Modern Hopfield networks (MHNs) have recently gained significant attention in the field of artificial intelligence because they can store and retrieve a large set of patterns with an exponentially large memory capacity. A MHN is generally a dynamical system defined with Lagrangians of memory and feature neurons,where memories associated with in-distribution (ID) samples are represented by attractors in the feature space. One major problem in existing MHNs lies in managing out-of-distribution (OOD) samples because it was originally assumed that all samples are ID samples. To address this, we propose the rectified Lagrangian (RegLag), a new Lagrangian for memory neurons that explicitly incorporates an attractor for OOD samples in the dynamical system of MHNs. RecLag creates a trivial point attractor for any interaction matrix, enabling OOD detection by identifying samples that fall into this attractor as OOD. The interaction matrix is optimized so that the probability densities can be estimated to identify ID/OOD. We demonstrate the effectiveness of RecLag-based MHNs compared to energy-based OOD detection methods, including those using state-of-the-art Hopfield energies, across nine image datasets.

For deploying deep neural networks on edge devices with limited resources, binary neural networks (BNNs) have attracted significant attention, due to their computational and memory efficiency. However, once a neural network is binarized, finetuning it on edge devices becomes challenging because most conventional training algorithms for BNNs are designed for use on centralized servers and require storing real-valued parameters during training. To address this limitation, this paper introduces binary stochastic flip optimization (BinSFO), a novel training algorithm for BNNs. BinSFO employs a parameter update rule based on Boolean operations, eliminating the need to store real-valued parameters and thereby reducing memory requirements and computational overhead. In experiments, we demonstrated the effectiveness and memory efficiency of BinSFO in fine-tuning scenarios on six image classification datasets. BinSFO performed comparably to conventional training algorithms with a 70.7% smaller memory requirement. Code is released at https://github.com/TatsukichiShibuya/ICASSP2025_BinSFO

Generating realistic group interactions involving multiple characters remains challenging due to increasing complexity as group size expands. While existing conditional diffusion models incrementally generate motions by conditioning on previously generated characters, they rely on single shared prompts, limiting nuanced control and leading to overly simplified interactions. In this paper, we introduce Person-Interaction Noise Optimization (PINO), a novel, training-free framework designed for generating realistic and customizable interactions among groups of arbitrary size. PINO decomposes complex group interactions into semantically relevant pairwise interactions, and leverages pretrained two-person interaction diffusion models to incrementally compose group interactions. To ensure physical plausibility and avoid common artifacts such as overlapping or penetration between characters, PINO employs physics-based penalties during noise optimization. This approach allows precise user control over character orientation, speed, and spatial relationships without additional training. Comprehensive evaluations demonstrate that PINO generates visually realistic, physically coherent, and adaptable multi-person interactions suitable for diverse animation, gaming, and robotics applications.

Surface anomaly detection is a task to localize abnormal regions in a given image, typically used for product inspection. A representative approach is the reconstruction-based method, which detects defects using reconstruction errors computed by generative models, such as diffusion models trained exclusively on normal images. In reality, however, for products largely comprised of metal or resin, it is common to identify abnormalities based on local physical distortion levels; i.e., regions exceeding a predefined tolerance are regarded as defective. Reconstruction error-based approaches cannot directly estimate this metric. To address this issue, we propose DiffuDewarp, a novel method that directly estimates local distortions. Our approach defines a pseudo-deformation defect generation process as a new diffusion process based on localized warping. Experiments on the MVTec dataset demonstrate that our method outperforms state-of-the-art techniques in categories where local deformations are the primary cause of defects. Code is released at https://github.com/UCHIDA-AKIRA018/DiffuDewarp.

Gated Linear Units (GLUs) have become essential components in the feed-forward networks of state-of-the-art Large Language Models (LLMs). However, they require twice as many memory reads compared to feed-forward layers without gating, due to the use of separate weight matrices for the gate and value streams. To address this bottleneck, we introduce Masked Gated Linear Units (MGLUs), a novel family of GLUs with an efficient kernel implementation. The core contribution of MGLUs include: (1) the Mixture of Element-wise Gating (MoEG) architecture that learns multiple binary masks, each determining gate or value assignments at the element level on a single shared weight matrix resulting in reduced memory transfer, and (2) FlashMGLU, a hardware-friendly kernel that yields up to a 19.7$\times$ inference-time speed-up over a na\"ive PyTorch MGLU and is 47\% more memory-efficient and 34\% faster than standard GLUs despite added architectural complexity on an RTX5090 GPU. In LLM experiments, the Swish-activated variant SwiMGLU preserves its memory advantages while matching—or even surpassing—the downstream accuracy of the SwiGLU baseline.

Exploring biologically plausible algorithms as alternatives to error backpropagation (BP) is a challenging research topic in artificial intelligence. It also provides insights into the brain's learning methods. Recently, when combined with well-designed feedback loss functions such as Local Difference Reconstruction Loss (LDRL) and through hierarchical training of feedback pathway synaptic weights, Target Propagation (TP) has achieved performance comparable to BP in image classification tasks. However, with an increase in the number of network layers, the tuning and training cost of feedback weights escalates. Drawing inspiration from the work of Ernoult et al., we propose a training method that seeks the optimal solution for feedback weights. This method enhances the efficiency of feedback training by analytically minimizing feedback loss, allowing the feedback layer to skip certain local training iterations. More specifically, we introduce the Jacobian matching loss (JML) for feedback training. We also proactively implement layers designed to derive analytical solutions that minimize JML. Through experiments, we have validated the effectiveness of this approach. Using the CIFAR-10 dataset, our method showcases accuracy levels comparable to state-of-the-art TP methods. Furthermore, we have explored its effectiveness in more intricate network architectures.

We propose Gumbel-NeRF, a mixture-of-expert (MoE) neural radiance fields (NeRF) model with a hindsight expert selection mechanism for synthesizing novel views of unseen objects. Previous studies have shown that the MoE structure provides high-quality representations of a given large-scale scene consisting of many objects. However, we observe that such a MoE NeRF model often produces low-quality representations in the vicinity of experts’ boundaries when applied to the task of novel view synthesis of an unseen object from one/few-shot input. We find that this deterioration is primarily caused by the foresight expert selection mechanism, which may leave an unnatural discontinuity in the object shape near the experts’ boundaries. Gumbel-NeRF adopts a hindsight expert selection mechanism, which guarantees continuity in the density field even near the experts’ boundaries. Experiments using the SRN cars dataset demonstrate the superiority of Gumbel-NeRF over the baselines in terms of various image quality metrics. The code will be available upon acceptance.

Target Propagation (TP) is a biologically more plausible algorithm than the error backpropagation (BP) to train deep networks, and improving practicality of TP is an open issue. TP methods require the feedforward and feedback networks to form layer-wise autoencoders for propagating the target values generated at the output layer. However, this causes certain drawbacks; e.g., careful hyperparameter tuning is required to synchronize the feedforward and feedback training, and frequent updates of the feedback path are usually required than that of the feedforward path. Learning of the feedforward and feedback networks is sufficient to make TP methods capable of training, but is having these layer-wise autoencoders a necessary condition for TP to work? We answer this question by presenting Fixed-Weight Difference Target Propagation (FW-DTP) that keeps the feedback weights constant during training. We confirmed that this simple method, which naturally resolves the abovementioned problems of TP, can still deliver informative target values to hidden layers for a given task; indeed, FW-DTP consistently achieves higher test performance than a baseline, the Difference Target Propagation (DTP), on four classification datasets. We also present a novel propagation architecture that explains the exact form of the feedback function of DTP to analyze FW-DTP. Our code is available at https://github.com/TatsukichiShibuya/Fixed-Weight-Difference-Target-Propagation.

It has been known by neuroscience studies that partial and transient forgetting of memory often plays an important role in the brain to improve performance for certain intellectual activities. In machine learning, associative memory models such as classical and modern Hopfield networks have been proposed to express memories as attractors in the feature space of a closed recurrent network. In this work, we propose learning with partial forgetting (LwPF), where a partial forgetting functionality is designed by element-wise non-bijective projections, for memory neurons in modern Hopfield networks to improve model performance. We incorporate LwPF into the attention mechanism also, whose process has been shown to be identical to the update rule of a certain modern Hopfield network, by modifying the corresponding Lagrangian. We evaluated the effectiveness of LwPF on three diverse tasks such as bit-pattern classification, immune repertoire classification for computational biology, and image classification for computer vision, and confirmed that LwPF consistently improves the performance of existing neural networks including DeepRC and vision transformers.

It has been intensively investigated that the local shape, especially flatness, of the loss landscape near a minimum plays an important role for generalization of deep models. We developed a training algorithm called PoF: Post-Training of Feature Extractor that updates the feature extractor part of an already-trained deep model to search a flatter minimum. The characteristics are two-fold: 1) Feature extractor is trained under parameter perturbations in the higher-layer parameter space, based on observations that suggest flattening higher-layer parameter space, and 2) the perturbation range is determined in a data-driven manner aiming to reduce a part of test loss caused by the positive loss curvature. We provide a theoretical analysis that shows the proposed algorithm implicitly reduces the target Hessian components as well as the loss. Experimental results show that PoF improved model performance against baseline methods on both CIFAR-10 and CIFAR-100 datasets for only 10-epoch post-training, and on SVHN dataset for 50-epoch post-training.

Ensembles of deep neural networks demonstrate improved performance over single models. For enhancing the diversity of ensemble members while keeping their performance, particle-based inference methods offer a promising approach from a Bayesian perspective. However, the best way to apply these methods to neural networks is still unclear: seeking samples from the weight-space posterior suffers from inefficiency due to the over-parameterization issues, while seeking samples directly from the function-space posterior often leads to serious underfitting. In this study, we propose to optimize particles in the feature space where activations of a specific intermediate layer lie to alleviate the abovementioned difficulties. Our method encourages each member to capture distinct features, which are expected to increase the robustness of the ensemble prediction. Extensive evaluation on real-world datasets exhibits that our model significantly outperforms the gold-standard Deep Ensembles on various metrics, including accuracy, calibration, and robustness.

Among various supervised deep metric learning methods proxy-based approaches have achieved high retrieval accuracies. Proxies, which are class-representative points in an embedding space, receive updates based on proxy-sample similarities in a similar manner to sample representations. In existing methods, a relatively small number of samples can produce large gradient magnitudes (i.e., hard samples), and a relatively large number of samples can produce small gradient magnitudes (i.e., easy samples); these can play a major part in updates. Assuming that acquiring too much sensitivity to such extreme sets of samples would deteriorate the generalizability of a method, we propose a novel proxy-based method called Informative Sample-Aware Proxy (Proxy-ISA), which directly modifies a gradient weighting factor for each sample using a scheduled threshold function, so that the model is more sensitive to the informative samples. Extensive experiments on the CUB-200-2011, Cars-196, Stanford Online Products and In-shop Clothes Retrieval datasets demonstrate the superiority of Proxy-ISA compared with the state-of-the-art methods.

This paper proposes a framework for training variational autoencoders (VAEs) for image distributions that have latent groups of factors. Our key idea is to introduce a mechanism to predict the factor group an image belongs to while simultaneously disentangling factors in it. More specifically, we propose an architecture consisting of three components: an encoder, a decoder, and a factor-group prediction header. The first two components are trained with a VAE objective, and the last one is trained with the proposed algorithm using the loss of unsupervised contrastive learning. In experiments, we designed a task in which more than one group of factors were entangled by combining multiple datasets and demonstrated the effectiveness of the proposed framework. The Mutual Information Gap score was improved from 0.089 to 0.125 on a merged dataset of Color-dSprites, 3DShapes, and MPI3D.

We propose a Regularization framework based on Adversarial Transformations (RAT) for semi-supervised learning. RAT is designed to enhance robustness of the output distribution of class prediction for a given data against input perturbation. RAT is an extension of Virtual Adversarial Training (VAT) in such a way that RAT adversraialy transforms data along the underlying data distribution by a rich set of data transformation functions that leave class label invariant, whereas VAT simply produces adversarial additive noises. In addition, we verified that a technique of gradually increasing of perturbation region further improves the robustness. In experiments, we show that RAT significantly improves classification performance on CIFAR-10 and SVHN compared to existing regularization methods under standard semi-supervised image classification settings.

This paper addresses the generation of referring expressions that not only refer to objects correctly but also let humans find them quickly. As a target becomes relatively less salient, identifying referred objects itself becomes more difficult. However, the existing studies regarded all sentences that refer to objects correctly as equally good, ignoring whether they are easily understood by humans. If the target is not salient, humans utilize relationships with the salient contexts around it to help listeners to comprehend it better. To derive this information from human annotations, our model is designed to extract information from the target and from the environment. Moreover, we regard that sentences that are easily understood are those that are comprehended correctly and quickly by humans. We optimized this by using the time required to locate the referred objects by humans and their accuracies. To evaluate our system, we created a new referring expression dataset whose images were acquired from Grand Theft Auto V (GTA V), limiting targets to persons. Experimental results show the effectiveness of our approach. Our code and dataset are available at https://github.com/mikittt/easy-to-understand-REG.

This study addresses an issue of co-adaptation between a feature extractor and a classifier in a neural network. A naive joint optimization of a feature extractor and a classifier often brings situations in which an excessively complex feature distribution adapted to a very specific classifier degrades the test performance. We introduce a method called Feature-extractor Optimization through Classifier Anonymization (FOCA), which is designed to avoid an explicit co-adaptation between a feature extractor and a particular classifier by using many randomly-generated, weak classifiers during optimization. We put forth a mathematical proposition that states the FOCA features form a point-like distribution within the same class in a class-separable fashion under special conditions. Real-data experiments under more general conditions provide supportive evidences.

A method that can robustly estimate the distance to a foregoing vehicle with a monocular camera is in high demand for developing inexpensive Adaptive Cruise Control (ACC) systems. The accuracy of the estimated distances heavily depends on the road geometry and the true distance to the target vehicle. That motivates us to develop a distance estimation method that has two important properties: (a) it can deal with non-planar road surfaces from the first principle, and (b) it can estimate not only the distance but its variance of the error through mathematical analyses. Experiments on the KITTI dataset demonstrated that the proposed distance estimator is more robust and stable than the planar assumption model, and we verified by Monte Carlo simulations that our error model correctly predicts the variance of the error in the estimated distances.

We propose a novel three-dimensional (3D)-convolution method, cv3dconv, for detecting spatiotemporal features from videos. It reduces the number of sum-of-products of 3D convolution by thousands of times by assuming the constant moving velocity of the camera. We observed that a specific class of video sequences, such as those captured by an in-vehicle camera, can be well approximated with piece-wise linear movements of 2D features in the temporal dimension. Our principal finding is that the 3D kernel, represented by the constant-velocity, can be decomposed into a convolution of a 2D kernel representing the shapes and a 3D kernel representing the velocity. We derived the efficient recursive algorithm for this class of 3D convolution which is exceptionally suited for sparse data, and this parameterized decomposed representation imposes a structured regularization along the temporal direction. We experimentally verified the validity of our approximation using a controlled dataset, and we also showed the effectiveness of cv3dconv for the visual odometry estimation task using real event camera data captured in urban road scene.

It has been claimed that development of an invehicle early warning system is important to maximize collision avoidance capability. This study aims to provide a method that can predict the true ego-vehicle motion long enough so that early warning could be feasible, using a monocular forward-view camera. Based on an observation that severalsecond future position of a vehicle is probabilistic rather than deterministic, our approach utilizes a machine learning algorithm that can probabilistically model human driving behavior from data to predict multiple possible paths, such as going straight, turning left, and turning right. Experimental results on KITTI dataset suggest that our probabilistic learning approach could suffice for 4-second early warning, while an orthodox, deterministic learning approach and a simple motion extrapolation approach do not satisfy the requirement.

Many studies have shown that Deep Convolutional Neural Networks (DCNNs) exhibit great accuracies given large training datasets in image recognition tasks. Optimization technique known as asynchronous mini-batch Stochastic Gradient Descent (SGD) is widely used for deep learning because it gives fast training speed and good recognition accuracies, while it may increases generalization error if training parameters are in inappropriate ranges. We propose a performance model of a distributed DCNN training system called SPRINT that uses asynchronous GPU processing based on mini-batch SGD. The model considers the probability distribution of mini-batch size and gradient staleness that are the core parameters of asynchronous SGD training. Our performance model takes DCNN architecture and machine specifications as input parameters, and predicts time to sweep entire dataset, mini-batch size and staleness with 5%, 9% and 19% error in average respectively on several supercomputers with up to thousands of GPUs. Experimental results on two different supercomputers show that our model can steadily choose the fastest machine configuration that nearly meets a target mini-batch size.

We propose a computer vision algorithm that detects obstacles crossing a vehicle's path with a monocular camera mounted on the vehicle. False positives are strongly suppressed even for low-resolution images by imposing constraints on feature-based optical flows. The constraints are derived from a model of crossing obstacle motion under perspective projection. A key concept in this model is “Relative Incoming Angle”, which is an angle between the camera's translational direction and relative velocity of a crossing obstacle with respect to the camera. We show a ROC curve that has been obtained by varying the Relative Incoming Angle using our dataset consisting of 18 scenes, 1456 frames. A representative point on the curve yields the detection rate of 59.7% and false positive rate of 2.6% (per-image).