Xin Feng

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.

Xin Feng, Yifeng Xu, Guangming Lu et al.

Effective image restoration with large-size corruptions, such as blind image inpainting, entails precise detection of corruption region masks which remains extremely challenging due to diverse shapes and patterns of corruptions. In this work, we present a novel method for automatic corruption detection, which allows for blind corruption restoration without known corruption masks. Specifically, we develop a hierarchical contrastive learning framework to detect corrupted regions by capturing the intrinsic semantic distinctions between corrupted and uncorrupted regions. In particular, our model detects the corrupted mask in a coarse-to-fine manner by first predicting a coarse mask by contrastive learning in low-resolution feature space and then refines the uncertain area of the mask by high-resolution contrastive learning. A specialized hierarchical interaction mechanism is designed to facilitate the knowledge propagation of contrastive learning in different scales, boosting the modeling performance substantially. The detected multi-scale corruption masks are then leveraged to guide the corruption restoration. Detecting corrupted regions by learning the contrastive distinctions rather than the semantic patterns of corruptions, our model has well generalization ability across different corruption patterns. Extensive experiments demonstrate following merits of our model: 1) the superior performance over other methods on both corruption detection and various image restoration tasks including blind inpainting and watermark removal, and 2) strong generalization across different corruption patterns such as graffiti, random noise or other image content. Codes and trained weights are available at https://github.com/xyfJASON/HCL .

Wenjin Liu, Haoran Luo, Xin Feng et al.

Legal general intelligence (GI) refers to artificial intelligence (AI) that encompasses legal understanding, reasoning, and decision-making, simulating the expertise of legal experts across domains. However, existing benchmarks are result-oriented and fail to systematically evaluate the legal intelligence of large language models (LLMs), hindering the development of legal GI. To address this, we propose LexGenius, an expert-level Chinese legal benchmark for evaluating legal GI in LLMs. It follows a Dimension-Task-Ability framework, covering seven dimensions, eleven tasks, and twenty abilities. We use the recent legal cases and exam questions to create multiple-choice questions with a combination of manual and LLM reviews to reduce data leakage risks, ensuring accuracy and reliability through multiple rounds of checks. We evaluate 12 state-of-the-art LLMs using LexGenius and conduct an in-depth analysis. We find significant disparities across legal intelligence abilities for LLMs, with even the best LLMs lagging behind human legal professionals. We believe LexGenius can assess the legal intelligence abilities of LLMs and enhance legal GI development. Our project is available at https://github.com/QwenQKing/LexGenius.

Zhihao Li, Ming Lu, Xu Zhang et al.

Conventional cameras capture image irradiance on a sensor and convert it to RGB images using an image signal processor (ISP). The images can then be used for photography or visual computing tasks in a variety of applications, such as public safety surveillance and autonomous driving. One can argue that since RAW images contain all the captured information, the conversion of RAW to RGB using an ISP is not necessary for visual computing. In this paper, we propose a novel $ρ$-Vision framework to perform high-level semantic understanding and low-level compression using RAW images without the ISP subsystem used for decades. Considering the scarcity of available RAW image datasets, we first develop an unpaired CycleR2R network based on unsupervised CycleGAN to train modular unrolled ISP and inverse ISP (invISP) models using unpaired RAW and RGB images. We can then flexibly generate simulated RAW images (simRAW) using any existing RGB image dataset and finetune different models originally trained for the RGB domain to process real-world camera RAW images. We demonstrate object detection and image compression capabilities in RAW-domain using RAW-domain YOLOv3 and RAW image compressor (RIC) on snapshots from various cameras. Quantitative results reveal that RAW-domain task inference provides better detection accuracy and compression compared to RGB-domain processing. Furthermore, the proposed \r{ho}-Vision generalizes across various camera sensors and different task-specific models. Additional advantages of the proposed $ρ$-Vision that eliminates the ISP are the potential reductions in computations and processing times.

Wenjie Pei, Xin Feng, Canmiao Fu et al.

The key challenge of sequence representation learning is to capture the long-range temporal dependencies. Typical methods for supervised sequence representation learning are built upon recurrent neural networks to capture temporal dependencies. One potential limitation of these methods is that they only model one-order information interactions explicitly between adjacent time steps in a sequence, hence the high-order interactions between nonadjacent time steps are not fully exploited. It greatly limits the capability of modeling the long-range temporal dependencies since the temporal features learned by one-order interactions cannot be maintained for a long term due to temporal information dilution and gradient vanishing. To tackle this limitation, we propose the Non-local Recurrent Neural Memory (NRNM) for supervised sequence representation learning, which performs non-local operations \MR{by means of self-attention mechanism} to learn full-order interactions within a sliding temporal memory block and models global interactions between memory blocks in a gated recurrent manner. Consequently, our model is able to capture long-range dependencies. Besides, the latent high-level features contained in high-order interactions can be distilled by our model. We validate the effectiveness and generalization of our NRNM on three types of sequence applications across different modalities, including sequence classification, step-wise sequential prediction and sequence similarity learning. Our model compares favorably against other state-of-the-art methods specifically designed for each of these sequence applications.

Xin Feng, Haobo Ji, Wenjie Pei et al.

While the research on image background restoration from regular size of degraded images has achieved remarkable progress, restoring ultra high-resolution (e.g., 4K) images remains an extremely challenging task due to the explosion of computational complexity and memory usage, as well as the deficiency of annotated data. In this paper we present a novel model for ultra high-resolution image restoration, referred to as the Global-Local Stepwise Generative Network (GLSGN), which employs a stepwise restoring strategy involving four restoring pathways: three local pathways and one global pathway. The local pathways focus on conducting image restoration in a fine-grained manner over local but high-resolution image patches, while the global pathway performs image restoration coarsely on the scale-down but intact image to provide cues for the local pathways in a global view including semantics and noise patterns. To smooth the mutual collaboration between these four pathways, our GLSGN is designed to ensure the inter-pathway consistency in four aspects in terms of low-level content, perceptual attention, restoring intensity and high-level semantics, respectively. As another major contribution of this work, we also introduce the first ultra high-resolution dataset to date for both reflection removal and rain streak removal, comprising 4,670 real-world and synthetic images. Extensive experiments across three typical tasks for image background restoration, including image reflection removal, image rain streak removal and image dehazing, show that our GLSGN consistently outperforms state-of-the-art methods.

Bin Chen, Ran Wang, Di Ming et al.

Recent advances of Transformers have brought new trust to computer vision tasks. However, on small dataset, Transformers is hard to train and has lower performance than convolutional neural networks. We make vision transformers as data-efficient as convolutional neural networks by introducing multi-focal attention bias. Inspired by the attention distance in a well-trained ViT, we constrain the self-attention of ViT to have multi-scale localized receptive field. The size of receptive field is adaptable during training so that optimal configuration can be learned. We provide empirical evidence that proper constrain of receptive field can reduce the amount of training data for vision transformers. On Cifar100, our ViT-P Base model achieves the state-of-the-art accuracy (83.16%) trained from scratch. We also perform analysis on ImageNet to show our method does not lose accuracy on large data sets.

Fengjun Li, Xin Feng, Fanglin Chen et al.

Typical methods for blind image super-resolution (SR) focus on dealing with unknown degradations by directly estimating them or learning the degradation representations in a latent space. A potential limitation of these methods is that they assume the unknown degradations can be simulated by the integration of various handcrafted degradations (e.g., bicubic downsampling), which is not necessarily true. The real-world degradations can be beyond the simulation scope by the handcrafted degradations, which are referred to as novel degradations. In this work, we propose to learn a latent representation space for degradations, which can be generalized from handcrafted (base) degradations to novel degradations. The obtained representations for a novel degradation in this latent space are then leveraged to generate degraded images consistent with the novel degradation to compose paired training data for SR model. Furthermore, we perform variational inference to match the posterior of degradations in latent representation space with a prior distribution (e.g., Gaussian distribution). Consequently, we are able to sample more high-quality representations for a novel degradation to augment the training data for SR model. We conduct extensive experiments on both synthetic and real-world datasets to validate the effectiveness and advantages of our method for blind super-resolution with novel degradations.

Xin Feng

This paper develops a multipole expansion method for the quasi-periodic elastic single layer potential $\mathcal{S}_D^{α,0}$ associated with the Kelvin tensor in one-dimensional periodic arrays. A key step in this approach is the derivation of translation addition theorems for the real vector spherical harmonics $V_{lm}$, $W_{lm}$, and $X_{lm}$. These addition theorems enable the exact calculation of all matrix entries of $\mathcal{S}_D^{α,0}$ in closed form. By working entirely within the spherical harmonic basis, the proposed analytical method overcomes the poor convergence and mesh-dependent issues commonly caused by the direct surface discretization of weakly singular kernels. Additionally, the involved infinite sums are evaluated exactly using polylogarithm functions, which eliminates the need for series truncation. As an application, the integral equation $\mathcal{S}_D^{α,0}[f]=φ$ is reduced to a linear system. This framework is further extended to dimer geometries consisting of two disjoint balls in each cell, where the off-diagonal matrices are explicitly formulated via the Lerch transcendent.

Zeyu Chen, Pengfei Zhang, Kai Ye et al.

The burgeoning short video industry has accelerated the advancement of video-music retrieval technology, assisting content creators in selecting appropriate music for their videos. In self-supervised training for video-to-music retrieval, the video and music samples in the dataset are separated from the same video work, so they are all one-to-one matches. This does not match the real situation. In reality, a video can use different music as background music, and a music can be used as background music for different videos. Many videos and music that are not in a pair may be compatible, leading to false negative noise in the dataset. A novel inter-intra modal (II) loss is proposed as a solution. By reducing the variation of feature distribution within the two modalities before and after the encoder, II loss can reduce the model's overfitting to such noise without removing it in a costly and laborious way. The video-music retrieval framework, II-CLVM (Contrastive Learning for Video-Music Retrieval), incorporating the II Loss, achieves state-of-the-art performance on the YouTube8M dataset. The framework II-CLVTM shows better performance when retrieving music using multi-modal video information (such as text in videos). Experiments are designed to show that II loss can effectively alleviate the problem of false negative noise in retrieval tasks. Experiments also show that II loss improves various self-supervised and supervised uni-modal and cross-modal retrieval tasks, and can obtain good retrieval models with a small amount of training samples.

Qian Wan, Xin Feng, Yining Bei et al.

Human emotions are essentially molded by lived experiences, from which we construct personalised meaning. The engagement in such meaning-making process has been practiced as an intervention in various psychotherapies to promote wellness. Nevertheless, to support recollecting and recounting lived experiences in everyday life remains under explored in HCI. It also remains unknown how technologies such as generative AI models can facilitate the meaning making process, and ultimately support affective mindfulness. In this paper we present Metamorpheus, an affective interface that engages users in a creative visual storytelling of emotional experiences during dreams. Metamorpheus arranges the storyline based on a dream's emotional arc, and provokes self-reflection through the creation of metaphorical images and text depictions. The system provides metaphor suggestions, and generates visual metaphors and text depictions using generative AI models, while users can apply generations to recolour and re-arrange the interface to be visually affective. Our experience-centred evaluation manifests that, by interacting with Metamorpheus, users can recall their dreams in vivid detail, through which they relive and reflect upon their experiences in a meaningful way.

Xin Feng, Yi Jiang, Jia-Xian Qin et al.

The wave equation is an important physical partial differential equation, and in recent years, deep learning has shown promise in accelerating or replacing traditional numerical methods for solving it. However, existing deep learning methods suffer from high data acquisition costs, low training efficiency, and insufficient generalization capability for boundary conditions. To address these issues, this paper proposes an unsupervised learning method for the wave equation based on finite difference residual constraints. We construct a novel finite difference residual constraint based on structured grids and finite difference methods, as well as an unsupervised training strategy, enabling convolutional neural networks to train without data and predict the forward propagation process of waves. Experimental results show that finite difference residual constraints have advantages over physics-informed neural networks (PINNs) type physical information constraints, such as easier fitting, lower computational costs, and stronger source term generalization capability, making our method more efficient in training and potent in application.

Haobo Ji, Xin Feng, Wenjie Pei et al.

While Transformer has achieved remarkable performance in various high-level vision tasks, it is still challenging to exploit the full potential of Transformer in image restoration. The crux lies in the limited depth of applying Transformer in the typical encoder-decoder framework for image restoration, resulting from heavy self-attention computation load and inefficient communications across different depth (scales) of layers. In this paper, we present a deep and effective Transformer-based network for image restoration, termed as U2-Former, which is able to employ Transformer as the core operation to perform image restoration in a deep encoding and decoding space. Specifically, it leverages the nested U-shaped structure to facilitate the interactions across different layers with different scales of feature maps. Furthermore, we optimize the computational efficiency for the basic Transformer block by introducing a feature-filtering mechanism to compress the token representation. Apart from the typical supervision ways for image restoration, our U2-Former also performs contrastive learning in multiple aspects to further decouple the noise component from the background image. Extensive experiments on various image restoration tasks, including reflection removal, rain streak removal and dehazing respectively, demonstrate the effectiveness of the proposed U2-Former.

Huijun Liu, Chunhua Yang, Ao Li et al.

Deep learning-based pavement cracks detection methods often require large-scale labels with detailed crack location information to learn accurate predictions. In practice, however, crack locations are very difficult to be manually annotated due to various visual patterns of pavement crack. In this paper, we propose a Deep Domain Adaptation-based Crack Detection Network (DDACDN), which learns domain invariant features by taking advantage of the source domain knowledge to predict the multi-category crack location information in the target domain, where only image-level labels are available. Specifically, DDACDN first extracts crack features from both the source and target domain by a two-branch weights-shared backbone network. And in an effort to achieve the cross-domain adaptation, an intermediate domain is constructed by aggregating the three-scale features from the feature space of each domain to adapt the crack features from the source domain to the target domain. Finally, the network involves the knowledge of both domains and is trained to recognize and localize pavement cracks. To facilitate accurate training and validation for domain adaptation, we use two challenging pavement crack datasets CQU-BPDD and RDD2020. Furthermore, we construct a new large-scale Bituminous Pavement Multi-label Disease Dataset named CQU-BPMDD, which contains 38994 high-resolution pavement disease images to further evaluate the robustness of our model. Extensive experiments demonstrate that DDACDN outperforms state-of-the-art pavement crack detection methods in predicting the crack location on the target domain.

Xin Feng, Wenjie Pei, Fengjun Li et al.

Most existing methods for image inpainting focus on learning the intra-image priors from the known regions of the current input image to infer the content of the corrupted regions in the same image. While such methods perform well on images with small corrupted regions, it is challenging for these methods to deal with images with large corrupted area due to two potential limitations: 1) such methods tend to overfit each single training pair of images relying solely on the intra-image prior knowledge learned from the limited known area; 2) the inter-image prior knowledge about the general distribution patterns of visual semantics, which can be transferred across images sharing similar semantics, is not exploited. In this paper, we propose the Generative Memory-Guided Semantic Reasoning Model (GM-SRM), which not only learns the intra-image priors from the known regions, but also distills the inter-image reasoning priors to infer the content of the corrupted regions. In particular, the proposed GM-SRM first pre-learns a generative memory from the whole training data to capture the semantic distribution patterns in a global view. Then the learned memory are leveraged to retrieve the matching inter-image priors for the current corrupted image to perform semantic reasoning during image inpainting. While the intra-image priors are used for guaranteeing the pixel-level content consistency, the inter-image priors are favorable for performing high-level semantic reasoning, which is particularly effective for inferring semantic content for large corrupted area. Extensive experiments on Paris Street View, CelebA-HQ, and Places2 benchmarks demonstrate that our GM-SRM outperforms the state-of-the-art methods for image inpainting in terms of both the visual quality and quantitative metrics.

Xin Feng, Wenjie Pei, Zihui Jia et al.

Restoring the clean background from the superimposed images containing a noisy layer is the common crux of a classical category of tasks on image restoration such as image reflection removal, image deraining and image dehazing. These tasks are typically formulated and tackled individually due to the diverse and complicated appearance patterns of noise layers within the image. In this work we present the Deep-Masking Generative Network (DMGN), which is a unified framework for background restoration from the superimposed images and is able to cope with different types of noise. Our proposed DMGN follows a coarse-to-fine generative process: a coarse background image and a noise image are first generated in parallel, then the noise image is further leveraged to refine the background image to achieve a higher-quality background image. In particular, we design the novel Residual Deep-Masking Cell as the core operating unit for our DMGN to enhance the effective information and suppress the negative information during image generation via learning a gating mask to control the information flow. By iteratively employing this Residual Deep-Masking Cell, our proposed DMGN is able to generate both high-quality background image and noisy image progressively. Furthermore, we propose a two-pronged strategy to effectively leverage the generated noise image as contrasting cues to facilitate the refinement of the background image. Extensive experiments across three typical tasks for image background restoration, including image reflection removal, image rain steak removal and image dehazing, show that our DMGN consistently outperforms state-of-the-art methods specifically designed for each single task.

Chao Tan, Xin Feng

Unsupervised shadow removal aims to learn a non-linear function to map the original image from shadow domain to non-shadow domain in the absence of paired shadow and non-shadow data. In this paper, we develop a simple yet efficient target-consistency generative adversarial network (TC-GAN) for the shadow removal task in the unsupervised manner. Compared with the bidirectional mapping in cycle-consistency GAN based methods for shadow removal, TC-GAN tries to learn a one-sided mapping to cast shadow images into shadow-free ones. With the proposed target-consistency constraint, the correlations between shadow images and the output shadow-free image are strictly confined. Extensive comparison experiments results show that TC-GAN outperforms the state-of-the-art unsupervised shadow removal methods by 14.9% in terms of FID and 31.5% in terms of KID. It is rather remarkable that TC-GAN achieves comparable performance with supervised shadow removal methods.

Xin Feng, Lei Wang

In this paper, we present how to hybridize a Word2vec model and an attention-based end-to-end speech recognition model. We build a phoneme recognition system based on Listen, Attend and Spell model. And the phoneme recognition model uses a word2vec model to initialize the embedding matrix for the improvement of the performance, which can increase the distance among the phoneme vectors. At the same time, in order to solve the problem of overfitting in the 61 phoneme recognition model on TIMIT dataset, we propose a new training method. A 61-39 phoneme mapping comparison table is used to inverse map the phonemes of the dataset to generate more 61 phoneme training data. At the end of training, replace the dataset with a standard dataset for corrective training. Our model can achieve the best result under the TIMIT dataset which is 16.5% PER (Phoneme Error Rate).

Chao Tan, Xin Feng, Jianwu Long et al.

With the highly demand of large-scale and real-time weather service for public, a refinement of short-time cloudage prediction has become an essential part of the weather forecast productions. To provide a weather-service-compliant cloudage nowcasting, in this paper, we propose a novel hierarchical Convolutional Long-Short-Term Memory network based deep learning model, which we term as FORECAST-CLSTM, with a new Forecaster loss function to predict the future satellite cloud images. The model is designed to fuse multi-scale features in the hierarchical network structure to predict the pixel value and the morphological movement of the cloudage simultaneously. We also collect about 40K infrared satellite nephograms and create a large-scale Satellite Cloudage Map Dataset(SCMD). The proposed FORECAST-CLSTM model is shown to achieve better prediction performance compared with the state-of-the-art ConvLSTM model and the proposed Forecaster Loss Function is also demonstrated to retain the uncertainty of the real atmosphere condition better than conventional loss function.

Chenge Li, Gregory Dobler, Xin Feng et al.

Object detection and object tracking are usually treated as two separate processes. Significant progress has been made for object detection in 2D images using deep learning networks. The usual tracking-by-detection pipeline for object tracking requires that the object is successfully detected in the first frame and all subsequent frames, and tracking is done by associating detection results. Performing object detection and object tracking through a single network remains a challenging open question. We propose a novel network structure named trackNet that can directly detect a 3D tube enclosing a moving object in a video segment by extending the faster R-CNN framework. A Tube Proposal Network (TPN) inside the trackNet is proposed to predict the objectness of each candidate tube and location parameters specifying the bounding tube. The proposed framework is applicable for detecting and tracking any object and in this paper, we focus on its application for traffic video analysis. The proposed model is trained and tested on UA-DETRAC, a large traffic video dataset available for multi-vehicle detection and tracking, and obtained very promising results.

Shaohua Wang, Song Gao, Xin Feng et al.

Given different types of constraints on human life, people must make decisions that satisfy social activity needs. Minimizing costs (i.e., distance, time, or money) associated with travel plays an important role in perceived and realized social quality of life. Identifying optimal interaction locations on road networks when there are multiple moving objects (MMO) with space-time constraints remains a challenge. In this research, we formalize the problem of finding dynamic ideal interaction locations for MMO as a spatial optimization model and introduce a context-based geoprocessing heuristic framework to address this problem. As a proof of concept, a case study involving identification of a meetup location for multiple people under traffic conditions is used to validate the proposed geoprocessing framework. Five heuristic methods with regard to efficient shortest-path search space have been tested. We find that the R* tree-based algorithm performs the best with high quality solutions and low computation time. This framework is implemented in a GIS environment to facilitate integration with external geographic contextual information, e.g., temporary road barriers, points of interest (POI), and real-time traffic information, when dynamically searching for ideal meetup sites. The proposed method can be applied in trip planning, carpooling services, collaborative interaction, and logistics management.

Chuanyun Xu, Yang Zhang, Xin Feng et al.

Learning a deep model from small data is yet an opening and challenging problem. We focus on one-shot classification by deep learning approach based on a small quantity of training samples. We proposed a novel deep learning approach named Local Contrast Learning (LCL) based on the key insight about a human cognitive behavior that human recognizes the objects in a specific context by contrasting the objects in the context or in her/his memory. LCL is used to train a deep model that can contrast the recognizing sample with a couple of contrastive samples randomly drawn and shuffled. On one-shot classification task on Omniglot, the deep model based LCL with 122 layers and 1.94 millions of parameters, which was trained on a tiny dataset with only 60 classes and 20 samples per class, achieved the accuracy 97.99% that outperforms human and state-of-the-art established by Bayesian Program Learning (BPL) trained on 964 classes. LCL is a fundamental idea which can be applied to alleviate parametric model's overfitting resulted by lack of training samples.