论文检索

Deep Learning · Theory

Kedar Karhadkar, Erin George, Michael Murray, Guido Montufar, Deanna Needell

The problem of benign overfitting asks whether it is possible for a model to perfectly fit noisy training data and still generalize well. We study benign overfitting in two-layer leaky ReLU networks trained with the hinge loss on a binary classification task. We consider input data which can be decomposed into the sum of a common signal and a random noise component, which lie on subspaces orthogonal to one another. We characterize conditions on the signal to noise ratio (SNR) of the model parameters giving rise to benign versus non-benign, or harmful, overfitting: in particular, if the SNR is high then benign overfitting occurs, conversely if the SNR is low then harmful overfitting occurs. We attribute both benign and non-benign overfitting to an approximate margin maximization property and show that leaky ReLU networks trained on hinge loss with gradient descent (GD) satisfy this property. In contrast to prior work we do not require the training data to be nearly orthogonal. Notably, for input dimension $d$ and training sample size $n$, while results in prior work require $d = \Omega(n^2 \log n)$, here we require only $d = \Omega(n)$.

Computer Vision

Fei Xie, Weijia Zhang, Zhongdao Wang, Chao Ma

Recent advancements in State Space Models, notably Mamba, have demonstrated superior performance over the dominant Transformer models, particularly in reducing the computational complexity from quadratic to linear. Yet, difficulties in adapting Mamba from language to vision tasks arise due to the distinct characteristics of visual data, such as the spatial locality and adjacency within images and large variations in information granularity across visual tokens. Existing vision Mamba approaches either flatten tokens into sequences in a raster scan fashion, which breaks the local adjacency of images, or manually partition tokens into windows, which limits their long-range modeling and generalization capabilities. To address these limitations, we present a new vision Mamba model, coined QuadMamba, that effectively captures local dependencies of varying granularities via quadtree-based image partition and scan. Concretely, our lightweight quadtree-based scan module learns to preserve the 2D locality of spatial regions within learned window quadrants. The module estimates the locality score of each token from their features, before adaptively partitioning tokens into window quadrants. An omnidirectional window shifting scheme is also introduced to capture more intact and informative features across different local regions. To make the discretized quadtree partition end-to-end trainable, we further devise a sequence masking strategy based on Gumbel-Softmax and its straight-through gradient estimator. Extensive experiments demonstrate that QuadMamba achieves state-of-the-art performance in various vision tasks, including image classification, object detection, instance segmentation, and semantic segmentation. Our code and models will be released.

Trustworthy Machine Learning

Yuanjie Shi, Subhankar Ghosh, Taha Belkhouja, Jana Doppa, Yan Yan

Conformal prediction (CP) is an emerging uncertainty quantification framework that allows us to construct a prediction set to cover the true label with a pre-specified marginal or conditional probability.Although the valid coverage guarantee has been extensively studied for classification problems, CP often produces large prediction sets which may not be practically useful.This issue is exacerbated for the setting of class-conditional coverage on imbalanced classification tasks with many and/or imbalanced classes.This paper proposes the Rank Calibrated Class-conditional CP (RC3P) algorithm to reduce the prediction set sizes to achieve class-conditional coverage, where the valid coverage holds for each class.In contrast to the standard class-conditional CP (CCP) method that uniformly thresholds the class-wise conformity score for each class, the augmented label rank calibration step allows RC3P to selectively iterate this class-wise thresholding subroutine only for a subset of classes whose class-wise top-$k$ error is small.We prove that agnostic to the classifier and data distribution, RC3P achieves class-wise coverage. We also show that RC3P reduces the size of prediction sets compared to the CCP method. Comprehensive experiments on multiple real-world datasets demonstrate that RC3P achieves class-wise coverage and $26.25\\%$ $\downarrow$ reduction in prediction set sizes on average.

Steve Hanneke, Amin Karbasi, Shay Moran, Grigoris Velegkas

In this work we study the problem of actively learning binary classifiers from a given concept class, i.e., learning by utilizing unlabeled data and submitting targeted queries about their labels to a domain expert. We evaluate the quality of our solutions by considering the learning curves they induce, i.e., the rate of decrease of the misclassification probability as the number of label queries increases. The majority of the literature on active learning has focused on obtaining uniform guarantees on the error rate which are only able to explain the upper envelope of the learning curves over families of different data-generating distributions. We diverge from this line of work and we focus on the distribution-dependent framework of universal learning whose goal is to obtain guarantees that hold for any fixed distribution, but do not apply uniformly over all the distributions. We provide a complete characterization of the optimal learning rates that are achievable by algorithms that have to specify the number of unlabeled examples they use ahead of their execution. Moreover, we identify combinatorial complexity measures that give rise to each case of our tetrachotomic characterization. This resolves an open question that was posed by Balcan et al. (2010). As a byproduct of our main result, we develop an active learning algorithm for partial concept classes that achieves exponential learning rates in the uniform setting.

Neuroscience, Cognitive Science

Yufei Guo, Weihang Peng, Xiaode Liu, Yuanpei Chen, Yuhan Zhang, Xin Tong, Zhou Jie, Zhe Ma

Spiking neural networks (SNNs) have gained more and more interest as one of the energy-efficient alternatives of conventional artificial neural networks (ANNs). They exchange 0/1 spikes for processing information, thus most of the multiplications in networks can be replaced by additions. However, binary spike feature maps will limit the expressiveness of the SNN and result in unsatisfactory performance compared with ANNs. It is shown that a rich output feature representation, i.e., the feature vector before classifier) is beneficial to training an accurate model in ANNs for classification. We wonder if it also does for SNNs and how to improve the feature representation of the SNN.To this end, we materialize this idea in two special designed methods for SNNs.First, inspired by some ANN-SNN methods that directly copy-paste the weight parameters from trained ANN with light modification to homogeneous SNN can obtain a well-performed SNN, we use rich information of the weight parameters from the trained ANN counterpart to guide the feature representation learning of the SNN. In particular, we present the SNN's and ANN's feature representation from the same input to ANN's classifier to product SNN's and ANN's outputs respectively and then align the feature with the KL-divergence loss as in knowledge distillation methods, called L_ AF loss.It can be seen as a novel and effective knowledge distillation method specially designed for the SNN that comes from both the knowledge distillation and ANN-SNN methods. Various ablation study shows that the L_AF loss is more powerful than the vanilla knowledge distillation method.Second, we replace the last Leaky Integrate-and-Fire (LIF) activation layer as the ReLU activation layer to generate the output feature, thus a more powerful SNN with full-precision feature representation can be achieved but with only a little extra computation.Experimental results show that our method consistently outperforms the current state-of-the-art algorithms on both popular non-spiking static and neuromorphic datasets. We provide an extremely simple but effective way to train high-accuracy spiking neural networks.

Theory · Game Theory

Lee Cohen, Saeed Sharifi-Malvajerdi, Kevin Stangl, Ali Vakilian, Juba Ziani

In strategic classification, agents modify their features, at a cost, to obtain a positive classification outcome from the learner’s classifier, typically assuming agents have full knowledge of the deployed classifier. In contrast, we consider a Bayesian setting where agents have a common distributional prior on the classifier being used and agents manipulate their features to maximize their expected utility according to this prior.The learner can reveal truthful, yet not necessarily complete, information about the classifier to the agents, aiming to release just enough information to shape the agents' behavior and thus maximize accuracy. We show that partial information release can counter-intuitively benefit the learner’s accuracy, allowing qualified agents to pass the classifier while preventing unqualified agents from doing so. Despite the intractability of computing the best response of an agent in the general case, we provide oracle-efficient algorithms for scenarios where the learner’s hypothesis class consists of low-dimensional linear classifiers or when the agents’ cost function satisfies a sub-modularity condition. Additionally, we address the learner’s optimization problem, offering both positive and negative results on determining the optimal information release to maximize expected accuracy, particularly in settings where an agent’s qualification can be represented by a real-valued number.

Neuroscience, Cognitive Science

Dongyang Li, Chen Wei, Shiying Li, Jiachen Zou, Quanying Liu

How to decode human vision through neural signals has attracted a long-standing interest in neuroscience and machine learning. Modern contrastive learning and generative models improved the performance of visual decoding and reconstruction based on functional Magnetic Resonance Imaging (fMRI). However, the high cost and low temporal resolution of fMRI limit their applications in brain-computer interfaces (BCIs), prompting a high need for visual decoding based on electroencephalography (EEG). In this study, we present an end-to-end EEG-based visual reconstruction zero-shot framework, consisting of a tailored brain encoder, called the Adaptive Thinking Mapper (ATM), which projects neural signals from different sources into the shared subspace as the clip embedding, and a two-stage multi-pipe EEG-to-image generation strategy. In stage one, EEG is embedded to align the high-level clip embedding, and then the prior diffusion model refines EEG embedding into image priors. A blurry image also decoded from EEG for maintaining the low-level feature. In stage two, we input both the high-level clip embedding, the blurry image and caption from EEG latent to a pre-trained diffusion model. Furthermore, we analyzed the impacts of different time windows and brain regions on decoding and reconstruction. The versatility of our framework is demonstrated in the magnetoencephalogram (MEG) data modality. The experimental results indicate that our EEG-based visual zero-shot framework achieves SOTA performance in classification, retrieval and reconstruction, highlighting the portability, low cost, and high temporal resolution of EEG, enabling a wide range of BCI applications. Our code is available at https://github.com/ncclab-sustech/EEG_Image_decode.

Neuroscience, Cognitive Science

Xuan-Hao Liu, Yan-Kai Liu, Yansen Wang, Kan Ren, Hanwen Shi, Zilong Wang, Dongsheng Li, Bao-Liang Lu, Wei-Long Zheng

Our visual experience in daily life are dominated by dynamic change. Decoding such dynamic information from brain activity can enhance the understanding of the brain’s visual processing system. However, previous studies predominately focus on reconstructing static visual stimuli. In this paper, we explore to decode dynamic visual perception from electroencephalography (EEG), a neuroimaging technique able to record brain activity with high temporal resolution (1000 Hz) for capturing rapid changes in brains. Our contributions are threefold: Firstly, we develop a large dataset recording signals from 20 subjects while they were watching 1400 dynamic video clips of 40 concepts. This dataset fills the gap in the lack of EEG-video pairs. Secondly, we annotate each video clips to investigate the potential for decoding some specific meta information (e.g., color, dynamic, human or not) from EEG. Thirdly, we propose a novel baseline EEG2Video for video reconstruction from EEG signals that better aligns dynamic movements with high temporal resolution brain signals by Seq2Seq architecture. EEG2Video achieves a 2-way accuracy of 79.8% in semantic classification tasks and 0.256 in structural similarity index (SSIM). Overall, our works takes an important step towards decoding dynamic visual perception from EEG signals. Our dataset and code will be released soon.

Computer Vision · Image Generation

Lei Zhu, Fangyun Wei, Yanye Lu, Dong Chen

In the realm of image quantization exemplified by VQGAN, the process encodes images into discrete tokens drawn from a codebook with a predefined size. Recent advancements, particularly with LLAMA 3, reveal that enlarging the codebook significantly enhances model performance. However, VQGAN and its derivatives, such as VQGAN-FC (Factorized Codes) and VQGAN-EMA, continue to grapple with challenges related to expanding the codebook size and enhancing codebook utilization. For instance, VQGAN-FC is restricted to learning a codebook with a maximum size of 16,384, maintaining a typically low utilization rate of less than 12% on ImageNet. In this work, we propose a novel image quantization model named VQGAN-LC (Large Codebook), which extends the codebook size to 100,000, achieving an utilization rate exceeding 99%. Unlike previous methods that optimize each codebook entry, our approach begins with a codebook initialized with 100,000 features extracted by a pre-trained vision encoder. Optimization then focuses on training a projector that aligns the entire codebook with the feature distributions of the encoder in VQGAN-LC. We demonstrate the superior performance of our model over its counterparts across a variety of tasks, including image reconstruction, image classification, auto-regressive image generation using GPT, and image creation with diffusion- and flow-based generative models.

Theory · Game Theory

Tinashe Handina, Eric Mazumdar

The deployment of ever-larger machine learning models reflects a growing consensus that the more expressive the model class one optimizes over—and the more data one has access to—the more one can improve performance. As models get deployed in a variety of real-world scenarios, they inevitably face strategic environments. In this work, we consider the natural question of how the interplay of models and strategic interactions affects the relationship between performance at equilibrium and the expressivity of model classes. We find that strategic interactions can break the conventional view—meaning that performance does not necessarily monotonically improve as model classes get larger or more expressive (even with infinite data). We show the implications of this result in several contexts including strategic regression, strategic classification, and multi-agent reinforcement learning. In particular, we show that each of these settings admits a Braess' paradox-like phenomenon in which optimizing over less expressive model classes allows one to achieve strictly better equilibrium outcomes. Motivated by these examples, we then propose a new paradigm for model selection in games wherein an agent seeks to choose amongst different model classes to use as their action set in a game.

Trustworthy Machine Learning

Eleni Straitouri, Suhas Thejaswi, Manuel Rodriguez

Decision support systems based on prediction sets help humans solve multiclass classification tasks by narrowing down the set of potential label values to a subset of them, namely a prediction set, and asking them to always predict label values from the prediction sets. While this type of systems have been proven to be effective at improving the average accuracy of the predictions made by humans, by restricting human agency, they may cause harm---a human who has succeeded at predicting the ground-truth label of an instance on their own may have failed had they used these systems. In this paper, our goal is to control how frequently a decision support system based on prediction sets may cause harm, by design. To this end, we start by characterizing the above notion of harm using the theoretical framework of structural causal models. Then, we show that, under a natural, albeit unverifiable, monotonicity assumption, we can estimate how frequently a system may cause harm using only predictions made by humans on their own. Further, we also show that, under a weaker monotonicity assumption, which can be verified experimentally, we can bound how frequently a system may cause harm again using only predictions made by humans on their own. Building upon these assumptions, we introduce a computational framework to design decision support systems based on prediction sets that are guaranteed to cause harm less frequently than a user-specified value using conformal risk control. We validate our framework using real human predictions from two different human subject studies and show that, in decision support systems based on prediction sets, there is a trade-off between accuracy and counterfactual harm.

Optimization · Learning for Optimization

Pham Khanh, Hoang-Chau Luong, Boris Mordukhovich, Dat Tran

The paper investigates the fundamental convergence properties of Sharpness-Aware Minimization (SAM), a recently proposed gradient-based optimization method (Foret et al., 2021) that significantly improves the generalization of deep neural networks. The convergence properties including the stationarity of accumulation points, the convergence of the sequence of gradients to the origin, the sequence of function values to the optimal value, and the sequence of iterates to the optimal solution are established for the method. The universality of the provided convergence analysis based on inexact gradient descent frameworks (Khanh et al., 2023b) allows its extensions to the normalized versions of SAM such as F-SAM (Li et al. 2024), VaSSO (Li & Giannakis, 2023), RSAM (Liu et al., 2022), and to the unnormalized versions of SAM such as USAM (Andriushchenko & Flammarion, 2022). Numerical experiments are conducted on classification tasks using deep learning models to confirm the practical aspects of our analysis.

Deep Learning · Self-Supervised Learning

Walter Simoncini, Andrei Bursuc, Spyridon Gidaris, Yuki Asano

This paper introduces FUNGI, **F**eatures from **UN**supervised **G**rad**I**ents, a method to enhance the features of transformer encoders by leveraging self-supervised gradients. Our method is simple: given any pretrained model, we first compute gradients from various self-supervised objectives for each input. These gradients are projected to a lower dimension and then concatenated with the model's output embedding. The resulting features are evaluated on k-nearest neighbor classification over 11 datasets from vision, 5 from natural language processing, and 2 from audio. Across backbones spanning various sizes and pretraining strategies, FUNGI features provide consistent performance improvements over the embeddings. We also show that using FUNGI features can benefit linear classification, clustering and image retrieval, and that they significantly improve the retrieval-based in-context scene understanding abilities of pretrained models, for example improving upon DINO by +17% for semantic segmentation - without any training. Code is available at https://github.com/WalterSimoncini/fungivision.

Computer Vision

Chau Tran, Duy M. H. Nguyen, Manh-Duy Nguyen, TrungTin Nguyen, Ngan Le, Pengtao Xie, Daniel Sonntag, James Zou, Binh Nguyen, Mathias Niepert

Increasing the throughput of the Transformer architecture, a foundational component used in numerous state-of-the-art models for vision and language tasks (e.g., GPT, LLaVa), is an important problem in machine learning. One recent and effective strategy is to merge token representations within Transformer models, aiming to reduce computational and memory requirements while maintaining accuracy. Prior work has proposed algorithms based on Bipartite Soft Matching (BSM), which divides tokens into distinct sets and merges the top $k$ similar tokens. However, these methods have significant drawbacks, such as sensitivity to token-splitting strategies and damage to informative tokens in later layers. This paper presents a novel paradigm called PiToMe, which prioritizes the preservation of informative tokens using an additional metric termed the \textit{energy score}. This score identifies large clusters of similar tokens as high-energy, indicating potential candidates for merging, while smaller (unique and isolated) clusters are considered as low-energy and preserved. Experimental findings demonstrate that PiToMe saved from 40-60\% FLOPs of the base models while exhibiting superior off-the-shelf performance on image classification (0.5\% average performance drop of ViT-MAEH compared to 2.6\% as baselines), image-text retrieval (0.3\% average performance drop of Clip on Flick30k compared to 4.5\% as others), and analogously in visual questions answering with LLaVa-7B. Furthermore, PiToMe is theoretically shown to preserve intrinsic spectral properties to the original token space under mild conditions.

Applications

Jiahao Li, Yang Lu, Yuan Xie, Yanyun Qu

Open-vocabulary semantic segmentation (OVSS) aims to segment unseen classes without corresponding labels. Existing Vision-Language Model (VLM)-based methods leverage VLM's rich knowledge to enhance additional explicit segmentation-specific networks, yielding competitive results, but at the cost of extensive training cost. To reduce the cost, we attempt to enable VLM to directly produce the segmentation results without any segmentation-specific networks. Prompt learning offers a direct and parameter-efficient approach, yet it falls short in guiding VLM for pixel-level visual classification. Therefore, we propose the ${\bf R}$elationship ${\bf P}$rompt ${\bf M}$odule (${\bf RPM}$), which generates the relationship prompt that directs VLM to extract pixel-level semantic embeddings suitable for OVSS. Moreover, RPM integrates with VLM to construct the ${\bf R}$elationship ${\bf P}$rompt ${\bf N}$etwork (${\bf RPN}$), achieving OVSS without any segmentation-specific networks. RPN attains state-of-the-art performance with merely about ${\bf 3M}$ trainable parameters (2\% of total parameters).

Computer Vision

zhengrui Xu, Guan'an Wang, Xiaowen Huang, Jitao Sang

The denoising model has been proven a powerful generative model but has little exploration of discriminative tasks. Representation learning is important in discriminative tasks, which is defined as *"learning representations (or features) of the data that make it easier to extract useful information when building classifiers or other predictors"*. In this paper, we propose a novel Denoising Model for Representation Learning (*DenoiseRep*) to improve feature discrimination with joint feature extraction and denoising. *DenoiseRep* views each embedding layer in a backbone as a denoising layer, processing the cascaded embedding layers as if we are recursively denoise features step-by-step. This unifies the frameworks of feature extraction and denoising, where the former progressively embeds features from low-level to high-level, and the latter recursively denoises features step-by-step. After that, *DenoiseRep* fuses the parameters of feature extraction and denoising layers, and *theoretically demonstrates* its equivalence before and after the fusion, thus making feature denoising computation-free. *DenoiseRep* is a label-free algorithm that incrementally improves features but also complementary to the label if available. Experimental results on various discriminative vision tasks, including re-identification (Market-1501, DukeMTMC-reID, MSMT17, CUHK-03, vehicleID), image classification (ImageNet, UB200, Oxford-Pet, Flowers), object detection (COCO), image segmentation (ADE20K) show stability and impressive improvements. We also validate its effectiveness on the CNN (ResNet) and Transformer (ViT, Swin, Vmamda) architectures.

Graph Neural Networks

Yufei Jin, Heng Lian, Yi He, Xingquan Zhu

Label Distribution Learning (LDL) has been extensively studied in IID data applications such as computer vision, thanks to its more generic setting over single-label and multi-label classification. This paper advances LDL into graph domains and aims to tackle a novel and fundamentalheterogeneous graph label distribution learning (HGDL) problem.We argue that the graph heterogeneity reflected on node types, node attributes, and neighborhood structures can impose significant challenges for generalizing LDL onto graphs. To address the challenges, we propose a new learning framework with two key components: 1) proactive graph topology homogenization, and 2) topology and content consistency-aware graph transformer. Specifically, the former learns optimal information aggregation between meta-paths, so that the nodeheterogeneity can be proactively addressed prior to the succeeding embedding learning; the latter leverages an attention mechanism to learn consistency between meta-path and node attributes, allowing network topology and nodal attributes to be equally emphasized during the label distribution learning. By using KL-divergence and additional constraints, \method~delivers an end-to-end solution for learning and predicting label distribution for nodes. Both theoretical and empirical studies substantiate the effectiveness of our HGDL approach.Our code and datasets are available at https://github.com/Listener-Watcher/HGDL.

Learning Theory

Anqi Mao, Mehryar Mohri, Yutao Zhong

We present a comprehensive study of surrogate loss functions for learning to defer. We introduce a broad family of surrogate losses, parameterized by a non-increasing function $\Psi$, and establish their realizable $H$-consistency under mild conditions. For cost functions based on classification error, we further show that these losses admit $H$-consistency bounds when the hypothesis set is symmetric and complete, a property satisfied by common neural network and linear function hypothesis sets. Our results also resolve an open question raised in previous work [Mozannar et al., 2023] by proving the realizable $H$-consistency and Bayes-consistency of a specific surrogate loss. Furthermore, we identify choices of $\Psi$ that lead to $H$-consistent surrogate losses for *any general cost function*, thus achieving Bayes-consistency, realizable $H$-consistency, and $H$-consistency bounds *simultaneously*. We also investigate the relationship between $H$-consistency bounds and realizable $H$-consistency in learning to defer, highlighting key differences from standard classification. Finally, we empirically evaluate our proposed surrogate losses and compare them with existing baselines.

Language

Qianyue Hao, Jingyang Fan, Fengli Xu, Jian Yuan, Yong Li

Citation networks are critical infrastructures of modern science, serving as intricate webs of past literature and enabling researchers to navigate the knowledge production system. To mine information hiding in the link space of such networks, predicting which previous papers (candidates) will a new paper (query) cite is a critical problem that has long been studied. However, an important gap remains unaddressed: the roles of a paper's citations vary significantly, ranging from foundational knowledge basis to superficial contexts. Distinguishing these roles requires a deeper understanding of the logical relationships among papers, beyond simple edges in citation networks. The emergence of large language models (LLMs) with textual reasoning capabilities offers new possibilities for discerning these relationships, but there are two major challenges. First, in practice, a new paper may select its citations from gigantic existing papers, where the combined texts far exceed the context length of LLMs. Second, logical relationships between papers are often implicit, and directly prompting an LLM to predict citations may lead to results based primarily on surface-level textual similarities, rather than the deeper logical reasoning required. In this paper, we introduce the novel concept of core citation, which identifies the critical references that go beyond superficial mentions. Thereby, we elevate the citation prediction task from a simple binary classification to a more nuanced problem: distinguishing core citations from both superficial citations and non-citations. To address this, we propose $\textbf{HLM-Cite}$, a $\textbf{H}$ybrid $\textbf{L}$anguage $\textbf{M}$odel workflow for citation prediction, which combines embedding and generative LMs. We design a curriculum finetune procedure to adapt a pretrained text embedding model to coarsely retrieve high-likelihood core citations from vast candidate sets and then design an LLM agentic workflow to rank the retrieved papers through one-shot reasoning, revealing the implicit relationships among papers. With the two-stage pipeline, we can scale the candidate sets to 100K papers, vastly exceeding the size handled by existing methods. We evaluate HLM-Cite on a dataset across 19 scientific fields, demonstrating a 17.6\% performance improvement comparing SOTA methods. Our code is open-source at https://github.com/tsinghua-fib-lab/H-LM for reproducibility.

Online Learning

Giovanni Bellitto, Federica Proietto Salanitri, Matteo Pennisi, Matteo Boschini, Lorenzo Bonicelli, Angelo Porrello, SIMONE CALDERARA, Simone Palazzo, Concetto Spampinato

We present Saliency-driven Experience Replay - SER - a biologically-plausible approach based on replicating human visual saliency to enhance classification models in continual learning settings. Inspired by neurophysiological evidence that the primary visual cortex does not contribute to object manifold untangling for categorization and that primordial saliency biases are still embedded in the modern brain, we propose to employ auxiliary saliency prediction features as a modulation signal to drive and stabilize the learning of a sequence of non-i.i.d. classification tasks. Experimental results confirm that SER effectively enhances the performance (in some cases up to about twenty percent points) of state-of-the-art continual learning methods, both in class-incremental and task-incremental settings. Moreover, we show that saliency-based modulation successfully encourages the learning of features that are more robust to the presence of spurious features and to adversarial attacks than baseline methods. Code is available at: https://github.com/perceivelab/SER