Predictive coding has emerged as a prominent model of how the brain learns through predictions, anticipating the importance accorded to predictive learning in recent AI architectures such as transformers. Here we propose a new framework for predictive coding called active predictive coding which can learn hierarchical world models and solve two radically different open problems in AI: (1) how do we learn compositional representations, e.g., part-whole hierarchies, for equivariant vision? and (2) how do we solve large-scale planning problems, which are hard for traditional reinforcement learning, by composing complex action sequences from primitive policies? Our approach exploits hypernetworks, self-supervised learning and reinforcement learning to learn hierarchical world models that combine task-invariant state transition networks and task-dependent policy networks at multiple abstraction levels. We demonstrate the viability of our approach on a variety of vision datasets (MNIST, FashionMNIST, Omniglot) as well as on a scalable hierarchical planning problem. Our results represent, to our knowledge, the first demonstration of a unified solution to the part-whole learning problem posed by Hinton, the nested reference frames problem posed by Hawkins, and the integrated state-action hierarchy learning problem in reinforcement learning.
Pre-trained speech Transformers have facilitated great success across various speech processing tasks. However, fine-tuning these encoders for downstream tasks require sufficiently large training data to converge or to achieve state-of-the-art. In text domain this has been partly attributed to sub-optimality of the representation space in pre-trained Transformers. In this work, we take a sober look into pre-trained speech encoders and rewire their representation space without requiring any task-specific labels. Our method utilises neutrally synthesised version of audio inputs along with frame masking to construct positive pairs for contrastive self-supervised learning. When used for augmenting the wav2vec 2 encoder, we observe consistent improvement of isotropy in the representation space. Our experiments on 6 speech processing tasks, exhibit a significant convergence speedup during task fine-tuning as well as consistent task improvement, specially in low-resource settings.
Video corpus moment retrieval (VCMR) is the task to retrieve the most relevant video moment from a large video corpus using a natural language query. For narrative videos, e.g., dramas or movies, the holistic understanding of temporal dynamics and multimodal reasoning is crucial. Previous works have shown promising results; however, they relied on the expensive query annotations for VCMR, i.e., the corresponding moment intervals. To overcome this problem, we propose a self-supervised learning framework: Modal-specific Pseudo Query Generation Network (MPGN). First, MPGN selects candidate temporal moments via subtitle-based moment sampling. Then, it generates pseudo queries exploiting both visual and textual information from the selected temporal moments. Through the multimodal information in the pseudo queries, we show that MPGN successfully learns to localize the video corpus moment without any explicit annotation. We validate the effectiveness of MPGN on the TVR dataset, showing competitive results compared with both supervised models and unsupervised setting models.
This paper introduces a structured, adaptive-length deep representation called Neural Eigenmap. Unlike prior spectral methods such as Laplacian Eigenmap that operate in a nonparametric manner, Neural Eigenmap leverages NeuralEF to parametrically model eigenfunctions using a neural network. We show that, when the eigenfunction is derived from positive relations in a data augmentation setup, applying NeuralEF results in an objective function that resembles those of popular self-supervised learning methods, with an additional symmetry-breaking property that leads to \emph{structured} representations where features are ordered by importance. We demonstrate using such representations as adaptive-length codes in image retrieval systems. By truncation according to feature importance, our method requires up to $16\times$ shorter representation length than leading self-supervised learning ones to achieve similar retrieval performance. We further apply our method to graph data and report strong results on a node representation learning benchmark with more than one million nodes.
Model-based control requires an accurate model of the system dynamics for precisely and safely controlling the robot in complex and dynamic environments. Moreover, in the presence of variations in the operating conditions, the model should be continuously refined to compensate for dynamics changes. In this paper, we present a self-supervised learning approach that actively models the dynamics of nonlinear robotic systems. We combine offline learning from past experience and online learning from current robot interaction with the unknown environment. These two ingredients enable a highly sample-efficient and adaptive learning process, capable of accurately inferring model dynamics in real-time even in operating regimes that greatly differ from the training distribution. Moreover, we design an uncertainty-aware model predictive controller that is heuristically conditioned to the aleatoric (data) uncertainty of the learned dynamics. This controller actively chooses the optimal control actions that (i) optimize the control performance and (ii) improve the efficiency of online learning sample collection. We demonstrate the effectiveness of our method through a series of challenging real-world experiments using a quadrotor system. Our approach showcases high resilience and generalization capabilities by consistently adapting to unseen flight conditions, while it significantly outperforms classical and adaptive control baselines.
The exponential growth of Location-based Social Networks (LBSNs) has greatly stimulated the demand for precise location-based recommendation services. Next Point-of-Interest (POI) recommendation, which aims to provide personalised POI suggestions for users based on their visiting histories, has become a prominent component in location-based e-commerce. Recent POI recommenders mainly employ self-attention mechanism or graph neural networks to model complex high-order POI-wise interactions. However, most of them are merely trained on the historical check-in data in a standard supervised learning manner, which fail to fully explore each user's multi-faceted preferences, and suffer from data scarcity and long-tailed POI distribution, resulting in sub-optimal performance. To this end, we propose a Self-s}upervised Graph-enhanced POI Recommender (S2GRec) for next POI recommendation. In particular, we devise a novel Graph-enhanced Self-attentive layer to incorporate the collaborative signals from both global transition graph and local trajectory graphs to uncover the transitional dependencies among POIs and capture a user's temporal interests. In order to counteract the scarcity and incompleteness of POI check-ins, we propose a novel self-supervised learning paradigm in \ssgrec, where the trajectory representations are contrastively learned from two augmented views on geolocations and temporal transitions. Extensive experiments are conducted on three real-world LBSN datasets, demonstrating the effectiveness of our model against state-of-the-art methods.
Deep learning has led to remarkable advances in computer vision. Even so, today's best models are brittle when presented with variations that differ even slightly from those seen during training. Minor shifts in the pose, color, or illumination of an object can lead to catastrophic misclassifications. State-of-the art models struggle to understand how a set of variations can affect different objects. We propose a framework for instilling a notion of how objects vary in more realistic settings. Our approach applies the formalism of Lie groups to capture continuous transformations to improve models' robustness to distributional shifts. We apply our framework on top of state-of-the-art self-supervised learning (SSL) models, finding that explicitly modeling transformations with Lie groups leads to substantial performance gains of greater than 10% for MAE on both known instances seen in typical poses now presented in new poses, and on unknown instances in any pose. We also apply our approach to ImageNet, finding that the Lie operator improves performance by almost 4%. These results demonstrate the promise of learning transformations to improve model robustness.
This article presents Holistically-Attracted Wireframe Parsing (HAWP), a method for geometric analysis of 2D images containing wireframes formed by line segments and junctions. HAWP utilizes a parsimonious Holistic Attraction (HAT) field representation that encodes line segments using a closed-form 4D geometric vector field. The proposed HAWP consists of three sequential components empowered by end-to-end and HAT-driven designs: (1) generating a dense set of line segments from HAT fields and endpoint proposals from heatmaps, (2) binding the dense line segments to sparse endpoint proposals to produce initial wireframes, and (3) filtering false positive proposals through a novel endpoint-decoupled line-of-interest aligning (EPD LOIAlign) module that captures the co-occurrence between endpoint proposals and HAT fields for better verification. Thanks to our novel designs, HAWPv2 shows strong performance in fully supervised learning, while HAWPv3 excels in self-supervised learning, achieving superior repeatability scores and efficient training (24 GPU hours on a single GPU). Furthermore, HAWPv3 exhibits a promising potential for wireframe parsing in out-of-distribution images without providing ground truth labels of wireframes.
Amodal perception requires inferring the full shape of an object that is partially occluded. This task is particularly challenging on two levels: (1) it requires more information than what is contained in the instant retina or imaging sensor, (2) it is difficult to obtain enough well-annotated amodal labels for supervision. To this end, this paper develops a new framework of Self-supervised amodal Video object segmentation (SaVos). Our method efficiently leverages the visual information of video temporal sequences to infer the amodal mask of objects. The key intuition is that the occluded part of an object can be explained away if that part is visible in other frames, possibly deformed as long as the deformation can be reasonably learned. Accordingly, we derive a novel self-supervised learning paradigm that efficiently utilizes the visible object parts as the supervision to guide the training on videos. In addition to learning type prior to complete masks for known types, SaVos also learns the spatiotemporal prior, which is also useful for the amodal task and could generalize to unseen types. The proposed framework achieves the state-of-the-art performance on the synthetic amodal segmentation benchmark FISHBOWL and the real world benchmark KINS-Video-Car. Further, it lends itself well to being transferred to novel distributions using test-time adaptation, outperforming existing models even after the transfer to a new distribution.
Self-supervised learning (SSL) has become prevalent for learning representations in computer vision. Notably, SSL exploits contrastive learning to encourage visual representations to be invariant under various image transformations. The task of gaze estimation, on the other hand, demands not just invariance to various appearances but also equivariance to the geometric transformations. In this work, we propose a simple contrastive representation learning framework for gaze estimation, named Gaze Contrastive Learning (GazeCLR). GazeCLR exploits multi-view data to promote equivariance and relies on selected data augmentation techniques that do not alter gaze directions for invariance learning. Our experiments demonstrate the effectiveness of GazeCLR for several settings of the gaze estimation task. Particularly, our results show that GazeCLR improves the performance of cross-domain gaze estimation and yields as high as 17.2% relative improvement. Moreover, the GazeCLR framework is competitive with state-of-the-art representation learning methods for few-shot evaluation. The code and pre-trained models are available at https://github.com/jswati31/gazeclr.
Behaviour biometrics are being explored as a viable alternative to overcome the limitations of traditional authentication methods such as passwords and static biometrics. Also, they are being considered as a viable authentication method for IoT devices such as smart headsets with AR/VR capabilities, wearables, and erables, that do not have a large form factor or the ability to seamlessly interact with the user. Recent behavioural biometric solutions use deep learning models that require large amounts of annotated training data. Collecting such volumes of behaviour biometrics data raises privacy and usability concerns. To this end, we propose using SimSiam-based non-contrastive self-supervised learning to improve the label efficiency of behavioural biometric systems. The key idea is to use large volumes of unlabelled (and anonymised) data to build good feature extractors that can be subsequently used in supervised settings. Using two EEG datasets, we show that at lower amounts of labelled data, non-contrastive learning performs 4%-11% more than conventional methods such as supervised learning and data augmentation. We also show that, in general, self-supervised learning methods perform better than other baselines. Finally, through careful experimentation, we show various modifications that can be incorporated into the non-contrastive learning process to archive high performance.
In defense-related remote sensing applications, such as vehicle detection on satellite imagery, supervised learning requires a huge number of labeled examples to reach operational performances. Such data are challenging to obtain as it requires military experts, and some observables are intrinsically rare. This limited labeling capability, as well as the large number of unlabeled images available due to the growing number of sensors, make object detection on remote sensing imagery highly relevant for self-supervised learning. We study in-domain self-supervised representation learning for object detection on very high resolution optical satellite imagery, that is yet poorly explored. For the first time to our knowledge, we study the problem of label efficiency on this task. We use the large land use classification dataset Functional Map of the World to pretrain representations with an extension of the Momentum Contrast framework. We then investigate this model's transferability on a real-world task of fine-grained vehicle detection and classification on Preligens proprietary data, which is designed to be representative of an operational use case of strategic site surveillance. We show that our in-domain self-supervised learning model is competitive with ImageNet pretraining, and outperforms it in the low-label regime.
Recent self-supervised learning (SSL) models have proven to learn rich representations of speech, which can readily be utilized by diverse downstream tasks. To understand such utilities, various analyses have been done for speech SSL models to reveal which and how information is encoded in the learned representations. Although the scope of previous analyses is extensive in acoustic, phonetic, and semantic perspectives, the physical grounding by speech production has not yet received full attention. To bridge this gap, we conduct a comprehensive analysis to link speech representations to articulatory trajectories measured by electromagnetic articulography (EMA). Our analysis is based on a linear probing approach where we measure articulatory score as an average correlation of linear mapping to EMA. We analyze a set of SSL models selected from the leaderboard of the SUPERB benchmark and perform further layer-wise analyses on two most successful models, Wav2Vec 2.0 and HuBERT. Surprisingly, representations from the recent speech SSL models are highly correlated with EMA traces (best: r = 0.81), and only 5 minutes are sufficient to train a linear model with high performance (r = 0.77). Our findings suggest that SSL models learn to align closely with continuous articulations, and provide a novel insight into speech SSL.
The computer-assisted radiologic informative report is currently emerging in dental practice to facilitate dental care and reduce time consumption in manual panoramic radiographic interpretation. However, the amount of dental radiographs for training is very limited, particularly from the point of view of deep learning. This study aims to utilize recent self-supervised learning methods like SimMIM and UM-MAE to increase the model efficiency and understanding of the limited number of dental radiographs. We use the Swin Transformer for teeth numbering, detection of dental restorations, and instance segmentation tasks. To the best of our knowledge, this is the first study that applied self-supervised learning methods to Swin Transformer on dental panoramic radiographs. Our results show that the SimMIM method obtained the highest performance of 90.4% and 88.9% on detecting teeth and dental restorations and instance segmentation, respectively, increasing the average precision by 13.4 and 12.8 over the random initialization baseline. Moreover, we augment and correct the existing dataset of panoramic radiographs. The code and the dataset are available at https://github.com/AmaniHAlmalki/DentalMIM.
This work focuses on the apparent emotional reaction recognition (AERR) from the video-only input, conducted in a self-supervised fashion. The network is first pre-trained on different self-supervised pretext tasks and later fine-tuned on the downstream target task. Self-supervised learning facilitates the use of pre-trained architectures and larger datasets that might be deemed unfit for the target task and yet might be useful to learn informative representations and hence provide useful initializations for further fine-tuning on smaller more suitable data. Our presented contribution is two-fold: (1) an analysis of different state-of-the-art (SOTA) pretext tasks for the video-only apparent emotional reaction recognition architecture, and (2) an analysis of various combinations of the regression and classification losses that are likely to improve the performance further. Together these two contributions result in the current state-of-the-art performance for the video-only spontaneous apparent emotional reaction recognition with continuous annotations.
Although increasingly training-expensive, most self-supervised learning (SSL) models have repeatedly been trained from scratch but not fully utilized, since only a few SOTAs are employed for downstream tasks. In this work, we explore a sustainable SSL framework with two major challenges: i) learning a stronger new SSL model based on the existing pretrained SSL model, also called as "base" model, in a cost-friendly manner, ii) allowing the training of the new model to be compatible with various base models. We propose a Target-Enhanced Conditional (TEC) scheme which introduces two components to the existing mask-reconstruction based SSL. Firstly, we propose patch-relation enhanced targets which enhances the target given by base model and encourages the new model to learn semantic-relation knowledge from the base model by using incomplete inputs. This hardening and target-enhancing help the new model surpass the base model, since they enforce additional patch relation modeling to handle incomplete input. Secondly, we introduce a conditional adapter that adaptively adjusts new model prediction to align with the target of different base models. Extensive experimental results show that our TEC scheme can accelerate the learning speed, and also improve SOTA SSL base models, e.g., MAE and iBOT, taking an explorative step towards sustainable SSL.
Self-supervised Learning (SSL) has been widely applied to learn image representations through exploiting unlabeled images. However, it has not been fully explored in the medical image analysis field. In this work, Saliency-guided Self-Supervised image Transformer (SSiT) is proposed for Diabetic Retinopathy (DR) grading from fundus images. We novelly introduce saliency maps into SSL, with a goal of guiding self-supervised pre-training with domain-specific prior knowledge. Specifically, two saliency-guided learning tasks are employed in SSiT: (1) Saliency-guided contrastive learning is conducted based on the momentum contrast, wherein fundus images' saliency maps are utilized to remove trivial patches from the input sequences of the momentum-updated key encoder. Thus, the key encoder is constrained to provide target representations focusing on salient regions, guiding the query encoder to capture salient features. (2) The query encoder is trained to predict the saliency segmentation, encouraging the preservation of fine-grained information in the learned representations. To assess our proposed method, four publicly-accessible fundus image datasets are adopted. One dataset is employed for pre-training, while the three others are used to evaluate the pre-trained models' performance on downstream DR grading. The proposed SSiT significantly outperforms other representative state-of-the-art SSL methods on all downstream datasets and under various evaluation settings. For example, SSiT achieves a Kappa score of 81.88% on the DDR dataset under fine-tuning evaluation, outperforming all other ViT-based SSL methods by at least 9.48%.
A mainstream type of current self-supervised learning methods pursues a general-purpose representation that can be well transferred to downstream tasks, typically by optimizing on a given pretext task such as instance discrimination. In this work, we argue that existing pretext tasks inevitably introduce biases into the learned representation, which in turn leads to biased transfer performance on various downstream tasks. To cope with this issue, we propose Maximum Entropy Coding (MEC), a more principled objective that explicitly optimizes on the structure of the representation, so that the learned representation is less biased and thus generalizes better to unseen downstream tasks. Inspired by the principle of maximum entropy in information theory, we hypothesize that a generalizable representation should be the one that admits the maximum entropy among all plausible representations. To make the objective end-to-end trainable, we propose to leverage the minimal coding length in lossy data coding as a computationally tractable surrogate for the entropy, and further derive a scalable reformulation of the objective that allows fast computation. Extensive experiments demonstrate that MEC learns a more generalizable representation than previous methods based on specific pretext tasks. It achieves state-of-the-art performance consistently on various downstream tasks, including not only ImageNet linear probe, but also semi-supervised classification, object detection, instance segmentation, and object tracking. Interestingly, we show that existing batch-wise and feature-wise self-supervised objectives could be seen equivalent to low-order approximations of MEC. Code and pre-trained models are available at https://github.com/xinliu20/MEC.
The recent progress in self-supervised learning has successfully combined Masked Image Modeling (MIM) with Siamese Networks, harnessing the strengths of both methodologies. Nonetheless, certain challenges persist when integrating conventional erase-based masking within Siamese ConvNets. Two primary concerns are: (1) The continuous data processing nature of ConvNets, which doesn't allow for the exclusion of non-informative masked regions, leading to reduced training efficiency compared to ViT architecture; (2) The misalignment between erase-based masking and the contrastive-based objective, distinguishing it from the MIM technique. To address these challenges, this work introduces a novel filling-based masking approach, termed \textbf{MixMask}. The proposed method replaces erased areas with content from a different image, effectively countering the information depletion seen in traditional masking methods. Additionally, we unveil an adaptive loss function that captures the semantics of the newly patched views, ensuring seamless integration within the architectural framework. We empirically validate the effectiveness of our approach through comprehensive experiments across various datasets and application scenarios. The findings underscore our framework's enhanced performance in areas such as linear probing, semi-supervised and supervised finetuning, object detection and segmentation. Notably, our method surpasses the MSCN, establishing MixMask as a more advantageous masking solution for Siamese ConvNets. Our code and models are publicly available at https://github.com/kirill-vish/MixMask.
Recently self supervised learning has seen explosive growth and use in variety of machine learning tasks because of its ability to avoid the cost of annotating large-scale datasets. This paper gives an overview for best self supervised learning approaches for multimodal learning. The presented approaches have been aggregated by extensive study of the literature and tackle the application of self supervised learning in different ways. The approaches discussed are cross modal generation, cross modal pretraining, cyclic translation, and generating unimodal labels in self supervised fashion.