Ayush Jaiswal

Amazon AGI, Aaron Langford, Aayush Shah et al. · amazon-science

We present Amazon Nova, a new generation of state-of-the-art foundation models that deliver frontier intelligence and industry-leading price performance. Amazon Nova Pro is a highly-capable multimodal model with the best combination of accuracy, speed, and cost for a wide range of tasks. Amazon Nova Lite is a low-cost multimodal model that is lightning fast for processing images, video, documents and text. Amazon Nova Micro is a text-only model that delivers our lowest-latency responses at very low cost. Amazon Nova Canvas is an image generation model that creates professional grade images with rich customization controls. Amazon Nova Reel is a video generation model offering high-quality outputs, customization, and motion control. Our models were built responsibly and with a commitment to customer trust, security, and reliability. We report benchmarking results for core capabilities, agentic performance, long context, functional adaptation, runtime performance, and human evaluation.

Anwesan Pal, Sahil Wadhwa, Ayush Jaiswal et al.

Multi-turn textual feedback-based fashion image retrieval focuses on a real-world setting, where users can iteratively provide information to refine retrieval results until they find an item that fits all their requirements. In this work, we present a novel memory-based method, called FashionNTM, for such a multi-turn system. Our framework incorporates a new Cascaded Memory Neural Turing Machine (CM-NTM) approach for implicit state management, thereby learning to integrate information across all past turns to retrieve new images, for a given turn. Unlike vanilla Neural Turing Machine (NTM), our CM-NTM operates on multiple inputs, which interact with their respective memories via individual read and write heads, to learn complex relationships. Extensive evaluation results show that our proposed method outperforms the previous state-of-the-art algorithm by 50.5%, on Multi-turn FashionIQ -- the only existing multi-turn fashion dataset currently, in addition to having a relative improvement of 12.6% on Multi-turn Shoes -- an extension of the single-turn Shoes dataset that we created in this work. Further analysis of the model in a real-world interactive setting demonstrates two important capabilities of our model -- memory retention across turns, and agnosticity to turn order for non-contradictory feedback. Finally, user study results show that images retrieved by FashionNTM were favored by 83.1% over other multi-turn models. Project page: https://sites.google.com/eng.ucsd.edu/fashionntm

Jiaxin Cheng, Ayush Jaiswal, Yue Wu et al.

Neural Style Transfer (NST) has quickly evolved from single-style to infinite-style models, also known as Arbitrary Style Transfer (AST). Although appealing results have been widely reported in literature, our empirical studies on four well-known AST approaches (GoogleMagenta, AdaIN, LinearTransfer, and SANet) show that more than 50% of the time, AST stylized images are not acceptable to human users, typically due to under- or over-stylization. We systematically study the cause of this imbalanced style transferability (IST) and propose a simple yet effective solution to mitigate this issue. Our studies show that the IST issue is related to the conventional AST style loss, and reveal that the root cause is the equal weightage of training samples irrespective of the properties of their corresponding style images, which biases the model towards certain styles. Through investigation of the theoretical bounds of the AST style loss, we propose a new loss that largely overcomes IST. Theoretical analysis and experimental results validate the effectiveness of our loss, with over 80% relative improvement in style deception rate and 98% relatively higher preference in human evaluation.

Ayush Jaiswal, Yue Wu, Pradeep Natarajan et al.

Object detection models perform well at localizing and classifying objects that they are shown during training. However, due to the difficulty and cost associated with creating and annotating detection datasets, trained models detect a limited number of object types with unknown objects treated as background content. This hinders the adoption of conventional detectors in real-world applications like large-scale object matching, visual grounding, visual relation prediction, obstacle detection (where it is more important to determine the presence and location of objects than to find specific types), etc. We propose class-agnostic object detection as a new problem that focuses on detecting objects irrespective of their object-classes. Specifically, the goal is to predict bounding boxes for all objects in an image but not their object-classes. The predicted boxes can then be consumed by another system to perform application-specific classification, retrieval, etc. We propose training and evaluation protocols for benchmarking class-agnostic detectors to advance future research in this domain. Finally, we propose (1) baseline methods and (2) a new adversarial learning framework for class-agnostic detection that forces the model to exclude class-specific information from features used for predictions. Experimental results show that adversarial learning improves class-agnostic detection efficacy.

Ekraam Sabir, Ayush Jaiswal, Wael AbdAlmageed et al.

Fake news often involves semantic manipulations across modalities such as image, text, location etc and requires the development of multimodal semantic forensics for its detection. Recent research has centered the problem around images, calling it image repurposing -- where a digitally unmanipulated image is semantically misrepresented by means of its accompanying multimodal metadata such as captions, location, etc. The image and metadata together comprise a multimedia package. The problem setup requires algorithms to perform multimodal semantic forensics to authenticate a query multimedia package using a reference dataset of potentially related packages as evidences. Existing methods are limited to using a single evidence (retrieved package), which ignores potential performance improvement from the use of multiple evidences. In this work, we introduce a novel graph neural network based model for multimodal semantic forensics, which effectively utilizes multiple retrieved packages as evidences and is scalable with the number of evidences. We compare the scalability and performance of our model against existing methods. Experimental results show that the proposed model outperforms existing state-of-the-art algorithms with an error reduction of up to 25%.

Xiao Guo, Hengameh Mirzaalian, Ekraam Sabir et al.

In order to combat the COVID-19 pandemic, society can benefit from various natural language processing applications, such as dialog medical diagnosis systems and information retrieval engines calibrated specifically for COVID-19. These applications rely on the ability to measure semantic textual similarity (STS), making STS a fundamental task that can benefit several downstream applications. However, existing STS datasets and models fail to translate their performance to a domain-specific environment such as COVID-19. To overcome this gap, we introduce CORD19STS dataset which includes 13,710 annotated sentence pairs collected from COVID-19 open research dataset (CORD-19) challenge. To be specific, we generated one million sentence pairs using different sampling strategies. We then used a finetuned BERT-like language model, which we call Sen-SCI-CORD19-BERT, to calculate the similarity scores between sentence pairs to provide a balanced dataset with respect to the different semantic similarity levels, which gives us a total of 32K sentence pairs. Each sentence pair was annotated by five Amazon Mechanical Turk (AMT) crowd workers, where the labels represent different semantic similarity levels between the sentence pairs (i.e. related, somewhat-related, and not-related). After employing a rigorous qualification tasks to verify collected annotations, our final CORD19STS dataset includes 13,710 sentence pairs.

Ayush Jaiswal, Rob Brekelmans, Daniel Moyer et al.

Supervised machine learning models often associate irrelevant nuisance factors with the prediction target, which hurts generalization. We propose a framework for training robust neural networks that induces invariance to nuisances through learning to discover and separate predictive and nuisance factors of data. We present an information theoretic formulation of our approach, from which we derive training objectives and its connections with previous methods. Empirical results on a wide array of datasets show that the proposed framework achieves state-of-the-art performance, without requiring nuisance annotations during training.

Ayush Jaiswal, Daniel Moyer, Greg Ver Steeg et al.

We propose a novel approach to achieving invariance for deep neural networks in the form of inducing amnesia to unwanted factors of data through a new adversarial forgetting mechanism. We show that the forgetting mechanism serves as an information-bottleneck, which is manipulated by the adversarial training to learn invariance to unwanted factors. Empirical results show that the proposed framework achieves state-of-the-art performance at learning invariance in both nuisance and bias settings on a diverse collection of datasets and tasks.

I-Hung Hsu, Ayush Jaiswal, Premkumar Natarajan

Deep neural network models for speech recognition have achieved great success recently, but they can learn incorrect associations between the target and nuisance factors of speech (e.g., speaker identities, background noise, etc.), which can lead to overfitting. While several methods have been proposed to tackle this problem, existing methods incorporate additional information about nuisance factors during training to develop invariant models. However, enumeration of all possible nuisance factors in speech data and the collection of their annotations is difficult and expensive. We present a robust training scheme for end-to-end speech recognition that adopts an unsupervised adversarial invariance induction framework to separate out essential factors for speech-recognition from nuisances without using any supplementary labels besides the transcriptions. Experiments show that the speech recognition model trained with the proposed training scheme achieves relative improvements of 5.48% on WSJ0, 6.16% on CHiME3, and 6.61% on TIMIT dataset over the base model. Additionally, the proposed method achieves a relative improvement of 14.44% on the combined WSJ0+CHiME3 dataset.

Ayush Jaiswal, Yue Wu, Wael AbdAlmageed et al.

We present a unified invariance framework for supervised neural networks that can induce independence to nuisance factors of data without using any nuisance annotations, but can additionally use labeled information about biasing factors to force their removal from the latent embedding for making fair predictions. Invariance to nuisance is achieved by learning a split representation of data through competitive training between the prediction task and a reconstruction task coupled with disentanglement, whereas that to biasing factors is brought about by penalizing the network if the latent embedding contains any information about them. We describe an adversarial instantiation of this framework and provide analysis of its working. Our model outperforms previous works at inducing invariance to nuisance factors without using any labeled information about such variables, and achieves state-of-the-art performance at learning independence to biasing factors in fairness settings.

Ekraam Sabir, Jiaxin Cheng, Ayush Jaiswal et al.

The spread of misinformation through synthetically generated yet realistic images and videos has become a significant problem, calling for robust manipulation detection methods. Despite the predominant effort of detecting face manipulation in still images, less attention has been paid to the identification of tampered faces in videos by taking advantage of the temporal information present in the stream. Recurrent convolutional models are a class of deep learning models which have proven effective at exploiting the temporal information from image streams across domains. We thereby distill the best strategy for combining variations in these models along with domain specific face preprocessing techniques through extensive experimentation to obtain state-of-the-art performance on publicly available video-based facial manipulation benchmarks. Specifically, we attempt to detect Deepfake, Face2Face and FaceSwap tampered faces in video streams. Evaluation is performed on the recently introduced FaceForensics++ dataset, improving the previous state-of-the-art by up to 4.55% in accuracy.

Ayush Jaiswal, Shuai Xia, Iacopo Masi et al.

For enterprise, personal and societal applications, there is now an increasing demand for automated authentication of identity from images using computer vision. However, current authentication technologies are still vulnerable to presentation attacks. We present RoPAD, an end-to-end deep learning model for presentation attack detection that employs unsupervised adversarial invariance to ignore visual distractors in images for increased robustness and reduced overfitting. Experiments show that the proposed framework exhibits state-of-the-art performance on presentation attack detection on several benchmark datasets.

Ayush Jaiswal, Yue Wu, Wael AbdAlmageed et al.

Image repurposing is a commonly used method for spreading misinformation on social media and online forums, which involves publishing untampered images with modified metadata to create rumors and further propaganda. While manual verification is possible, given vast amounts of verified knowledge available on the internet, the increasing prevalence and ease of this form of semantic manipulation call for the development of robust automatic ways of assessing the semantic integrity of multimedia data. In this paper, we present a novel method for image repurposing detection that is based on the real-world adversarial interplay between a bad actor who repurposes images with counterfeit metadata and a watchdog who verifies the semantic consistency between images and their accompanying metadata, where both players have access to a reference dataset of verified content, which they can use to achieve their goals. The proposed method exhibits state-of-the-art performance on location-identity, subject-identity and painting-artist verification, showing its efficacy across a diverse set of scenarios.

Ayush Jaiswal, Yue Wu, Wael AbdAlmageed et al.

Data representations that contain all the information about target variables but are invariant to nuisance factors benefit supervised learning algorithms by preventing them from learning associations between these factors and the targets, thus reducing overfitting. We present a novel unsupervised invariance induction framework for neural networks that learns a split representation of data through competitive training between the prediction task and a reconstruction task coupled with disentanglement, without needing any labeled information about nuisance factors or domain knowledge. We describe an adversarial instantiation of this framework and provide analysis of its working. Our unsupervised model outperforms state-of-the-art methods, which are supervised, at inducing invariance to inherent nuisance factors, effectively using synthetic data augmentation to learn invariance, and domain adaptation. Our method can be applied to any prediction task, eg., binary/multi-class classification or regression, without loss of generality.

Ayush Jaiswal, Dong Guo, Cauligi S. Raghavendra et al.

Machine Learning (ML) is increasingly being used for computer aided diagnosis of brain related disorders based on structural magnetic resonance imaging (MRI) data. Most of such work employs biologically and medically meaningful hand-crafted features calculated from different regions of the brain. The construction of such highly specialized features requires a considerable amount of time, manual oversight and careful quality control to ensure the absence of errors in the computational process. Recent advances in Deep Representation Learning have shown great promise in extracting highly non-linear and information-rich features from data. In this paper, we present a novel large-scale deep unsupervised approach to learn generic feature representations of structural brain MRI scans, which requires no specialized domain knowledge or manual intervention. Our method produces low-dimensional representations of brain structure, which can be used to reconstruct brain images with very low error and exhibit performance comparable to FreeSurfer features on various classification tasks.

Ayush Jaiswal, Wael AbdAlmageed, Yue Wu et al.

We present Generative Adversarial Capsule Network (CapsuleGAN), a framework that uses capsule networks (CapsNets) instead of the standard convolutional neural networks (CNNs) as discriminators within the generative adversarial network (GAN) setting, while modeling image data. We provide guidelines for designing CapsNet discriminators and the updated GAN objective function, which incorporates the CapsNet margin loss, for training CapsuleGAN models. We show that CapsuleGAN outperforms convolutional-GAN at modeling image data distribution on MNIST and CIFAR-10 datasets, evaluated on the generative adversarial metric and at semi-supervised image classification.

Ayush Jaiswal, Wael AbdAlmageed, Yue Wu et al.

Conditional Generative Adversarial Networks (cGANs) are generative models that can produce data samples ($x$) conditioned on both latent variables ($z$) and known auxiliary information ($c$). We propose the Bidirectional cGAN (BiCoGAN), which effectively disentangles $z$ and $c$ in the generation process and provides an encoder that learns inverse mappings from $x$ to both $z$ and $c$, trained jointly with the generator and the discriminator. We present crucial techniques for training BiCoGANs, which involve an extrinsic factor loss along with an associated dynamically-tuned importance weight. As compared to other encoder-based cGANs, BiCoGANs encode $c$ more accurately, and utilize $z$ and $c$ more effectively and in a more disentangled way to generate samples.

Ayush Jaiswal, Ekraam Sabir, Wael AbdAlmageed et al.

Real world multimedia data is often composed of multiple modalities such as an image or a video with associated text (e.g. captions, user comments, etc.) and metadata. Such multimodal data packages are prone to manipulations, where a subset of these modalities can be altered to misrepresent or repurpose data packages, with possible malicious intent. It is, therefore, important to develop methods to assess or verify the integrity of these multimedia packages. Using computer vision and natural language processing methods to directly compare the image (or video) and the associated caption to verify the integrity of a media package is only possible for a limited set of objects and scenes. In this paper, we present a novel deep learning-based approach for assessing the semantic integrity of multimedia packages containing images and captions, using a reference set of multimedia packages. We construct a joint embedding of images and captions with deep multimodal representation learning on the reference dataset in a framework that also provides image-caption consistency scores (ICCSs). The integrity of query media packages is assessed as the inlierness of the query ICCSs with respect to the reference dataset. We present the MultimodAl Information Manipulation dataset (MAIM), a new dataset of media packages from Flickr, which we make available to the research community. We use both the newly created dataset as well as Flickr30K and MS COCO datasets to quantitatively evaluate our proposed approach. The reference dataset does not contain unmanipulated versions of tampered query packages. Our method is able to achieve F1 scores of 0.75, 0.89 and 0.94 on MAIM, Flickr30K and MS COCO, respectively, for detecting semantically incoherent media packages.