SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers

• URL: http://arxiv.org/abs/2312.00648v3
• Date: Fri, 5 Apr 2024 11:31:12 GMT
• Title: SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers
• Authors: Ioannis Kakogeorgiou, Spyros Gidaris, Konstantinos Karantzalos, Nikos Komodakis,
• Abstract summary: Unsupervised object-centric learning aims to decompose scenes into interpretable object entities, termed slots. Slot-based auto-encoders stand out as a prominent method for this task. This work introduces two novel techniques, which distills superior slot-based attention masks from the decoder to the encoder.
• Score: 13.173384346104802
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Unsupervised object-centric learning aims to decompose scenes into interpretable object entities, termed slots. Slot-based auto-encoders stand out as a prominent method for this task. Within them, crucial aspects include guiding the encoder to generate object-specific slots and ensuring the decoder utilizes them during reconstruction. This work introduces two novel techniques, (i) an attention-based self-training approach, which distills superior slot-based attention masks from the decoder to the encoder, enhancing object segmentation, and (ii) an innovative patch-order permutation strategy for autoregressive transformers that strengthens the role of slot vectors in reconstruction. The effectiveness of these strategies is showcased experimentally. The combined approach significantly surpasses prior slot-based autoencoder methods in unsupervised object segmentation, especially with complex real-world images. We provide the implementation code at https://github.com/gkakogeorgiou/spot .

Related papers

• A Revisit to the Decoder for Camouflaged Object Detection [34.886607866949845]
  Camouflaged object detection (COD) aims to generate a fine-grained segmentation map of camouflaged objects hidden in their background. We propose a novel architecture that augments the prevalent decoding strategy in COD with Enrich Decoder and Retouch Decoder.
  arXiv  Detail & Related papers  (2025-03-18T08:51:50Z)
• 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)
• Self-supervised Object-Centric Learning for Videos [39.02148880719576]
  We propose the first fully unsupervised method for segmenting multiple objects in real-world sequences. Our object-centric learning framework spatially binds objects to slots on each frame and then relates these slots across frames. Our method can successfully segment multiple instances of complex and high-variety classes in YouTube videos.
  arXiv  Detail & Related papers  (2023-10-10T18:03:41Z)
• Regress Before Construct: Regress Autoencoder for Point Cloud Self-supervised Learning [18.10704604275133]
  Masked Autoencoders (MAE) have demonstrated promising performance in self-supervised learning for 2D and 3D computer vision. We propose Point Regress AutoEncoder (Point-RAE), a new scheme for regressive autoencoders for point cloud self-supervised learning. Our approach is efficient during pre-training and generalizes well on various downstream tasks.
  arXiv  Detail & Related papers  (2023-09-25T17:23:33Z)
• Semantic-Constraint Matching Transformer for Weakly Supervised Object Localization [31.039698757869974]
  Weakly supervised object localization (WSOL) strives to learn to localize objects with only image-level supervision. Previous CNN-based methods suffer from partial activation issues, concentrating on the object's discriminative part instead of the entire entity scope. We propose a novel Semantic-Constraint Matching Network (SCMN) via a transformer to converge on the divergent activation.
  arXiv  Detail & Related papers  (2023-09-04T03:20:31Z)
• Object Discovery from Motion-Guided Tokens [50.988525184497334]
  We augment the auto-encoder representation learning framework with motion-guidance and mid-level feature tokenization. Our approach enables the emergence of interpretable object-specific mid-level features.
  arXiv  Detail & Related papers  (2023-03-27T19:14:00Z)
• Learning Explicit Object-Centric Representations with Vision Transformers [81.38804205212425]
  We build on the self-supervision task of masked autoencoding and explore its effectiveness for learning object-centric representations with transformers. We show that the model efficiently learns to decompose simple scenes as measured by segmentation metrics on several multi-object benchmarks.
  arXiv  Detail & Related papers  (2022-10-25T16:39:49Z)
• Self-Supervised Point Cloud Representation Learning with Occlusion Auto-Encoder [63.77257588569852]
  We present 3D Occlusion Auto-Encoder (3D-OAE) for learning representations for point clouds. Our key idea is to randomly occlude some local patches of the input point cloud and establish the supervision via recovering the occluded patches. In contrast with previous methods, our 3D-OAE can remove a large proportion of patches and predict them only with a small number of visible patches.
  arXiv  Detail & Related papers  (2022-03-26T14:06:29Z)
• Laneformer: Object-aware Row-Column Transformers for Lane Detection [96.62919884511287]
  Laneformer is a transformer-based architecture tailored for lane detection in autonomous driving. Inspired by recent advances of the transformer encoder-decoder architecture in various vision tasks, we move forwards to design a new end-to-end Laneformer architecture.
  arXiv  Detail & Related papers  (2022-03-18T10:14:35Z)
• Context Autoencoder for Self-Supervised Representation Learning [64.63908944426224]
  We pretrain an encoder by making predictions in the encoded representation space. The network is an encoder-regressor-decoder architecture. We demonstrate the effectiveness of our CAE through superior transfer performance in downstream tasks.
  arXiv  Detail & Related papers  (2022-02-07T09:33:45Z)
• Sparsity and Sentence Structure in Encoder-Decoder Attention of Summarization Systems [38.672160430296536]
  Transformer models have achieved state-of-the-art results in a wide range of NLP tasks including summarization. Previous work has focused on one important bottleneck, the quadratic self-attention mechanism in the encoder. This work focuses on the transformer's encoder-decoder attention mechanism.
  arXiv  Detail & Related papers  (2021-09-08T19:32:42Z)

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.