Models prone to spurious correlations in training data often produce brittle
predictions and introduce unintended biases. Addressing this challenge
typically involves methods relying on prior knowledge and group annotation to
remove spurious correlations, which may not be readily available in many
applications. In this paper, we establish a novel connection between
unsupervised object-centric learning and mitigation of spurious correlations.
Instead of directly inferring sub-groups with varying correlations with labels,
our approach focuses on discovering concepts: discrete ideas that are shared
across input samples. Leveraging existing object-centric representation
learning, we introduce CoBalT: a concept balancing technique that effectively
mitigates spurious correlations without requiring human labeling of subgroups.
Evaluation across the Waterbirds, CelebA and ImageNet-9 benchmark datasets for
subpopulation shifts demonstrate superior or competitive performance compared
state-of-the-art baselines, without the need for group annotation.

我们提出了一种用于减轻虚假相关的概念平衡技术，通过利用现有的物体为中心的表示学习方法，无需对子群进行人工标注，在水鸟、CelebA 和 ImageNet-9 基准数据集上进行评估并展示了优越或竞争性的性能。

无监督概念发现减轻虚假相关性

Unsupervised Concept Discovery Mitigates Spurious Correlations

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
this https URL .

非监督式物体中心学习中引入了两个新技术：一种基于注意力的自我训练方法，通过从解码器到编码器提取出优越的基于槽的注意力掩码来增强物体分割；一种创新的自回归变换器中的补丁顺序排列策略，加强了槽向量在重构中的作用。这些策略的有效性在实验证明了该方法明显优于以往的基于槽的自编码器方法，特别是在处理复杂的真实图像时。具体实现代码请参考此网址。

SPOT: 自身训练的基于补丁顺序置换的自回归 Transformer 的物体中心学习

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

Unsupervised object-centric learning methods allow the partitioning of scenes
into entities without additional localization information and are excellent
candidates for reducing the annotation burden of multiple-object tracking (MOT)
pipelines. Unfortunately, they lack two key properties: objects are often split
into parts and are not consistently tracked over time. In fact,
state-of-the-art models achieve pixel-level accuracy and temporal consistency
by relying on supervised object detection with additional ID labels for the
association through time. This paper proposes a video object-centric model for
MOT. It consists of an index-merge module that adapts the object-centric slots
into detection outputs and an object memory module that builds complete object
prototypes to handle occlusions. Benefited from object-centric learning, we
only require sparse detection labels (0%-6.25%) for object localization and
feature binding. Relying on our self-supervised
Expectation-Maximization-inspired loss for object association, our approach
requires no ID labels. Our experiments significantly narrow the gap between the
existing object-centric model and the fully supervised state-of-the-art and
outperform several unsupervised trackers.

该研究提出了一种视频基于物体为中心的模型，通过适应物体为中心的插槽以及构建完整物体原型来处理遮挡，仅需要稀疏的检测标签进行物体定位和特征绑定，无需 ID 标签，并通过自我监督的期望最大化损失函数实现物体关联，实验证明了该方法在物体为中心的学习领域的卓越性能。