视听学习

Model-based imitation learning (MBIL) is a popular reinforcement learning method that improves sample efficiency on high-dimension input sources, such as images and videos. Following the convention of MBIL research, existing algorithms are highly deceptive by task-irrelevant information, especially moving distractors in videos. To tackle this problem, we propose a new algorithm - named Separated Model-based Adversarial Imitation Learning (SeMAIL) - decoupling the environment dynamics into two parts by task-relevant dependency, which is determined by agent actions, and training separately. In this way, the agent can imagine its trajectories and imitate the expert behavior efficiently in task-relevant state space. Our method achieves near-expert performance on various visual control tasks with complex observations and the more challenging tasks with different backgrounds from expert observations.

Estimating the effects of multi-dimensional treatments (i.e., joint treatment effects) is critical in many data-intensive domains, including genetics and drug evaluation. The main challenges for studying the joint treatment effects include the need for large sample sizes to explore different treatment combinations as well as potentially unsafe treatment interactions. In this paper, we develop machinery for estimating joint treatment effects by combining data from multiple experimental datasets. In particular, first, we develop new identification conditions for determining whether a joint treatment effect can be computed in terms of multiple interventional distributions under various scenarios. Further, we develop estimators with statistically appealing properties, including consistency and robustness to model misspecification and slow convergence. Finally, we perform simulation studies, which corroborate the effectiveness of the proposed methods.

This paper investigates the dynamics-inspired neuromorphic architecture for visual representation learning following Hamilton's principle. Our method converts weight-based neural structure to its dynamics-based form that consists of finite sub-models, whose mutual relations measured by computing path integrals amongst their dynamical states are equivalent to the typical neural weights. Based on the entropy reduction process derived from the Euler-Lagrange equations, the feedback signals interpreted as stress forces amongst sub-models push them to move. We first train a dynamics-based neural model from scratch and observe that this model outperforms traditional neural models on MNIST. We then convert several pre-trained neural structures into dynamics-based forms, followed by fine-tuning via entropy reduction to obtain the stabilized dynamical states. We observe consistent improvements in these transformed models over their weight-based counterparts on ImageNet and WebVision in terms of computational complexity, parameter size, testing accuracy, and robustness. Besides, we show the correlation between model performance and structural entropy, providing deeper insight into weight-free neuromorphic learning.

Decoding seen images from brain activities has been an absorbing field. However, the reconstructed images still suffer from low quality with existing studies. This can be because our visual system is not like a camera that ''remembers'' every pixel. Instead, only part of the information can be perceived with our selective attention, and the brain ''guesses'' the rest to form what we think we see. Most existing approaches ignored the brain completion mechanism. In this work, we propose to reconstruct seen images with both the visual perception and the brain completion process, and design a simple, yet effective visual decoding framework to achieve this goal. Specifically, we first construct a shared discrete representation space for both brain signals and images. Then, a novel self-supervised token-to-token inpainting network is designed to implement visual content completion by building context and prior knowledge about the visual objects from the discrete latent space. Our approach improved the quality of visual reconstruction significantly and achieved state-of-the-art.

With its inspirational roots in game-theory, path attribution framework stands out among the post-hoc model interpretation techniques due to its axiomatic nature. However, recent developments show that despite being axiomatic, path attribution methods can compute counter-intuitive feature attributions. Not only that, for deep visual models, the methods may also not conform to the original game-theoretic intuitions that are the basis of their axiomatic nature. To address these issues, we perform a systematic investigation of the path attribution framework. We first pinpoint the conditions in which the counter-intuitive attributions of deep visual models can be avoided under this framework. Then, we identify a mechanism of integrating the attributions over the paths such that they computationally conform to the original insights of game-theory. These insights are eventually combined into a method, which provides intuitive and reliable feature attributions. We also establish the findings empirically by evaluating the method on multiple datasets, models and evaluation metrics. Extensive experiments show a consistent quantitative and qualitative gain in the results over the baselines.

Addressing imbalanced or long-tailed data is a major challenge in visual recognition tasks due to disparities between training and testing distributions and issues with data noise. We propose the Wrapped Cauchy Distributed Angular Softmax (WCDAS), a novel softmax function that incorporates data-wise Gaussian-based kernels into the angular correlation between feature representations and classifier weights, effectively mitigating noise and sparse sampling concerns. The class-wise distribution of angular representation becomes a sum of these kernels. Our theoretical analysis reveals that the wrapped Cauchy distribution excels the Gaussian distribution in approximating mixed distributions. Additionally, WCDAS uses trainable concentration parameters to dynamically adjust the compactness and margin of each class. Empirical results confirm label-aware behavior in these parameters and demonstrate WCDAS's superiority over other state-of-the-art softmax-based methods in handling long-tailed visual recognition across multiple benchmark datasets. The code is public available.

The ability to accurately recognize, localize and separate sound sources is fundamental to any audio-visual perception task. Historically, these abilities were tackled separately, with several methods developed independently for each task. However, given the interconnected nature of source localization, separation, and recognition, independent models are likely to yield suboptimal performance as they fail to capture the interdependence between these tasks. To address this problem, we propose a unified audio-visual learning framework (dubbed OneAVM) that integrates audio and visual cues for joint localization, separation, and recognition. OneAVM comprises a shared audio-visual encoder and task-specific decoders trained with three objectives. The first objective aligns audio and visual representations through a localized audio-visual correspondence loss. The second tackles visual source separation using a traditional mix-and-separate framework. Finally, the third objective reinforces visual feature separation and localization by mixing images in pixel space and aligning their representations with those of all corresponding sound sources. Extensive experiments on MUSIC, VGG-Instruments, VGG-Music, and VGGSound datasets demonstrate the effectiveness of OneAVM for all three tasks, audio-visual source localization, separation, and nearest neighbor recognition, and empirically demonstrate a strong positive transfer between them.

Dense contrastive learning (DCL) has been recently explored for learning localized information for dense prediction tasks (e.g., detection and segmentation). It still suffers the difficulty of mining pixels/patches correspondence between two views. A simple way is inputting the same view twice and aligning the pixel/patch representation. However, it would reduce the variance of inputs, and hurts the performance. We propose a plug-in method PQCL (Positional Query for patch-level Contrastive Learning), which allows performing patch-level contrasts between two views with exact patch correspondence. Besides, by using positional queries, PQCL increases the variance of inputs, to enhance training. We apply PQCL to popular transformer-based CL frameworks (DINO and iBOT, and evaluate them on classification, detection and segmentation tasks, where our method obtains stable improvements, especially for dense tasks. It achieves new state-of-the-art in most settings. Code is available at https://github.com/Sherrylone/Query_Contrastive.

Geo-tagged images are publicly available in large quantities, whereas labels such as object classes are rather scarce and expensive to collect. Meanwhile, contrastive learning has achieved tremendous success in various natural image and language tasks with limited labeled data. However, existing methods fail to fully leverage geospatial information, which can be paramount to distinguishing objects that are visually similar. To directly leverage the abundant geospatial information associated with images in pre-training, fine-tuning, and inference stages, we present Contrastive Spatial Pre-Training (CSP), a self-supervised learning framework for geo-tagged images. We use a dual-encoder to separately encode the images and their corresponding geo-locations, and use contrastive objectives to learn effective location representations from images, which can be transferred to downstream supervised tasks such as image classification. Experiments show that CSP can improve model performance on both iNat2018 and fMoW datasets. Especially, on iNat2018, CSP significantly boosts the model performance with 10-34% relative improvement with various labeled training data sampling ratios.

Current fake audio detection algorithms have achieved promising performances on most datasets. However, their performance may be significantly degraded when dealing with audio of a different dataset. The orthogonal weight modification to overcome catastrophic forgetting does not consider the similarity of genuine audio across different datasets. To overcome this limitation, we propose a continual learning algorithm for fake audio detection to overcome catastrophic forgetting, called Regularized Adaptive Weight Modification (RAWM). When fine-tuning a detection network, our approach adaptively computes the direction of weight modification according to the ratio of genuine utterances and fake utterances. The adaptive modification direction ensures the network can effectively detect fake audio on the new dataset while preserving its knowledge of old model, thus mitigating catastrophic forgetting. In addition, genuine audio collected from quite different acoustic conditions may skew their feature distribution, so we introduce a regularization constraint to force the network to remember the old distribution in this regard. Our method can easily be generalized to related fields, like speech emotion recognition. We also evaluate our approach across multiple datasets and obtain a significant performance improvement on cross-dataset experiments.

We introduce a self-supervised learning (SSL) framework BEATs for general audio representation pre-training, where we optimize an acoustic tokenizer and an audio SSL model by iterations. Unlike the previous audio SSL models that employ reconstruction loss for pre-training, our audio SSL model is trained with the discrete label prediction task, where the labels are generated by a semantic-rich acoustic tokenizer. We propose an iterative pipeline to jointly optimize the tokenizer and the pre-trained model, aiming to abstract high-level semantics and discard the redundant details for audio. The experimental results demonstrate our acoustic tokenizers can generate discrete labels with rich audio semantics and our audio SSL models achieve state-of-the-art (SOTA) results across various audio classification benchmarks, even outperforming previous models that use more training data and model parameters significantly. Specifically, we set a new SOTA mAP 50.6% on AudioSet-2M without using any external data, and 98.1% accuracy on ESC-50. The code and pre-trained models are available at https://aka.ms/beats.

Reconstructing natural images from fMRI recordings is a challenging task of great importance in neuroscience. The current architectures are bottlenecked because they fail to effectively capture the hierarchical processing of visual stimuli that takes place in the human brain. Motivated by that fact, we introduce a novel neural network architecture for the problem of neural decoding. Our architecture uses Hierarchical Variational Autoencoders (HVAEs) to learn meaningful representations of natural images and leverages their latent space hierarchy to learn voxel-to-image mappings. By mapping the early stages of the visual pathway to the first set of latent variables and the higher visual cortex areas to the deeper layers in the latent hierarchy, we are able to construct a latent variable neural decoding model that replicates the hierarchical visual information processing. Our model achieves better reconstructions compared to the state of the art and our ablation study indicates that the hierarchical structure of the latent space is responsible for that performance.