposed normalizations represent minimal and easy to implement modifications of the usual Slot Attention module, changing the value aggregation mechanism from a weighted mean operation to a scaled weighted sum operation.

Related papers

• Slot Attention with Re-Initialization and Self-Distillation [22.024377849671033]
  We propose Slot Attention with re-Initialization and self-Distillation (DIAS) for object discovery and recognition.<n>DIAS achieves state-of-the-art on OCL tasks like object discovery and recognition, while also improving advanced visual prediction and reasoning.
  arXiv  Detail & Related papers  (2025-07-31T17:41:18Z)
• Adaptive Slot Attention: Object Discovery with Dynamic Slot Number [64.45419820717754]
  A major drawback of most object-centric models, including slot attention, is their reliance on predefining the number of slots. Within this framework, we introduce an adaptive slot attention (AdaSlot) mechanism that dynamically determines the optimal number of slots. Our framework, tested extensively on object discovery tasks with various datasets, shows performance matching or exceeding top fixed-slot models.
  arXiv  Detail & Related papers  (2024-06-13T14:55:11Z)
• Prompt-Driven Dynamic Object-Centric Learning for Single Domain Generalization [61.64304227831361]
  Single-domain generalization aims to learn a model from single source domain data to achieve generalized performance on other unseen target domains. We propose a dynamic object-centric perception network based on prompt learning, aiming to adapt to the variations in image complexity.
  arXiv  Detail & Related papers  (2024-02-28T16:16:51Z)
• Spatial Structure Constraints for Weakly Supervised Semantic Segmentation [100.0316479167605]
  A class activation map (CAM) can only locate the most discriminative part of objects. We propose spatial structure constraints (SSC) for weakly supervised semantic segmentation to alleviate the unwanted object over-activation of attention expansion. Our approach achieves 72.7% and 47.0% mIoU on the PASCAL VOC 2012 and COCO datasets, respectively.
  arXiv  Detail & Related papers  (2024-01-20T05:25:25Z)
• Interpreting and Improving Attention From the Perspective of Large Kernel Convolution [51.06461246235176]
  We introduce Large Kernel Convolutional Attention (LKCA), a novel formulation that reinterprets attention operations as a single large- Kernel convolution. LKCA achieves competitive performance across various visual tasks, particularly in data-constrained settings.
  arXiv  Detail & Related papers  (2024-01-11T08:40:35Z)
• Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentation [76.68301884987348]
  We propose a simple yet effective approach for self-supervised video object segmentation (VOS) Our key insight is that the inherent structural dependencies present in DINO-pretrained Transformers can be leveraged to establish robust-temporal segmentation correspondences in videos. Our method demonstrates state-of-the-art performance across multiple unsupervised VOS benchmarks and excels in complex real-world multi-object video segmentation tasks.
  arXiv  Detail & Related papers  (2023-11-29T18:47:17Z)
• Top-Down Visual Attention from Analysis by Synthesis [87.47527557366593]
  We consider top-down attention from a classic Analysis-by-Synthesis (AbS) perspective of vision. We propose Analysis-by-Synthesis Vision Transformer (AbSViT), which is a top-down modulated ViT model that variationally approximates AbS, and controllable achieves top-down attention.
  arXiv  Detail & Related papers  (2023-03-23T05:17:05Z)
• Guided Slot Attention for Unsupervised Video Object Segmentation [16.69412563413671]
  We propose a guided slot attention network to reinforce spatial structural information and obtain better foreground--background separation. The proposed model achieves state-of-the-art performance on two popular datasets.
  arXiv  Detail & Related papers  (2023-03-15T02:08:20Z)
• Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames [18.84636947819183]
  Slot-based neural networks that learn about objects in a self-supervised manner have made exciting progress. We present a simple yet highly effective method for incorporating spatial symmetries via slot-centric reference frames. We evaluate our method on a range of synthetic object discovery benchmarks namely CLEVR, Tetrominoes, CLEVR, Objects Room and MultiShapeNet.
  arXiv  Detail & Related papers  (2023-02-09T23:25:28Z)
• Self-Supervised Video Object Segmentation via Cutout Prediction and Tagging [117.73967303377381]
  We propose a novel self-supervised Video Object (VOS) approach that strives to achieve better object-background discriminability. Our approach is based on a discriminative learning loss formulation that takes into account both object and background information. Our proposed approach, CT-VOS, achieves state-of-the-art results on two challenging benchmarks: DAVIS-2017 and Youtube-VOS.
  arXiv  Detail & Related papers  (2022-04-22T17:53:27Z)
• Recurrent Attention Models with Object-centric Capsule Representation for Multi-object Recognition [4.143091738981101]
  We show that an object-centric hidden representation in an encoder-decoder model with iterative glimpse attention yields effective integration of attention and recognition. Our work takes a step toward a general architecture for how to integrate recurrent object-centric representation into the planning of attentional glimpses.
  arXiv  Detail & Related papers  (2021-10-11T01:41:21Z)
• Object-Centric Learning with Slot Attention [43.684193749891506]
  We present the Slot Attention module, an architectural component that interfaces with perceptual representations. Slot Attention produces task-dependent abstract representations which we call slots. We empirically demonstrate that Slot Attention can extract object-centric representations that enable generalization to unseen compositions.
  arXiv  Detail & Related papers  (2020-06-26T15:31:57Z)

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.