Modeling spatio-temporal read voltages with complex distortions arising from the write and read mechanisms in flash memory devices is essential for the design of signal processing and coding algorithms. In this work, we propose Flash-Gen, a data-driven approach to generating flash memory read voltages in both space and time using conditional generative networks. This generative modeling method reconstructs read voltages from an individual memory cell based on the program levels of the cell and its surrounding cells, as well as the time stamp, in a time-efficient, resource-saving, and function-comprehensive manner. We evaluate the model over a range of time stamps using the read voltage distributions, the cell level error rates, and the relative frequency of errors for patterns most susceptible to inter-cell interference (ICI) effects. We propose a flash system optimization procedure, referred to as the Flash-Gen coding workflow, that leverages reconstructed read voltages for the development of error correction codes (ECCs) and constrained codes. Experimental results demonstrate that the model accurately captures the complex spatial and temporal features of the flash memory channel. Flash-Gen coding workflow can effectively address a range of important tasks, including threshold determination, coding performance estimation, and pattern characterization.

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.

Visual-language foundation models, like CLIP, learn generalized representations that enable zero-shot open-set clas-sification. Few-shot adaptation methods, based on prompt tuning, have been shown to further improve performance on downstream datasets. However, these methods do not fare well in the taxonomic open set (TOS) setting, where the classifier is asked to make prediction from label set across different levels of semantic granularity. Frequently, they infer incorrect labels at coarser taxonomic class levels, even when the inference at the leaf level (original class labels) is correct. To address this problem, we propose a prompt tuning technique that calibrates the hierarchical consistency of model predictions. A set of metrics of hierarchical consistency, the Hierarchical Consistent Accuracy (HCA) and the Mean Treecut Accuracy (MTA), are first proposed to evaluate TOS model performance. A new Prompt Tuning for Hierarchical Consistency (ProTeCt) technique is then proposed to calibrate classification across label set granularities. Results show that ProTeCt can be combined with existing prompt tuning methods to significantly improve TOS classification without degrading the leaf level classification performance. The code is available at https://github.com/gina9726/ProTeCt.

Modeling spatio-temporal read voltages with complex distortions arising from the write and read mechanisms in flash memory devices is essential for the design of signal processing and coding algorithms. In this work, we propose a data-driven approach to modeling NAND flash memory read voltages in both space and time using conditional generative networks. This generative flash modeling (GFM) method reconstructs read voltages from an individual memory cell based on the program levels of the cell and its surrounding cells, as well as the time stamp. We evaluate the model over a range of time stamps using the cell read voltage distributions, the cell level error rates, and the relative frequency of errors for patterns most susceptible to inter-cell interference (ICI) effects. Experimental results demonstrate that the model accurately captures the complex spatial and temporal features of the flash memory channel.

The problem of realistic VQA (RVQA), where a model has to reject unanswerable questions (UQs) and answer answerable ones (AQs), is studied. We first point out 2 drawbacks in current RVQA research, where (1) datasets contain too many unchallenging UQs and (2) a large number of annotated UQs are required for training. To resolve the first drawback, we propose a new testing dataset, RGQA, which combines AQs from an existing VQA dataset with around 29K human-annotated UQs. These UQs consist of both fine-grained and coarse-grained image-question pairs generated with 2 approaches: CLIP-based and Perturbation-based. To address the second drawback, we introduce an unsupervised training approach. This combines pseudo UQs obtained by randomly pairing images and questions, with an RoI Mixup procedure to generate more fine-grained pseudo UQs, and model ensembling to regularize model confidence. Experiments show that using pseudo UQs significantly outperforms RVQA baselines. RoI Mixup and model ensembling further increase the gain. Finally, human evaluation reveals a performance gap between humans and models, showing that more RVQA research is needed. Code and dataset is released on https://github.com/chihhuiho/RGQA.

The problem of adversarial defenses for image classification, where the goal is to robustify a classifier against adversarial examples, is considered. Inspired by the hypothesis that these examples lie beyond the natural image manifold, a novel aDversarIal defenSe with local impliCit functiOns (DISCO) is proposed to remove adversarial perturbations by localized manifold projections. DISCO consumes an adversarial image and a query pixel location and outputs a clean RGB value at the location. It is implemented with an encoder and a local implicit module, where the former produces per-pixel deep features and the latter uses the features in the neighborhood of query pixel for predicting the clean RGB value. Extensive experiments demonstrate that both DISCO and its cascade version outperform prior defenses, regardless of whether the defense is known to the attacker. DISCO is also shown to be data and parameter efficient and to mount defenses that transfers across datasets, classifiers and attacks.

Camera calibration is a crucial prerequisite in many applications of computer vision. In this paper, a new geometry-based camera calibration technique is proposed, which resolves two main issues associated with the widely used Zhang's method: (i) the lack of guidelines to avoid outliers in the computation and (ii) the assumption of fixed camera focal length. The proposed approach is based on the closed-form solution of principal lines with their intersection being the principal point while each principal line can concisely represent relative orientation/position (up to one degree of freedom for both) between a special pair of coordinate systems of image plane and calibration pattern. With such analytically tractable image features, computations associated with the calibration are greatly simplified, while the guidelines in (i) can be established intuitively. Experimental results for synthetic and real data show that the proposed approach does compare favorably with Zhang's method, in terms of correctness, robustness, and flexibility, and addresses issues (i) and (ii) satisfactorily.

Multiview recognition has been well studied in the literature and achieves decent performance in object recognition and retrieval task. However, most previous works rely on supervised learning and some impractical underlying assumptions, such as the availability of all views in training and inference time. In this work, the problem of multiview self-supervised learning (MV-SSL) is investigated, where only image to object association is given. Given this setup, a novel surrogate task for self-supervised learning is proposed by pursuing "object invariant" representation. This is solved by randomly selecting an image feature of an object as object prototype, accompanied with multiview consistency regularization, which results in view invariant stochastic prototype embedding (VISPE). Experiments shows that the recognition and retrieval results using VISPE outperform that of other self-supervised learning methods on seen and unseen data. VISPE can also be applied to semi-supervised scenario and demonstrates robust performance with limited data available. Code is available at https://github.com/chihhuiho/VISPE.

Contrastive learning (CL) is a popular technique for self-supervised learning (SSL) of visual representations. It uses pairs of augmentations of unlabeled training examples to define a classification task for pretext learning of a deep embedding. Despite extensive works in augmentation procedures, prior works do not address the selection of challenging negative pairs, as images within a sampled batch are treated independently. This paper addresses the problem, by introducing a new family of adversarial examples for constrastive learning and using these examples to define a new adversarial training algorithm for SSL, denoted as CLAE. When compared to standard CL, the use of adversarial examples creates more challenging positive pairs and adversarial training produces harder negative pairs by accounting for all images in a batch during the optimization. CLAE is compatible with many CL methods in the literature. Experiments show that it improves the performance of several existing CL baselines on multiple datasets.

The problem of adversarial CNN attacks is considered, with an emphasis on attacks that are trivial to perform but difficult to defend. A framework for the study of such attacks is proposed, using real world object manipulations. Unlike most works in the past, this framework supports the design of attacks based on both small and large image perturbations, implemented by camera shake and pose variation. A setup is proposed for the collection of such perturbations and determination of their perceptibility. It is argued that perceptibility depends on context, and a distinction is made between imperceptible and semantically imperceptible perturbations. While the former survives image comparisons, the latter are perceptible but have no impact on human object recognition. A procedure is proposed to determine the perceptibility of perturbations using Turk experiments, and a dataset of both perturbation classes which enables replicable studies of object manipulation attacks, is assembled. Experiments using defenses based on many datasets, CNN models, and algorithms from the literature elucidate the difficulty of defending these attacks -- in fact, none of the existing defenses is found effective against them. Better results are achieved with real world data augmentation, but even this is not foolproof. These results confirm the hypothesis that current CNNs are vulnerable to attacks implementable even by a child, and that such attacks may prove difficult to defend.

The role of pose invariance in image recognition and retrieval is studied. A taxonomic classification of embeddings, according to their level of invariance, is introduced and used to clarify connections between existing embeddings, identify missing approaches, and propose invariant generalizations. This leads to a new family of pose invariant embeddings (PIEs), derived from existing approaches by a combination of two models, which follow from the interpretation of CNNs as estimators of class posterior probabilities: a view-to-object model and an object-to-class model. The new pose-invariant models are shown to have interesting properties, both theoretically and through experiments, where they outperform existing multiview approaches. Most notably, they achieve good performance for both 1) classification and retrieval, and 2) single and multiview inference. These are important properties for the design of real vision systems, where universal embeddings are preferable to task specific ones, and multiple images are usually not available at inference time. Finally, a new multiview dataset of real objects, imaged in the wild against complex backgrounds, is introduced. We believe that this is a much needed complement to the synthetic datasets in wide use and will contribute to the advancement of multiview recognition and retrieval.