A fundamental aspect of the semantics of natural language is that novel meanings can be formed from the composition of previously known parts. Vision-language models (VLMs) have made significant progress in recent years, however, there is evidence that they are unable to perform this kind of composition. For example, given an image of a red cube and a blue cylinder, a VLM such as CLIP is likely to incorrectly label the image as a red cylinder or a blue cube, indicating it represents the image as a `bag-of-words' and fails to capture compositional semantics. Diffusion models have recently gained significant attention for their impressive generative abilities, and zero-shot classifiers based on diffusion models have been shown to perform competitively with CLIP in certain compositional tasks. In this work we explore whether the generative Diffusion Classifier has improved compositional generalisation abilities compared to discriminative models. We assess three models -- Diffusion Classifier, CLIP, and ViLT -- on their ability to bind objects with attributes and relations in both zero-shot learning (ZSL) and generalised zero-shot learning (GZSL) settings. Our results show that the Diffusion Classifier and ViLT perform well at concept binding tasks, but that all models struggle significantly with the relational GZSL task, underscoring the broader challenges VLMs face with relational reasoning. Analysis of CLIP embeddings suggests that the difficulty may stem from overly similar representations of relational concepts such as left and right. Code and dataset are available at: https://github.com/otmive/diffusion_classifier_clip

Automated segmentation of the fetal head in ultrasound images is critical for prenatal monitoring. However, achieving robust segmentation remains challenging due to the poor quality of ultrasound images and the lack of annotated data. Semi-supervised methods alleviate the lack of annotated data but struggle with the unique characteristics of fetal head ultrasound images, making it challenging to generate reliable pseudo-labels and enforce effective consistency regularization constraints. To address this issue, we propose a novel semi-supervised framework, ERSR, for fetal head ultrasound segmentation. Our framework consists of the dual-scoring adaptive filtering strategy, the ellipse-constrained pseudo-label refinement, and the symmetry-based multiple consistency regularization. The dual-scoring adaptive filtering strategy uses boundary consistency and contour regularity criteria to evaluate and filter teacher outputs. The ellipse-constrained pseudo-label refinement refines these filtered outputs by fitting least-squares ellipses, which strengthens pixels near the center of the fitted ellipse and suppresses noise simultaneously. The symmetry-based multiple consistency regularization enforces multi-level consistency across perturbed images, symmetric regions, and between original predictions and pseudo-labels, enabling the model to capture robust and stable shape representations. Our method achieves state-of-the-art performance on two benchmarks. On the HC18 dataset, it reaches Dice scores of 92.05% and 95.36% with 10% and 20% labeled data, respectively. On the PSFH dataset, the scores are 91.68% and 93.70% under the same settings.

Active feature acquisition (AFA) is an instance-adaptive paradigm in which, at test time, a policy sequentially chooses which features to acquire (at a cost) before predicting. Existing approaches either train reinforcement learning (RL) policies, which deal with a difficult MDP, or greedy policies that cannot account for the joint informativeness of features or require knowledge about the underlying data distribution. To overcome this, we propose Template-based AFA (TAFA), a non-greedy framework that learns a small library of feature templates--a set of features that are jointly informative--and uses this library of templates to guide the next feature acquisitions. Through identifying feature templates, the proposed framework not only significantly reduces the action space considered by the policy but also alleviates the need to estimate the underlying data distribution. Extensive experiments on synthetic and real-world datasets show that TAFA outperforms the existing state-of-the-art baselines while achieving lower overall acquisition cost and computation.

The ever-growing amount of sensor data from machines, smart devices, and the environment leads to an abundance of high-resolution, unannotated time series (TS). These recordings encode recognizable properties of latent states and transitions from physical phenomena that can be modelled as abstract processes. The unsupervised localization and identification of these states and their transitions is the task of time series state detection (TSSD). Current TSSD algorithms employ classical unsupervised learning techniques, to infer state membership directly from feature space. This limits their predictive power, compared to supervised learning methods, which can exploit additional label information. We introduce CLaP, a new, highly accurate and efficient algorithm for TSSD. It leverages the predictive power of time series classification for TSSD in an unsupervised setting by applying novel self-supervision techniques to detect whether data segments emerge from the same state. To this end, CLaP cross-validates a classifier with segment-labelled subsequences to quantify confusion between segments. It merges labels from segments with high confusion, representing the same latent state, if this leads to an increase in overall classification quality. We conducted an experimental evaluation using 405 TS from five benchmarks and found CLaP to be significantly more precise in detecting states than six state-of-the-art competitors. It achieves the best accuracy-runtime tradeoff and is scalable to large TS. We provide a Python implementation of CLaP, which can be deployed in TS analysis workflows.

Early efforts on leveraging self-supervised learning (SSL) to improve machine learning (ML) fairness has proven promising. However, such an approach has yet to be explored within a multimodal context. Prior work has shown that, within a multimodal setting, different modalities contain modality-unique information that can complement information of other modalities. Leveraging on this, we propose a novel subject-level loss function to learn fairer representations via the following three mechanisms, adapting the variance-invariance-covariance regularization (VICReg) method: (i) the variance term, which reduces reliance on the protected attribute as a trivial solution; (ii) the invariance term, which ensures consistent predictions for similar individuals; and (iii) the covariance term, which minimizes correlational dependence on the protected attribute. Consequently, our loss function, coined as FAIRWELL, aims to obtain subject-independent representations, enforcing fairness in multimodal prediction tasks. We evaluate our method on three challenging real-world heterogeneous healthcare datasets (i.e. D-Vlog, MIMIC and MODMA) which contain different modalities of varying length and different prediction tasks. Our findings indicate that our framework improves overall fairness performance with minimal reduction in classification performance and significantly improves on the performance-fairness Pareto frontier.

Class-incremental with repetition (CIR), where previously trained classes repeatedly introduced in future tasks, is a more realistic scenario than the traditional class incremental setup, which assumes that each task contains unseen classes. CIR assumes that we can easily access abundant unlabeled data from external sources, such as the Internet. Therefore, we propose two components that efficiently use the unlabeled data to ensure the high stability and the plasticity of models trained in CIR setup. First, we introduce multi-level knowledge distillation (MLKD) that distills knowledge from multiple previous models across multiple perspectives, including features and logits, so the model can maintain much various previous knowledge. Moreover, we implement dynamic self-supervised loss (SSL) to utilize the unlabeled data that accelerates the learning of new classes, while dynamic weighting of SSL keeps the focus of training to the primary task. Both of our proposed components significantly improve the performance in CIR setup, achieving 2nd place in the CVPR 5th CLVISION Challenge.

Self-Supervised Learning (SSL) surmises that inputs and pairwise positive relationships are enough to learn meaningful representations.

The recently proposed FixMatch achieved state-of-the-art results on most semi-supervised learning (SSL) benchmarks.

What is it about human brains that allows us to reason symbolically whereas most other animals cannot? There is evidence that dynamic binding, the ability to combine neurons into groups on the fly, is necessary for symbolic thought, but there is also evidence that it is not sufficient. We propose that two kinds of hierarchical integration (integration of multiple role-bindings into multiplace predicates, and integration of multiple correspondences into structure mappings) are minimal requirements, on top of basic dynamic binding, to realize symbolic thought. We tested this hypothesis in a systematic collection of 17 simulations that explored the ability of cognitive architectures with and without the capacity for multi-place predicates and structure mapping to perform various kinds of tasks. The simulations were as generic as possible, in that no task could be performed based on any diagnostic features, depending instead on the capacity for multi-place predicates and structure mapping. The results are consistent with the hypothesis that, along with dynamic binding, multi-place predicates and structure mapping are minimal requirements for basic symbolic thought. These results inform our understanding of how human brains give rise to symbolic thought and speak to the differences between biological intelligence, which tends to generalize broadly from very few training examples, and modern approaches to machine learning, which typically require millions or billions of training examples. The results we report also have important implications for bio-inspired artificial intelligence.

The automation of robotic tasks requires high precision and adaptability, particularly in force-based operations such as insertions. Traditional learning-based approaches either rely on static datasets, which limit their ability to generalize, or require frequent manual intervention to maintain good performances. As a result, ensuring long-term reliability without human supervision remains a significant challenge. To address this, we propose an adaptive self-supervised learning framework for insertion classification that continuously improves its precision over time. The framework operates in real-time, incrementally refining its classification decisions by integrating newly acquired force data. Unlike conventional methods, it does not rely on pre-collected datasets but instead evolves dynamically with each task execution. Through real-world experiments, we demonstrate how the system progressively reduces execution time while maintaining near-perfect precision as more samples are processed. This adaptability ensures long-term reliability in force-based robotic tasks while minimizing the need for manual intervention.