Evaluating Large Vision-and-Language Models on Children's Mathematical Olympiads

Recent years have seen a significant progress in the general-purpose problem solving abilities of large vision and language models (LVLMs), such as ChatGPT, Gemini, etc.; some of these breakthroughs even seem to enable AI models to outperform human abilities in varied tasks that demand higher-order cognitive skills. Are the current large AI models indeed capable of generalized problem solving as humans do? A systematic analysis of AI capabilities for joint vision and text reasoning, however, is missing in the current scientific literature. In this paper, we make an effort towards filling this gap, by evaluating state-of-the-art LVLMs on their mathematical and algorithmic reasoning abilities using visuo-linguistic problems from children's Olympiads. Specifically, we consider problems from the Mathematical Kangaroo (MK) Olympiad, which is a popular international competition targeted at children from grades 1-12, that tests children's deeper mathematical abilities using puzzles that are appropriately gauged to their age and skills. Using the puzzles from MK, we created a dataset, dubbed SMART-840, consisting of 840 problems from years 2020-2024. With our dataset, we analyze LVLMs power on mathematical reasoning; their responses on our puzzles offer a direct way to compare against that of children. Our results show that modern LVLMs do demonstrate increasingly powerful reasoning skills in solving problems for higher grades, but lack the foundations to correctly answer problems designed for younger children. Further analysis shows that there is no significant correlation between the reasoning capabilities of AI models and that of young children, and their capabilities appear to be based on a different type of reasoning than the cumulative knowledge that underlies children's mathematics and logic skills.

Multimodal 3D Object Detection on Unseen Domains

LiDAR datasets for autonomous driving exhibit biases in properties such as point cloud density, range, and object dimensions. As a result, object detection networks trained and evaluated in different environments often experience performance degradation. Domain adaptation approaches assume access to unannotated samples from the test distribution to address this problem. However, in the real world, the exact conditions of deployment and access to samples representative of the test dataset may be unavailable while training. We argue that the more realistic and challenging formulation is to require robustness in performance to unseen target domains. We propose to address this problem in a two-pronged manner. First, we leverage paired LiDAR-image data present in most autonomous driving datasets to perform multimodal object detection. We suggest that working with multimodal features by leveraging both images and LiDAR point clouds for scene understanding tasks results in object detectors more robust to unseen domain shifts. Second, we train a 3D object detector to learn multimodal object features across different distributions and promote feature invariance across these source domains to improve generalizability to unseen target domains. To this end, we propose CLIX$^\text{3D}$, a multimodal fusion and supervised contrastive learning framework for 3D object detection that performs alignment of object features from same-class samples of different domains while pushing the features from different classes apart. We show that CLIX$^\text{3D}$ yields state-of-the-art domain generalization performance under multiple dataset shifts.

Equivariant Spatio-Temporal Self-Supervision for LiDAR Object Detection

Popular representation learning methods encourage feature invariance under transformations applied at the input. However, in 3D perception tasks like object localization and segmentation, outputs are naturally equivariant to some transformations, such as rotation. Using pre-training loss functions that encourage equivariance of features under certain transformations provides a strong self-supervision signal while also retaining information of geometric relationships between transformed feature representations. This can enable improved performance in downstream tasks that are equivariant to such transformations. In this paper, we propose a spatio-temporal equivariant learning framework by considering both spatial and temporal augmentations jointly. Our experiments show that the best performance arises with a pre-training approach that encourages equivariance to translation, scaling, and flip, rotation and scene flow. For spatial augmentations, we find that depending on the transformation, either a contrastive objective or an equivariance-by-classification objective yields best results. To leverage real-world object deformations and motion, we consider sequential LiDAR scene pairs and develop a novel 3D scene flow-based equivariance objective that leads to improved performance overall. We show our pre-training method for 3D object detection which outperforms existing equivariant and invariant approaches in many settings.

Long-Tailed Anomaly Detection with Learnable Class Names

Anomaly detection (AD) aims to identify defective images and localize their defects (if any). Ideally, AD models should be able to detect defects over many image classes; without relying on hard-coded class names that can be uninformative or inconsistent across datasets; learn without anomaly supervision; and be robust to the long-tailed distributions of real-world applications. To address these challenges, we formulate the problem of long-tailed AD by introducing several datasets with different levels of class imbalance and metrics for performance evaluation. We then propose a novel method, LTAD, to detect defects from multiple and long-tailed classes, without relying on dataset class names. LTAD combines AD by reconstruction and semantic AD modules. AD by reconstruction is implemented with a transformer-based reconstruction module. Semantic AD is implemented with a binary classifier, which relies on learned pseudo class names and a pretrained foundation model. These modules are learned over two phases. Phase 1 learns the pseudo-class names and a variational autoencoder (VAE) for feature synthesis that augments the training data to combat long-tails. Phase 2 then learns the parameters of the reconstruction and classification modules of LTAD. Extensive experiments using the proposed long-tailed datasets show that LTAD substantially outperforms the state-of-the-art methods for most forms of dataset imbalance. The long-tailed dataset split is available at https://zenodo.org/records/10854201 .

Tensor Factorization for Leveraging Cross-Modal Knowledge in Data-Constrained Infrared Object Detection

The primary bottleneck towards obtaining good recognition performance in IR images is the lack of sufficient labeled training data, owing to the cost of acquiring such data. Realizing that object detection methods for the RGB modality are quite robust (at least for some commonplace classes, like person, car, etc.), thanks to the giant training sets that exist, in this work we seek to leverage cues from the RGB modality to scale object detectors to the IR modality, while preserving model performance in the RGB modality. At the core of our method, is a novel tensor decomposition method called TensorFact which splits the convolution kernels of a layer of a Convolutional Neural Network (CNN) into low-rank factor matrices, with fewer parameters than the original CNN. We first pretrain these factor matrices on the RGB modality, for which plenty of training data are assumed to exist and then augment only a few trainable parameters for training on the IR modality to avoid over-fitting, while encouraging them to capture complementary cues from those trained only on the RGB modality. We validate our approach empirically by first assessing how well our TensorFact decomposed network performs at the task of detecting objects in RGB images vis-a-vis the original network and then look at how well it adapts to IR images of the FLIR ADAS v1 dataset. For the latter, we train models under scenarios that pose challenges stemming from data paucity. From the experiments, we observe that: (i) TensorFact shows performance gains on RGB images; (ii) further, this pre-trained model, when fine-tuned, outperforms a standard state-of-the-art object detector on the FLIR ADAS v1 dataset by about 4% in terms of mAP 50 score.

Are Deep Neural Networks SMARTer than Second Graders?

Recent times have witnessed an increasing number of applications of deep neural networks towards solving tasks that require superior cognitive abilities, e.g., playing Go, generating art, question answering (such as ChatGPT), etc. Such a dramatic progress raises the question: how generalizable are neural networks in solving problems that demand broad skills? To answer this question, we propose SMART: a Simple Multimodal Algorithmic Reasoning Task and the associated SMART-101 dataset, for evaluating the abstraction, deduction, and generalization abilities of neural networks in solving visuo-linguistic puzzles designed specifically for children in the 6-8 age group. Our dataset consists of 101 unique puzzles; each puzzle comprises a picture and a question, and their solution needs a mix of several elementary skills, including arithmetic, algebra, and spatial reasoning, among others. To scale our dataset towards training deep neural networks, we programmatically generate entirely new instances for each puzzle while retaining their solution algorithm. To benchmark the performance on the SMART-101 dataset, we propose a vision and language meta-learning model using varied state-of-the-art backbone neural networks. Our experiments reveal that while powerful deep models offer reasonable performances on puzzles that they are trained on, they are not better than random accuracy when analyzed for generalization. We also evaluate the recent ChatGPT large language model on a subset of our dataset and find that while ChatGPT produces convincing reasoning abilities, the answers are often incorrect.

Cross-Domain Video Anomaly Detection without Target Domain Adaptation

Most cross-domain unsupervised Video Anomaly Detection (VAD) works assume that at least few task-relevant target domain training data are available for adaptation from the source to the target domain. However, this requires laborious model-tuning by the end-user who may prefer to have a system that works ``out-of-the-box." To address such practical scenarios, we identify a novel target domain (inference-time) VAD task where no target domain training data are available. To this end, we propose a new `Zero-shot Cross-domain Video Anomaly Detection (zxvad)' framework that includes a future-frame prediction generative model setup. Different from prior future-frame prediction models, our model uses a novel Normalcy Classifier module to learn the features of normal event videos by learning how such features are different ``relatively" to features in pseudo-abnormal examples. A novel Untrained Convolutional Neural Network based Anomaly Synthesis module crafts these pseudo-abnormal examples by adding foreign objects in normal video frames with no extra training cost. With our novel relative normalcy feature learning strategy, zxvad generalizes and learns to distinguish between normal and abnormal frames in a new target domain without adaptation during inference. Through evaluations on common datasets, we show that zxvad outperforms the state-of-the-art (SOTA), regardless of whether task-relevant (i.e., VAD) source training data are available or not. Lastly, zxvad also beats the SOTA methods in inference-time efficiency metrics including the model size, total parameters, GPU energy consumption, and GMACs.

Cross-Modal Knowledge Transfer Without Task-Relevant Source Data

Cost-effective depth and infrared sensors as alternatives to usual RGB sensors are now a reality, and have some advantages over RGB in domains like autonomous navigation and remote sensing. As such, building computer vision and deep learning systems for depth and infrared data are crucial. However, large labeled datasets for these modalities are still lacking. In such cases, transferring knowledge from a neural network trained on a well-labeled large dataset in the source modality (RGB) to a neural network that works on a target modality (depth, infrared, etc.) is of great value. For reasons like memory and privacy, it may not be possible to access the source data, and knowledge transfer needs to work with only the source models. We describe an effective solution, SOCKET: SOurce-free Cross-modal KnowledgE Transfer for this challenging task of transferring knowledge from one source modality to a different target modality without access to task-relevant source data. The framework reduces the modality gap using paired task-irrelevant data, as well as by matching the mean and variance of the target features with the batch-norm statistics that are present in the source models. We show through extensive experiments that our method significantly outperforms existing source-free methods for classification tasks which do not account for the modality gap.

Towards To-a-T Spatio-Temporal Focus for Skeleton-Based Action Recognition

Graph Convolutional Networks (GCNs) have been widely used to model the high-order dynamic dependencies for skeleton-based action recognition. Most existing approaches do not explicitly embed the high-order spatio-temporal importance to joints' spatial connection topology and intensity, and they do not have direct objectives on their attention module to jointly learn when and where to focus on in the action sequence. To address these problems, we propose the To-a-T Spatio-Temporal Focus (STF), a skeleton-based action recognition framework that utilizes the spatio-temporal gradient to focus on relevant spatio-temporal features. We first propose the STF modules with learnable gradient-enforced and instance-dependent adjacency matrices to model the high-order spatio-temporal dynamics. Second, we propose three loss terms defined on the gradient-based spatio-temporal focus to explicitly guide the classifier when and where to look at, distinguish confusing classes, and optimize the stacked STF modules. STF outperforms the state-of-the-art methods on the NTU RGB+D 60, NTU RGB+D 120, and Kinetics Skeleton 400 datasets in all 15 settings over different views, subjects, setups, and input modalities, and STF also shows better accuracy on scarce data and dataset shifting settings.

Iterative Self Knowledge Distillation -- From Pothole Classification to Fine-Grained and COVID Recognition

Pothole classification has become an important task for road inspection vehicles to save drivers from potential car accidents and repair bills. Given the limited computational power and fixed number of training epochs, we propose iterative self knowledge distillation (ISKD) to train lightweight pothole classifiers. Designed to improve both the teacher and student models over time in knowledge distillation, ISKD outperforms the state-of-the-art self knowledge distillation method on three pothole classification datasets across four lightweight network architectures, which supports that self knowledge distillation should be done iteratively instead of just once. The accuracy relation between the teacher and student models shows that the student model can still benefit from a moderately trained teacher model. Implying that better teacher models generally produce better student models, our results justify the design of ISKD. In addition to pothole classification, we also demonstrate the efficacy of ISKD on six additional datasets associated with generic classification, fine-grained classification, and medical imaging application, which supports that ISKD can serve as a general-purpose performance booster without the need of a given teacher model and extra trainable parameters.