On the Generalization and Causal Explanation in Self-Supervised Learning

Self-supervised learning (SSL) methods learn from unlabeled data and achieve high generalization performance on downstream tasks. However, they may also suffer from overfitting to their training data and lose the ability to adapt to new tasks. To investigate this phenomenon, we conduct experiments on various SSL methods and datasets and make two observations: (1) Overfitting occurs abruptly in later layers and epochs, while generalizing features are learned in early layers for all epochs; (2) Coding rate reduction can be used as an indicator to measure the degree of overfitting in SSL models. Based on these observations, we propose Undoing Memorization Mechanism (UMM), a plug-and-play method that mitigates overfitting of the pre-trained feature extractor by aligning the feature distributions of the early and the last layers to maximize the coding rate reduction of the last layer output. The learning process of UMM is a bi-level optimization process. We provide a causal analysis of UMM to explain how UMM can help the pre-trained feature extractor overcome overfitting and recover generalization. We also demonstrate that UMM significantly improves the generalization performance of SSL methods on various downstream tasks.

EHC-MM: Embodied Holistic Control for Mobile Manipulation

Mobile manipulation typically entails the base for mobility, the arm for accurate manipulation, and the camera for perception. It is necessary to follow the principle of Distant Mobility, Close Grasping(DMCG) in holistic control. We propose Embodied Holistic Control for Mobile Manipulation(EHC-MM) with the embodied function of sig(w): By formulating the DMCG principle as a Quadratic Programming (QP) problem, sig(w) dynamically balances the robot's emphasis between movement and manipulation with the consideration of the robot's state and environment. In addition, we propose the Monitor-Position-Based Servoing (MPBS) with sig(w), enabling the tracking of the target during the operation. This approach allows coordinated control between the robot's base, arm, and camera. Through extensive simulations and real-world experiments, our approach significantly improves both the success rate and efficiency of mobile manipulation tasks, achieving a 95.6% success rate in the real-world scenarios and a 52.8% increase in time efficiency.

On the Discriminability of Self-Supervised Representation Learning

Self-supervised learning (SSL) has recently achieved significant success in downstream visual tasks. However, a notable gap still exists between SSL and supervised learning (SL), especially in complex downstream tasks. In this paper, we show that the features learned by SSL methods suffer from the crowding problem, where features of different classes are not distinctly separated, and features within the same class exhibit large intra-class variance. In contrast, SL ensures a clear separation between classes. We analyze this phenomenon and conclude that SSL objectives do not constrain the relationships between different samples and their augmentations. Our theoretical analysis delves into how SSL objectives fail to enforce the necessary constraints between samples and their augmentations, leading to poor performance in complex tasks. We provide a theoretical framework showing that the performance gap between SSL and SL mainly stems from the inability of SSL methods to capture the aggregation of similar augmentations and the separation of dissimilar augmentations. To address this issue, we propose a learnable regulator called Dynamic Semantic Adjuster (DSA). DSA aggregates and separates samples in the feature space while being robust to outliers. Through extensive empirical evaluations on multiple benchmark datasets, we demonstrate the superiority of DSA in enhancing feature aggregation and separation, ultimately closing the performance gap between SSL and SL.

Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments

Learning policies for multi-entity systems in 3D environments is far more complicated against single-entity scenarios, due to the exponential expansion of the global state space as the number of entities increases. One potential solution of alleviating the exponential complexity is dividing the global space into independent local views that are invariant to transformations including translations and rotations. To this end, this paper proposes Subequivariant Hierarchical Neural Networks (SHNN) to facilitate multi-entity policy learning. In particular, SHNN first dynamically decouples the global space into local entity-level graphs via task assignment. Second, it leverages subequivariant message passing over the local entity-level graphs to devise local reference frames, remarkably compressing the representation redundancy, particularly in gravity-affected environments. Furthermore, to overcome the limitations of existing benchmarks in capturing the subtleties of multi-entity systems under the Euclidean symmetry, we propose the Multi-entity Benchmark (MEBEN), a new suite of environments tailored for exploring a wide range of multi-entity reinforcement learning. Extensive experiments demonstrate significant advancements of SHNN on the proposed benchmarks compared to existing methods. Comprehensive ablations are conducted to verify the indispensability of task assignment and subequivariance.

A Physical Model-Guided Framework for Underwater Image Enhancement and Depth Estimation

Due to the selective absorption and scattering of light by diverse aquatic media, underwater images usually suffer from various visual degradations. Existing underwater image enhancement (UIE) approaches that combine underwater physical imaging models with neural networks often fail to accurately estimate imaging model parameters such as depth and veiling light, resulting in poor performance in certain scenarios. To address this issue, we propose a physical model-guided framework for jointly training a Deep Degradation Model (DDM) with any advanced UIE model. DDM includes three well-designed sub-networks to accurately estimate various imaging parameters: a veiling light estimation sub-network, a factors estimation sub-network, and a depth estimation sub-network. Based on the estimated parameters and the underwater physical imaging model, we impose physical constraints on the enhancement process by modeling the relationship between underwater images and desired clean images, i.e., outputs of the UIE model. Moreover, while our framework is compatible with any UIE model, we design a simple yet effective fully convolutional UIE model, termed UIEConv. UIEConv utilizes both global and local features for image enhancement through a dual-branch structure. UIEConv trained within our framework achieves remarkable enhancement results across diverse underwater scenes. Furthermore, as a byproduct of UIE, the trained depth estimation sub-network enables accurate underwater scene depth estimation. Extensive experiments conducted in various real underwater imaging scenarios, including deep-sea environments with artificial light sources, validate the effectiveness of our framework and the UIEConv model.

Bidirectional-Reachable Hierarchical Reinforcement Learning with Mutually Responsive Policies

Hierarchical reinforcement learning (HRL) addresses complex long-horizon tasks by skillfully decomposing them into subgoals. Therefore, the effectiveness of HRL is greatly influenced by subgoal reachability. Typical HRL methods only consider subgoal reachability from the unilateral level, where a dominant level enforces compliance to the subordinate level. However, we observe that when the dominant level becomes trapped in local exploration or generates unattainable subgoals, the subordinate level is negatively affected and cannot follow the dominant level's actions. This can potentially make both levels stuck in local optima, ultimately hindering subsequent subgoal reachability. Allowing real-time bilateral information sharing and error correction would be a natural cure for this issue, which motivates us to propose a mutual response mechanism. Based on this, we propose the Bidirectional-reachable Hierarchical Policy Optimization (BrHPO)--a simple yet effective algorithm that also enjoys computation efficiency. Experiment results on a variety of long-horizon tasks showcase that BrHPO outperforms other state-of-the-art HRL baselines, coupled with a significantly higher exploration efficiency and robustness.

When Vision Meets Touch: A Contemporary Review for Visuotactile Sensors from the Signal Processing Perspective

Tactile sensors, which provide information about the physical properties of objects, are an essential component of robotic systems. The visuotactile sensing technology with the merits of high resolution and low cost has facilitated the development of robotics from environment exploration to dexterous operation. Over the years, several reviews on visuotactile sensors for robots have been presented, but few of them discussed the significance of signal processing methods to visuotactile sensors. Apart from ingenious hardware design, the full potential of the sensory system toward designated tasks can only be released with the appropriate signal processing methods. Therefore, this paper provides a comprehensive review of visuotactile sensors from the perspective of signal processing methods and outlooks possible future research directions for visuotactile sensors.

RoboGolf: Mastering Real-World Minigolf with a Reflective Multi-Modality Vision-Language Model

Minigolf, a game with countless court layouts, and complex ball motion, constitutes a compelling real-world testbed for the study of embodied intelligence. As it not only challenges spatial and kinodynamic reasoning but also requires reflective and corrective capacities to address erroneously designed courses. We introduce RoboGolf, a framework that perceives dual-camera visual inputs with nested VLM-empowered closed-loop control and reflective equilibrium loop. Extensive experiments demonstrate the effectiveness of RoboGolf on challenging minigolf courts including those that are impossible to finish.

Small Scale Data-Free Knowledge Distillation

Data-free knowledge distillation is able to utilize the knowledge learned by a large teacher network to augment the training of a smaller student network without accessing the original training data, avoiding privacy, security, and proprietary risks in real applications. In this line of research, existing methods typically follow an inversion-and-distillation paradigm in which a generative adversarial network on-the-fly trained with the guidance of the pre-trained teacher network is used to synthesize a large-scale sample set for knowledge distillation. In this paper, we reexamine this common data-free knowledge distillation paradigm, showing that there is considerable room to improve the overall training efficiency through a lens of ``small-scale inverted data for knowledge distillation". In light of three empirical observations indicating the importance of how to balance class distributions in terms of synthetic sample diversity and difficulty during both data inversion and distillation processes, we propose Small Scale Data-free Knowledge Distillation SSD-KD. In formulation, SSD-KD introduces a modulating function to balance synthetic samples and a priority sampling function to select proper samples, facilitated by a dynamic replay buffer and a reinforcement learning strategy. As a result, SSD-KD can perform distillation training conditioned on an extremely small scale of synthetic samples (e.g., 10X less than the original training data scale), making the overall training efficiency one or two orders of magnitude faster than many mainstream methods while retaining superior or competitive model performance, as demonstrated on popular image classification and semantic segmentation benchmarks. The code is available at https://github.com/OSVAI/SSD-KD.

OMPO: A Unified Framework for RL under Policy and Dynamics Shifts

Training reinforcement learning policies using environment interaction data collected from varying policies or dynamics presents a fundamental challenge. Existing works often overlook the distribution discrepancies induced by policy or dynamics shifts, or rely on specialized algorithms with task priors, thus often resulting in suboptimal policy performances and high learning variances. In this paper, we identify a unified strategy for online RL policy learning under diverse settings of policy and dynamics shifts: transition occupancy matching. In light of this, we introduce a surrogate policy learning objective by considering the transition occupancy discrepancies and then cast it into a tractable min-max optimization problem through dual reformulation. Our method, dubbed Occupancy-Matching Policy Optimization (OMPO), features a specialized actor-critic structure equipped with a distribution discriminator and a small-size local buffer. We conduct extensive experiments based on the OpenAI Gym, Meta-World, and Panda Robots environments, encompassing policy shifts under stationary and nonstationary dynamics, as well as domain adaption. The results demonstrate that OMPO outperforms the specialized baselines from different categories in all settings. We also find that OMPO exhibits particularly strong performance when combined with domain randomization, highlighting its potential in RL-based robotics applications