This paper explores feature prediction as a stand-alone objective for unsupervised learning from video and introduces V-JEPA, a collection of vision models trained solely using a feature prediction objective, without the use of pretrained image encoders, text, negative examples, reconstruction, or other sources of supervision. The models are trained on 2 million videos collected from public datasets and are evaluated on downstream image and video tasks. Our results show that learning by predicting video features leads to versatile visual representations that perform well on both motion and appearance-based tasks, without adaption of the model's parameters; e.g., using a frozen backbone. Our largest model, a ViT-H/16 trained only on videos, obtains 81.9% on Kinetics-400, 72.2% on Something-Something-v2, and 77.9% on ImageNet1K.

A heterogeneous micro aerial vehicles (MAV) swarm consists of resource-intensive but expensive advanced MAVs (AMAVs) and resource-limited but cost-effective basic MAVs (BMAVs), offering opportunities in diverse fields. Accurate and real-time localization is crucial for MAV swarms, but current practices lack a low-cost, high-precision, and real-time solution, especially for lightweight BMAVs. We find an opportunity to accomplish the task by transforming AMAVs into mobile localization infrastructures for BMAVs. However, turning this insight into a practical system is non-trivial due to challenges in location estimation with BMAVs' unknown and diverse localization errors and resource allocation of AMAVs given coupled influential factors. This study proposes TransformLoc, a new framework that transforms AMAVs into mobile localization infrastructures, specifically designed for low-cost and resource-constrained BMAVs. We first design an error-aware joint location estimation model to perform intermittent joint location estimation for BMAVs and then design a proximity-driven adaptive grouping-scheduling strategy to allocate resources of AMAVs dynamically. TransformLoc achieves a collaborative, adaptive, and cost-effective localization system suitable for large-scale heterogeneous MAV swarms. We implement TransformLoc on industrial drones and validate its performance. Results show that TransformLoc outperforms baselines including SOTA up to 68\% in localization performance, motivating up to 60\% navigation success rate improvement.

In this study, we examine the representation learning abilities of Denoising Diffusion Models (DDM) that were originally purposed for image generation. Our philosophy is to deconstruct a DDM, gradually transforming it into a classical Denoising Autoencoder (DAE). This deconstructive procedure allows us to explore how various components of modern DDMs influence self-supervised representation learning. We observe that only a very few modern components are critical for learning good representations, while many others are nonessential. Our study ultimately arrives at an approach that is highly simplified and to a large extent resembles a classical DAE. We hope our study will rekindle interest in a family of classical methods within the realm of modern self-supervised learning.

We reformulate the problem of supervised learning as learning to learn with two nested loops (i.e. The inner loop learns on each individual instance with self-supervision before final prediction. The outer loop learns the self-supervised task used by the inner loop, such that its final prediction improves. Our inner loop turns out to be equivalent to linear attention when the inner-loop learner is only a linear model, and to self-attention when it is a kernel estimator. For practical comparison with linear or self-attention layers, we replace each of them in a transformer with an inner loop, so our outer loop is equivalent to training the architecture. When each inner-loop learner is a neural network, our approach vastly outperforms transformers with linear attention on ImageNet from 224 224 raw pixels in both accuracy and FLOPs, while (regular) transformers cannot run. Test-time training (TTT) is an algorithmic framework for machine learning. The core idea is that each test instance defines its own learning problem, with its own target of generalization (Sun et al., 2020). Since the test instance comes without its label, TTT is performed with a self-supervised task such as reconstruction. Performance should improve on this particular instance for the selfsupervised task, because that is the objective optimized by TTT. But will such a process lead to better performance for the main task we actually care about? If improvement for a self-supervised task transfers to a given main task, we say the two tasks are aligned (Sun et al., 2020). In prior work, task alignment has been an art, combining ingenuity with trial and error (Gandelsman et al., 2022; Wang et al., 2023). Crucially, the amount of ingenuity in task design does not scale with more data and compute.

Wheeled robot navigation has been widely used in urban environments, but little research has been conducted on its navigation in wild vegetation. External sensors (LiDAR, camera etc.) are often used to construct point cloud map of the surrounding environment, however, the supporting rigid ground used for travelling cannot be detected due to the occlusion of vegetation. This often causes unsafe or not smooth path during planning process. To address the drawback, we propose the PE-RRT* algorithm, which effectively combines a novel support plane estimation method and sampling algorithm to generate real-time feasible and safe path in vegetation environments. In order to accurately estimate the support plane, we combine external perception and proprioception, and use Multivariate Gaussian Processe Regression (MV-GPR) to estimate the terrain at the sampling nodes. We build a physical experimental platform and conduct experiments in different outdoor environments. Experimental results show that our method has high safety, robustness and generalization.

Prior work has established test-time training (TTT) as a general framework to further improve a trained model at test time. Before making a prediction on each test instance, the model is trained on the same instance using a self-supervised task, such as image reconstruction with masked autoencoders. We extend TTT to the streaming setting, where multiple test instances - video frames in our case - arrive in temporal order. Our extension is online TTT: The current model is initialized from the previous model, then trained on the current frame and a small window of frames immediately before. Online TTT significantly outperforms the fixed-model baseline for four tasks, on three real-world datasets. The relative improvement is 45% and 66% for instance and panoptic segmentation. Surprisingly, online TTT also outperforms its offline variant that accesses more information, training on all frames from the entire test video regardless of temporal order. This differs from previous findings using synthetic videos. We conceptualize locality as the advantage of online over offline TTT. We analyze the role of locality with ablations and a theory based on bias-variance trade-off.

Modeling spatial relationship in the data remains critical across many different tasks, such as image classification, semantic segmentation and protein structure understanding. Previous works often use a unified solution like relative positional encoding. However, there exists different kinds of spatial relations, including short-range, medium-range and long-range relations, and modeling them separately can better capture the focus of different tasks on the multi-range relations (e.g., short-range relations can be important in instance segmentation, while long-range relations should be upweighted for semantic segmentation). In this work, we introduce the EurNet for Efficient multi-range relational modeling. EurNet constructs the multi-relational graph, where each type of edge corresponds to short-, medium- or long-range spatial interactions. In the constructed graph, EurNet adopts a novel modeling layer, called gated relational message passing (GRMP), to propagate multi-relational information across the data. GRMP captures multiple relations within the data with little extra computational cost. We study EurNets in two important domains for image and protein structure modeling. Extensive experiments on ImageNet classification, COCO object detection and ADE20K semantic segmentation verify the gains of EurNet over the previous SoTA FocalNet. On the EC and GO protein function prediction benchmarks, EurNet consistently surpasses the previous SoTA GearNet. Our results demonstrate the strength of EurNets on modeling spatial multi-relational data from various domains. The implementations of EurNet for image modeling are available at https://github.com/hirl-team/EurNet-Image . The implementations for other applied domains/tasks will be released soon.

Self-supervised learning recently emerges as a promising direction to learn representations without manual labels. While contrastive learning (Oord et al., 2018; Tian et al., 2019; Bachman et al., 2019; He et al., 2020; Chen et al., 2020a) minimizes the distance of representation between positive pairs, and maximizes such distances between negative pairs, recently, non-contrastive self-supervised learning (abbreviated as nc-SSL) is able to learn nontrivial representation with only positive pairs, using an extra predictor and a stop-gradient operation. Furthermore, the learned representation shows comparable (or even better) performance for downstream tasks (e.g., image classification) (Grill et al., 2020; Chen & He, 2020). This brings about two fundamental questions: (1) why the learned representation does not collapse to trivial (i.e., constant) solutions, and (2) without negative pairs, what representation nc-SSL learns from the training and how the learned representation reduces the sample complexity in downstream tasks. While many theoretical results on contrastive SSL (Arora et al., 2019; Lee et al., 2020; Tosh et al., 2020; Wen & Li, 2021) do exist, similar study on nc-SSL has been very rare. As one of the first work towards this direction, Tian et al. (2021) show that while the global optimum of the non-contrastive loss is indeed a trivial one, following gradient direction in nc-SSL, one can find a local optimum that admits a nontrivial representation. Based on their theoretical findings on gradient-based methods, they proposed a new approach, DirectPred, that directly sets the predictor using the eigen-decomposition of the correlation matrix of input before the predictor, rather than updating it with gradient methods. As a method for nc-SSL, DirectPred shows comparable or better performance in multiple datasets, including CIFAR-10 (Krizhevsky et al., 2009), STL-10 (Coates et al., 2011) and ImageNet (Deng et al., 2009), compared to BYOL (Grill et al., 2020) and SimSiam (Chen & He, 2020) that optimize the predictor using gradient descent.

Contrastive approaches to self-supervised learning (SSL) learn representations by minimizing the distance between two augmented views of the same data point (positive pairs) and maximizing the same from different data points (negative pairs). However, recent approaches like BYOL and SimSiam, show remarkable performance {\it without} negative pairs, raising a fundamental theoretical question: how can SSL with only positive pairs avoid representational collapse? We study the nonlinear learning dynamics of non-contrastive SSL in simple linear networks. Our analysis yields conceptual insights into how non-contrastive SSL methods learn, how they avoid representational collapse, and how multiple factors, like predictor networks, stop-gradients, exponential moving averages, and weight decay all come into play. Our simple theory recapitulates the results of real-world ablation studies in both STL-10 and ImageNet. Furthermore, motivated by our theory we propose a novel approach that \emph{directly} sets the predictor based on the statistics of its inputs. In the case of linear predictors, our approach outperforms gradient training of the predictor by $5\%$ and on ImageNet it performs comparably with more complex two-layer non-linear predictors that employ BatchNorm. Code is released in https://github.com/facebookresearch/luckmatters/tree/master/ssl.

We propose a novel theoretical framework to understand self-supervised learning methods that employ dual pairs of deep ReLU networks (e.g., SimCLR, BYOL). First, we prove that in each SGD update of SimCLR with various loss functions (simple contrastive loss, soft Triplet loss and InfoNCE loss), the weights at each layer are updated by a covariance operator that specifically amplifies initial random selectivities that vary across data samples but survive averages over data augmentations. We show this leads to the emergence of hierarchical features, if the input data are generated from a hierarchical latent tree model. With the same framework, we also show analytically that in BYOL, the combination of Batch-Norm and a predictor network creates an implicit contrastive term, acting as an approximate covariance operator. Additionally, for linear architectures we derive exact solutions for BYOL that provide conceptual insights into how BYOL can learn useful non-collapsed representations without any contrastive terms that separate negative pairs. Extensive ablation studies justify our theoretical findings. Unlike supervised learning (SL) that deals with labeled data, SSL learns meaningful structures from randomly initialized networks without human-provided labels. In this paper, we propose a systematic theoretical analysis of SSL with deep ReLU networks. Our analysis imposes no parametric assumptions on the input data distribution and is applicable to stateof-the-art SSL methods that typically involve two parallel (or dual) deep ReLU networks during training (e.g., SimCLR (Chen et al., 2020a), BYOL (Grill et al., 2020), etc). We do so by developing an analogy between SSL and a theoretical framework for analyzing supervised learning, namely the student-teacher setting (Tian, 2020; Allen-Zhu and Li, 2020; Lampinen and Ganguli, 2018; Saad and Solla, 1996), which also employs a pair of dual networks.