Event cameras are novel bio-inspired sensors that capture motion dynamics with much higher temporal resolution than traditional cameras, since pixels react asynchronously to brightness changes. They are therefore better suited for tasks involving motion such as motion segmentation. However, training event-based networks still represents a difficult challenge, as obtaining ground truth is very expensive, error-prone and limited in frequency. In this article, we introduce EV-LayerSegNet, a self-supervised CNN for event-based motion segmentation. Inspired by a layered representation of the scene dynamics, we show that it is possible to learn affine optical flow and segmentation masks separately, and use them to deblur the input events. The deblurring quality is then measured and used as self-supervised learning loss. We train and test the network on a simulated dataset with only affine motion, achieving IoU and detection rate up to 71% and 87% respectively.
Self-supervised learning (SSL) for point cloud pre-training has become a cornerstone for many 3D vision tasks, enabling effective learning from large-scale unannotated data. At the scene level, existing SSL methods often incorporate volume rendering into the pre-training framework, using RGB-D images as reconstruction signals to facilitate cross-modal learning. This strategy promotes alignment between 2D and 3D modalities and enables the model to benefit from rich visual cues in the RGB-D inputs. However, these approaches are limited by their reliance on implicit scene representations and high memory demands. Furthermore, since their reconstruction objectives are applied only in 2D space, they often fail to capture underlying 3D geometric structures. To address these challenges, we propose Gaussian2Scene, a novel scene-level SSL framework that leverages the efficiency and explicit nature of 3D Gaussian Splatting (3DGS) for pre-training. The use of 3DGS not only alleviates the computational burden associated with volume rendering but also supports direct 3D scene reconstruction, thereby enhancing the geometric understanding of the backbone network. Our approach follows a progressive two-stage training strategy. In the first stage, a dual-branch masked autoencoder learns both 2D and 3D scene representations. In the second stage, we initialize training with reconstructed point clouds and further supervise learning using the geometric locations of Gaussian primitives and rendered RGB images. This process reinforces both geometric and cross-modal learning. We demonstrate the effectiveness of Gaussian2Scene across several downstream 3D object detection tasks, showing consistent improvements over existing pre-training methods.
Dense self-supervised learning has shown great promise for learning pixel- and patch-level representations, but extending it to videos remains challenging due to the complexity of motion dynamics. Existing approaches struggle as they rely on static augmentations that fail under object deformations, occlusions, and camera movement, leading to inconsistent feature learning over time. We propose a motion-guided self-supervised learning framework that clusters dense point tracks to learn spatiotemporally consistent representations. By leveraging an off-the-shelf point tracker, we extract long-range motion trajectories and optimize feature clustering through a momentum-encoder-based optimal transport mechanism. To ensure temporal coherence, we propagate cluster assignments along tracked points, enforcing feature consistency across views despite viewpoint changes. Integrating motion as an implicit supervisory signal, our method learns representations that generalize across frames, improving robustness in dynamic scenes and challenging occlusion scenarios. By initializing from strong image-pretrained models and leveraging video data for training, we improve state-of-the-art by 1% to 6% on six image and video datasets and four evaluation benchmarks. The implementation is publicly available at our GitHub repository: https://github.com/SMSD75/MoSiC/tree/main
State Space models (SSMs) such as PointMamba enable efficient feature extraction for point cloud self-supervised learning with linear complexity, outperforming Transformers in computational efficiency. However, existing PointMamba-based methods depend on complex token ordering and random masking, which disrupt spatial continuity and local semantic correlations. We propose ZigzagPointMamba to tackle these challenges. The core of our approach is a simple zigzag scan path that globally sequences point cloud tokens, enhancing spatial continuity by preserving the proximity of spatially adjacent point tokens. Nevertheless, random masking undermines local semantic modeling in self-supervised learning. To address this, we introduce a Semantic-Siamese Masking Strategy (SMS), which masks semantically similar tokens to facilitate reconstruction by integrating local features of original and similar tokens. This overcomes the dependence on isolated local features and enables robust global semantic modeling. Our pre-trained ZigzagPointMamba weights significantly improve downstream tasks, achieving a 1.59% mIoU gain on ShapeNetPart for part segmentation, a 0.4% higher accuracy on ModelNet40 for classification, and 0.19%, 1.22%, and 0.72% higher accuracies respectively for the classification tasks on the OBJ-BG, OBJ-ONLY, and PB-T50-RS subsets of ScanObjectNN.
The development of diffusion-based generative models over the past decade has largely proceeded independently of progress in representation learning. These diffusion models typically rely on regression-based objectives and generally lack explicit regularization. In this work, we propose \textit{Dispersive Loss}, a simple plug-and-play regularizer that effectively improves diffusion-based generative models. Our loss function encourages internal representations to disperse in the hidden space, analogous to contrastive self-supervised learning, with the key distinction that it requires no positive sample pairs and therefore does not interfere with the sampling process used for regression. Compared to the recent method of representation alignment (REPA), our approach is self-contained and minimalist, requiring no pre-training, no additional parameters, and no external data. We evaluate Dispersive Loss on the ImageNet dataset across a range of models and report consistent improvements over widely used and strong baselines. We hope our work will help bridge the gap between generative modeling and representation learning.
Speech technology systems struggle with many downstream tasks for child speech due to small training corpora and the difficulties that child speech pose. We apply a novel dataset, SpeechMaturity, to state-of-the-art transformer models to address a fundamental classification task: identifying child vocalizations. Unlike previous corpora, our dataset captures maximally ecologically-valid child vocalizations across an unprecedented sample, comprising children acquiring 25+ languages in the U.S., Bolivia, Vanuatu, Papua New Guinea, Solomon Islands, and France. The dataset contains 242,004 labeled vocalizations, magnitudes larger than previous work. Models were trained to distinguish between cry, laughter, mature (consonant+vowel), and immature speech (just consonant or vowel). Models trained on the dataset outperform state-of-the-art models trained on previous datasets, achieved classification accuracy comparable to humans, and were robust across rural and urban settings.
In the architectural design process, floorplan design is often a dynamic and iterative process. Architects progressively draw various parts of the floorplan according to their ideas and requirements, continuously adjusting and refining throughout the design process. Therefore, the ability to predict a complete floorplan from a partial one holds significant value in the design process. Such prediction can help architects quickly generate preliminary designs, improve design efficiency, and reduce the workload associated with repeated modifications. To address this need, we propose FloorplanMAE, a self-supervised learning framework for restoring incomplete floor plans into complete ones. First, we developed a floor plan reconstruction dataset, FloorplanNet, specifically trained on architectural floor plans. Secondly, we propose a floor plan reconstruction method based on Masked Autoencoders (MAE), which reconstructs missing parts by masking sections of the floor plan and training a lightweight Vision Transformer (ViT). We evaluated the reconstruction accuracy of FloorplanMAE and compared it with state-of-the-art benchmarks. Additionally, we validated the model using real sketches from the early stages of architectural design. Experimental results show that the FloorplanMAE model can generate high-quality complete floor plans from incomplete partial plans. This framework provides a scalable solution for floor plan generation, with broad application prospects.
Deep neural networks are vulnerable to backdoor attacks, where malicious behaviors are implanted during training. While existing defenses can effectively purify compromised models, they typically require labeled data or specific training procedures, making them difficult to apply beyond supervised learning settings. Notably, recent studies have shown successful backdoor attacks across various learning paradigms, highlighting a critical security concern. To address this gap, we propose Two-stage Symmetry Connectivity (TSC), a novel backdoor purification defense that operates independently of data format and requires only a small fraction of clean samples. Through theoretical analysis, we prove that by leveraging permutation invariance in neural networks and quadratic mode connectivity, TSC amplifies the loss on poisoned samples while maintaining bounded clean accuracy. Experiments demonstrate that TSC achieves robust performance comparable to state-of-the-art methods in supervised learning scenarios. Furthermore, TSC generalizes to self-supervised learning frameworks, such as SimCLR and CLIP, maintaining its strong defense capabilities. Our code is available at https://github.com/JiePeng104/TSC.
Heterogeneous Graph Neural Networks (HGNNs), have demonstrated excellent capabilities in processing heterogeneous information networks. Self-supervised learning on heterogeneous graphs, especially contrastive self-supervised strategy, shows great potential when there are no labels. However, this approach requires the use of carefully designed graph augmentation strategies and the selection of positive and negative samples. Determining the exact level of similarity between sample pairs is non-trivial.To solve this problem, we propose a novel self-supervised Heterogeneous graph neural network with Optimal Transport (HGOT) method which is designed to facilitate self-supervised learning for heterogeneous graphs without graph augmentation strategies. Different from traditional contrastive self-supervised learning, HGOT employs the optimal transport mechanism to relieve the laborious sampling process of positive and negative samples. Specifically, we design an aggregating view (central view) to integrate the semantic information contained in the views represented by different meta-paths (branch views). Then, we introduce an optimal transport plan to identify the transport relationship between the semantics contained in the branch view and the central view. This allows the optimal transport plan between graphs to align with the representations, forcing the encoder to learn node representations that are more similar to the graph space and of higher quality. Extensive experiments on four real-world datasets demonstrate that our proposed HGOT model can achieve state-of-the-art performance on various downstream tasks. In particular, in the node classification task, HGOT achieves an average of more than 6% improvement in accuracy compared with state-of-the-art methods.
Humans ponder before articulating complex sentence elements, enabling deeper cognitive processing through focused effort. In this work, we introduce this pondering process into language models by repeatedly invoking the forward process within a single token generation step. During pondering, instead of generating an actual token sampled from the prediction distribution, the model ponders by yielding a weighted sum of all token embeddings according to the predicted token distribution. The generated embedding is then fed back as input for another forward pass. We show that the model can learn to ponder in this way through self-supervised learning, without any human annotations. Our method is straightforward and can be seamlessly integrated with various existing language models. Experiments across three widely used open-source architectures-GPT-2, Pythia, and LLaMA-and extensive downstream task evaluations demonstrate the effectiveness and generality of our method. For language modeling tasks, pondering language models achieve performance comparable to vanilla models with twice the number of parameters. On 9 downstream benchmarks, our pondering-enhanced Pythia models significantly outperform the official Pythia models. Notably, pondering-enhanced Pythia-1B is comparable to TinyLlama-1.1B, which is trained on 10 times more data. The code is available at https://github.com/LUMIA-Group/PonderingLM.
Foundation models, a cornerstone of recent advancements in machine learning, have predominantly thrived on complete and well-structured data. Wearable sensor data frequently suffers from significant missingness, posing a substantial challenge for self-supervised learning (SSL) models that typically assume complete data inputs. This paper introduces the second generation of Large Sensor Model (LSM-2) with Adaptive and Inherited Masking (AIM), a novel SSL approach that learns robust representations directly from incomplete data without requiring explicit imputation. AIM's core novelty lies in its use of learnable mask tokens to model both existing ("inherited") and artificially introduced missingness, enabling it to robustly handle fragmented real-world data during inference. Pre-trained on an extensive dataset of 40M hours of day-long multimodal sensor data, our LSM-2 with AIM achieves the best performance across a diverse range of tasks, including classification, regression and generative modeling. Furthermore, LSM-2 with AIM exhibits superior scaling performance, and critically, maintains high performance even under targeted missingness scenarios, reflecting clinically coherent patterns, such as the diagnostic value of nighttime biosignals for hypertension prediction. This makes AIM a more reliable choice for real-world wearable data applications.
Session-based recommendation aims to predict intents of anonymous users based on limited behaviors. With the ability in alleviating data sparsity, contrastive learning is prevailing in the task. However, we spot that existing contrastive learning based methods still suffer from three obstacles: (1) they overlook item-level sparsity and primarily focus on session-level sparsity; (2) they typically augment sessions using item IDs like crop, mask and reorder, failing to ensure the semantic consistency of augmented views; (3) they treat all positive-negative signals equally, without considering their varying utility. To this end, we propose a novel multi-modal adaptive contrastive learning framework called MACL for session-based recommendation. In MACL, a multi-modal augmentation is devised to generate semantically consistent views at both item and session levels by leveraging item multi-modal features. Besides, we present an adaptive contrastive loss that distinguishes varying contributions of positive-negative signals to improve self-supervised learning. Extensive experiments on three real-world datasets demonstrate the superiority of MACL over state-of-the-art methods.
This paper addresses source tracing in synthetic speech-identifying generative systems behind manipulated audio via speaker recognition-inspired pipelines. While prior work focuses on spoofing detection, source tracing lacks robust solutions. We evaluate two approaches: classification-based and metric-learning. We tested our methods on the MLAADv5 benchmark using ResNet and self-supervised learning (SSL) backbones. The results show that ResNet achieves competitive performance with the metric learning approach, matching and even exceeding SSL-based systems. Our work demonstrates ResNet's viability for source tracing while underscoring the need to optimize SSL representations for this task. Our work bridges speaker recognition methodologies with audio forensic challenges, offering new directions for combating synthetic media manipulation.
Self-Supervised Learning (SSL) has demonstrated strong performance in speech processing, particularly in automatic speech recognition. In this paper, we explore an SSL pretraining framework that leverages masked language modeling with targets derived from a speech recognition model. We also present chunkwise attention with dynamic chunk size sampling during pretraining to enable both full-context and streaming fine-tuning. Our experiments examine scaling with respect to model size and the amount of data. Using our method, we train the GigaAM family of models, including a state-of-the-art model for Russian speech recognition that outperforms Whisper-large-v3 by 50%. We have released our foundation and ASR models, along with the inference code, under the MIT license as open-source resources to the research community. Available at https://github.com/salute-developers/gigaam.
The emergence of Mamba as an alternative to attention-based architectures has led to the development of Mamba-based self-supervised learning (SSL) pre-trained models (PTMs) for speech and audio processing. Recent studies suggest that these models achieve comparable or superior performance to state-of-the-art (SOTA) attention-based PTMs for speech emotion recognition (SER). Motivated by prior work demonstrating the benefits of PTM fusion across different speech processing tasks, we hypothesize that leveraging the complementary strengths of Mamba-based and attention-based PTMs will enhance SER performance beyond the fusion of homogenous attention-based PTMs. To this end, we introduce a novel framework, PARROT that integrates parallel branch fusion with Optimal Transport and Hadamard Product. Our approach achieves SOTA results against individual PTMs, homogeneous PTMs fusion, and baseline fusion techniques, thus, highlighting the potential of heterogeneous PTM fusion for SER.
Effective speech representations for spoken language models must balance semantic relevance with acoustic fidelity for high-quality reconstruction. However, existing approaches struggle to achieve both simultaneously. To address this, we introduce Hierarchical Acoustic and Semantic Representation Disentanglement (HASRD, pronounced `hazard'), a framework that factorizes self-supervised learning representations into discrete semantic and acoustic tokens. HASRD assigns the semantic representation to the first codebook, while encoding acoustic residuals in subsequent codebooks. This preserves ASR performance while achieving high-quality reconstruction. Additionally, we enhance HASRD's encoder efficiency, improving ASR performance without compromising reconstruction quality. Compared to SpeechTokenizer, HASRD achieves a 44% relative WER improvement, superior reconstruction quality, and 2x lower bitrate, demonstrating its effectiveness in disentangling acoustic and semantic information.
Contrastive learning is an essential method in self-supervised learning. It primarily employs a multi-branch strategy to compare latent representations obtained from different branches and train the encoder. In the case of multi-modal input, diverse modalities of the same object are fed into distinct branches. When using single-modal data, the same input undergoes various augmentations before being fed into different branches. However, all existing contrastive learning frameworks have so far only performed contrastive operations on the learned features at the final loss end, with no information exchange between different branches prior to this stage. In this paper, for point cloud unsupervised learning without the use of extra training data, we propose a Contrastive Cross-branch Attention-based framework for Point cloud data (termed PoCCA), to learn rich 3D point cloud representations. By introducing sub-branches, PoCCA allows information exchange between different branches before the loss end. Experimental results demonstrate that in the case of using no extra training data, the representations learned with our self-supervised model achieve state-of-the-art performances when used for downstream tasks on point clouds.
Physics-driven deep learning (PD-DL) models have proven to be a powerful approach for improved reconstruction of rapid MRI scans. In order to train these models in scenarios where fully-sampled reference data is unavailable, self-supervised learning has gained prominence. However, its application at high acceleration rates frequently introduces artifacts, compromising image fidelity. To mitigate this shortcoming, we propose a novel way to train PD-DL networks via carefully-designed perturbations. In particular, we enhance the k-space masking idea of conventional self-supervised learning with a novel consistency term that assesses the model's ability to accurately predict the added perturbations in a sparse domain, leading to more reliable and artifact-free reconstructions. The results obtained from the fastMRI knee and brain datasets show that the proposed training strategy effectively reduces aliasing artifacts and mitigates noise amplification at high acceleration rates, outperforming state-of-the-art self-supervised methods both visually and quantitatively.
In this work, we investigate the Meta PL unsupervised domain adaptation framework for Automatic Speech Recognition (ASR). We introduce a Multi-Stage Domain Adaptation pipeline (MSDA), a sample-efficient, two-stage adaptation approach that integrates self-supervised learning with semi-supervised techniques. MSDA is designed to enhance the robustness and generalization of ASR models, making them more adaptable to diverse conditions. It is particularly effective for low-resource languages like Greek and in weakly supervised scenarios where labeled data is scarce or noisy. Through extensive experiments, we demonstrate that Meta PL can be applied effectively to ASR tasks, achieving state-of-the-art results, significantly outperforming state-of-the-art methods, and providing more robust solutions for unsupervised domain adaptation in ASR. Our ablations highlight the necessity of utilizing a cascading approach when combining self-supervision with self-training.
Although speech emotion recognition (SER) has advanced significantly with deep learning, annotation remains a major hurdle. Human annotation is not only costly but also subject to inconsistencies annotators often have different preferences and may lack the necessary contextual knowledge, which can lead to varied and inaccurate labels. Meanwhile, Large Language Models (LLMs) have emerged as a scalable alternative for annotating text data. However, the potential of LLMs to perform emotional speech data annotation without human supervision has yet to be thoroughly investigated. To address these problems, we apply GPT-4o to annotate a multimodal dataset collected from the sitcom Friends, using only textual cues as inputs. By crafting structured text prompts, our methodology capitalizes on the knowledge GPT-4o has accumulated during its training, showcasing that it can generate accurate and contextually relevant annotations without direct access to multimodal inputs. Therefore, we propose MELT, a multimodal emotion dataset fully annotated by GPT-4o. We demonstrate the effectiveness of MELT by fine-tuning four self-supervised learning (SSL) backbones and assessing speech emotion recognition performance across emotion datasets. Additionally, our subjective experiments\' results demonstrate a consistence performance improvement on SER.