Search Results for author:
Found 89 papers, 44 papers with code
Differentiable Product Quantization for Learning Compact Embedding Layers
Embedding layers are commonly used to map discrete symbols into continuous embedding vectors that reflect their semantic meanings.
MURAL: Multimodal, Multitask Representations Across Languages
Both image-caption pairs and translation pairs provide the means to learn deep representations of and connections between languages.
RareAgents: Autonomous Multi-disciplinary Team for Rare Disease Diagnosis and Treatment
Rare diseases, despite their low individual incidence, collectively impact around 300 million people worldwide due to the huge number of diseases.
Large-scale cross-modality pretrained model enhances cardiovascular state estimation and cardiomyopathy detection from electrocardiograms: An AI system development and multi-center validation study
Cardiovascular diseases (CVDs) present significant challenges for early and accurate diagnosis.
All-in-one Weather-degraded Image Restoration via Adaptive Degradation-aware Self-prompting Model
Specifically, our model employs the contrastive language-image pre-training model (CLIP) to facilitate the training of our proposed latent prompt generators (LPGs), which represent three types of latent prompts to characterize the degradation type, degradation property and image caption.
VividMed: Vision Language Model with Versatile Visual Grounding for Medicine
For instance, most VLMs rely on a single method of visual grounding, whereas complex medical tasks demand more versatile approaches.
RMCBench: Benchmarking Large Language Models' Resistance to Malicious Code
Despite their benefits, LLMs also pose notable risks, including the potential to generate harmful content and being abused by malicious developers to create malicious code.
CoPRA: Bridging Cross-domain Pretrained Sequence Models with Complex Structures for Protein-RNA Binding Affinity Prediction
We propose a Co-Former to combine the cross-modal sequence and structure information and a bi-scope pre-training strategy for improving Co-Former's interaction understanding.
Unpaired Photo-realistic Image Deraining with Energy-informed Diffusion Model
In addition, we employ the rain-relevance discarding energy function (RDEF) and the rain-irrelevance preserving energy function (RPEF) to direct the reverse sampling procedure of a pre-trained diffusion model, effectively removing the rain streaks while preserving the image contents.
Layered Diffusion Model for One-Shot High Resolution Text-to-Image Synthesis
We present a one-shot text-to-image diffusion model that can generate high-resolution images from natural language descriptions.
HeMeNet: Heterogeneous Multichannel Equivariant Network for Protein Multitask Learning
In this paper, we propose a neural network model to address multiple tasks jointly upon the input of 3D protein structures.
RareBench: Can LLMs Serve as Rare Diseases Specialists?
Meanwhile, we have compiled the largest open-source dataset on rare disease patients, establishing a benchmark for future studies in this domain.
Automating Sound Change Prediction for Phylogenetic Inference: A Tukanoan Case Study
We describe a set of new methods to partially automate linguistic phylogenetic inference given (1) cognate sets with their respective protoforms and sound laws, (2) a mapping from phones to their articulatory features and (3) a typological database of sound changes.
Encoder-minimal and Decoder-minimal Framework for Remote Sensing Image Dehazing
Haze obscures remote sensing images, hindering valuable information extraction.
Building Universal Foundation Models for Medical Image Analysis with Spatially Adaptive Networks
In this work, we propose a universal foundation model for medical image analysis that processes images with heterogeneous spatial properties using a unified structure.
Perceptual Group Tokenizer: Building Perception with Iterative Grouping
In this paper, we propose the Perceptual Group Tokenizer, a model that entirely relies on grouping operations to extract visual features and perform self-supervised representation learning, where a series of grouping operations are used to iteratively hypothesize the context for pixels or superpixels to refine feature representations.
Ranked #25 on
Self-Supervised Image Classification
on ImageNet
Representation Learning
Self-Supervised Image Classification
+2
Towards A Unified Neural Architecture for Visual Recognition and Reasoning
Motivated by the recent success of multi-task transformers for visual recognition and language understanding, we propose a unified neural architecture for visual recognition and reasoning with a generic interface (e. g., tokens) for both.
Multi-dimension Queried and Interacting Network for Stereo Image Deraining
This module leverages dimension-wise queries that are independent of the input features and employs global context-aware attention (GCA) to capture essential features while avoiding the entanglement of redundant or irrelevant information.
HyperFormer: Learning Expressive Sparse Feature Representations via Hypergraph Transformer
Learning expressive representations for high-dimensional yet sparse features has been a longstanding problem in information retrieval.
FIT: Far-reaching Interleaved Transformers
We employ two types of transformer layers: local layers operate on data tokens within each group, while global layers operate on a smaller set of introduced latent tokens.
Towards an Effective and Efficient Transformer for Rain-by-snow Weather Removal
Rain-by-snow weather removal is a specialized task in weather-degraded image restoration aiming to eliminate coexisting rain streaks and snow particles.
On the Importance of Noise Scheduling for Diffusion Models
We empirically study the effect of noise scheduling strategies for denoising diffusion generative models.
Scalable Adaptive Computation for Iterative Generation
We show how to leverage recurrence by conditioning the latent tokens at each forward pass of the reverse diffusion process with those from prior computation, i. e. latent self-conditioning.
Ranked #5 on
Video Prediction
on Kinetics-600 12 frames, 64x64
An automated approach to extracting positive and negative clinical research results
Failure is common in clinical trials since the successful failures presented in negative results always indicate the ways that should not be taken.
DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detection
In this study, we propose an improved model called DeSTSeg, which integrates a pre-trained teacher network, a denoising student encoder-decoder, and a segmentation network into one framework.
Ranked #52 on
Anomaly Detection
on MVTec AD
A Generalist Framework for Panoptic Segmentation of Images and Videos
Panoptic segmentation assigns semantic and instance ID labels to every pixel of an image.
Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning
The main idea behind our approach is to first represent the discrete data as binary bits, and then train a continuous diffusion model to model these bits as real numbers which we call analog bits.
Ranked #7 on
Image Captioning
on MS COCO
Robust Learning of Deep Time Series Anomaly Detection Models with Contaminated Training Data
In this work, to tackle this important challenge, we firstly investigate the robustness of commonly used deep TSAD methods with contaminated training data which provides a guideline for applying these methods when the provided training data are not guaranteed to be anomaly-free.
DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization
We propose Diversity-Guided Policy Optimization (DGPO), an on-policy algorithm that discovers multiple strategies for solving a given task.
A Unified Sequence Interface for Vision Tasks
Despite that, by formulating the output of each task as a sequence of discrete tokens with a unified interface, we show that one can train a neural network with a single model architecture and loss function on all these tasks, with no task-specific customization.
Scalable Online Disease Diagnosis via Multi-Model-Fused Actor-Critic Reinforcement Learning
In the critic network, a supervised diagnosis model for disease predictions is involved to precisely estimate the state-value function.
Robust and Efficient Medical Imaging with Self-Supervision
These results suggest that REMEDIS can significantly accelerate the life-cycle of medical imaging AI development thereby presenting an important step forward for medical imaging AI to deliver broad impact.
From heavy rain removal to detail restoration: A faster and better network
This approach comprises two key modules, a rain streaks removal network (R$^2$Net) focusing on accurate rain removal, and a details reconstruction network (DRNet) designed to recover the textural details of rain-free images.
Auto robust relative radiometric normalization via latent change noise modelling
Relative radiometric normalization(RRN) of different satellite images of the same terrain is necessary for change detection, object classification/segmentation, and map-making tasks.
Improving Contrastive Learning on Imbalanced Seed Data via Open-World Sampling
Contrastive learning approaches have achieved great success in learning visual representations with few labels of the target classes.
Understanding and Improving Robustness of Vision Transformers through Patch-based Negative Augmentation
We show that patch-based negative augmentation consistently improves robustness of ViTs across a wide set of ImageNet based robustness benchmarks.
TiKick: Towards Playing Multi-agent Football Full Games from Single-agent Demonstrations
To the best of our knowledge, Tikick is the first learning-based AI system that can take over the multi-agent Google Research Football full game, while previous work could either control a single agent or experiment on toy academic scenarios.
Ranking Cost: Building An Efficient and Scalable Circuit Routing Planner with Evolution-Based Optimization
In this work, we propose a new algorithm for circuit routing, named Ranking Cost, which innovatively combines search-based methods (i. e., A* algorithm) and learning-based methods (i. e., Evolution Strategies) to form an efficient and trainable router.
Pix2seq: A Language Modeling Framework for Object Detection
We present Pix2Seq, a simple and generic framework for object detection.
Ranked #79 on
Object Detection
on COCO minival
(using extra training data)
MURAL: Multimodal, Multitask Retrieval Across Languages
Both image-caption pairs and translation pairs provide the means to learn deep representations of and connections between languages.
Ranked #1 on
Semantic Image-Text Similarity
on CxC
Improved Transformer for High-Resolution GANs
Attention-based models, exemplified by the Transformer, can effectively model long range dependency, but suffer from the quadratic complexity of self-attention operation, making them difficult to be adopted for high-resolution image generation based on Generative Adversarial Networks (GANs).
Ranked #2 on
Image Generation
on CelebA 256x256
(FID metric)
Nested Hierarchical Transformer: Towards Accurate, Data-Efficient and Interpretable Visual Understanding
Hierarchical structures are popular in recent vision transformers, however, they require sophisticated designs and massive datasets to work well.
Ranked #89 on
Image Classification
on CIFAR-10
Improving Contrastive Learning on Imbalanced Data via Open-World Sampling
Contrastive learning approaches have achieved great success in learning visual representations with few labels of the target classes.
StackVAE-G: An efficient and interpretable model for time series anomaly detection
We also leverage a graph learning module to learn a sparse adjacency matrix to explicitly capture the stable interrelation structure among multiple time series channels for the interpretable pattern reconstruction of interrelated channels.
Revisiting Hierarchical Approach for Persistent Long-Term Video Prediction
Despite the recent advances in the literature, existing approaches are limited to moderately short-term prediction (less than a few seconds), while extrapolating it to a longer future quickly leads to destruction in structure and content.
Big Self-Supervised Models Advance Medical Image Classification
Self-supervised pretraining followed by supervised fine-tuning has seen success in image recognition, especially when labeled examples are scarce, but has received limited attention in medical image analysis.
Demystifying Loss Functions for Classification
It is common to use the softmax cross-entropy loss to train neural networks on classification datasets where a single class label is assigned to each example.
Ranking Cost: One-Stage Circuit Routing by Directly Optimizing Global Objective Function
In our method, we introduce a new set of variables called cost maps, which can help the A* router to find out proper paths to achieve the global object.
CLUE: Towards Discovering Locked Cryptocurrencies in Ethereum
Because the locked cryptocurrencies can never be controlled by users, avoid interacting with the accounts discovered by CLUE and repeating the same mistakes again can help users to save money.
Cryptography and Security
BSODA: A Bipartite Scalable Framework for Online Disease Diagnosis
To address the challenge, we propose a non-RL Bipartite Scalable framework for Online Disease diAgnosis, called BSODA.
Intriguing Properties of Contrastive Losses
We construct datasets with explicit and controllable competing features, and show that, for contrastive learning, a few bits of easy-to-learn shared features can suppress, and even fully prevent, the learning of other sets of competing features.
Why Do Better Loss Functions Lead to Less Transferable Features?
We show that many objectives lead to statistically significant improvements in ImageNet accuracy over vanilla softmax cross-entropy, but the resulting fixed feature extractors transfer substantially worse to downstream tasks, and the choice of loss has little effect when networks are fully fine-tuned on the new tasks.
Robust Pre-Training by Adversarial Contrastive Learning
Recent work has shown that, when integrated with adversarial training, self-supervised pre-training can lead to state-of-the-art robustness In this work, we improve robustness-aware self-supervised pre-training by learning representations that are consistent under both data augmentations and adversarial perturbations.
Graph Contrastive Learning with Augmentations
In this paper, we propose a graph contrastive learning (GraphCL) framework for learning unsupervised representations of graph data.
Learning to Embed Categorical Features without Embedding Tables for Recommendation
Embedding learning of categorical features (e. g. user/item IDs) is at the core of various recommendation models including matrix factorization and neural collaborative filtering.
Self-supervised Learning for Large-scale Item Recommendations
Our online results also verify our hypothesis that our framework indeed improves model performance even more on slices that lack supervision.
Big Self-Supervised Models are Strong Semi-Supervised Learners
The proposed semi-supervised learning algorithm can be summarized in three steps: unsupervised pretraining of a big ResNet model using SimCLRv2, supervised fine-tuning on a few labeled examples, and distillation with unlabeled examples for refining and transferring the task-specific knowledge.
Self-Supervised Image Classification
Semi-Supervised Image Classification
Image Augmentations for GAN Training
We provide new state-of-the-art results for conditional generation on CIFAR-10 with both consistency loss and contrastive loss as additional regularizations.
Estimation of the Laser Frequency Nosie Spectrum by Continuous Dynamical Decoupling
Decoherence induced by the laser frequency noise is one of the most important obstacles in the quantum information processing.
Quantum Physics
Learning Multi-granular Quantized Embeddings for Large-Vocab Categorical Features in Recommender Systems
In this paper, we seek to learn highly compact embeddings for large-vocab sparse features in recommender systems (recsys).
A Simple Framework for Contrastive Learning of Visual Representations
This paper presents SimCLR: a simple framework for contrastive learning of visual representations.
Ranked #4 on
Contrastive Learning
on imagenet-1k
Understanding Why Neural Networks Generalize Well Through GSNR of Parameters
As deep neural networks (DNNs) achieve tremendous success across many application domains, researchers tried to explore in many aspects on why they generalize well.
SVQN: Sequential Variational Soft Q-Learning Networks
Partially Observable Markov Decision Processes (POMDPs) are popular and flexible models for real-world decision-making applications that demand the information from past observations to make optimal decisions.
The Origins and Prevalence of Texture Bias in Convolutional Neural Networks
By taking less aggressive random crops at training time and applying simple, naturalistic augmentation (color distortion, noise, and blur), we train models that classify ambiguous images by shape a majority of the time, and outperform baselines on out-of-distribution test sets.
Ranked #9 on
Object Recognition
on shape bias
Enhancing Dialogue Symptom Diagnosis with Global Attention and Symptom Graph
In this paper, we first construct a dialogue symptom diagnosis dataset based on an online medical forum with a large amount of dialogues between patients and doctors.
Learning Compact Embedding Layers via Differentiable Product Quantization
Embedding layers are commonly used to map discrete symbols into continuous embedding vectors that reflect their semantic meanings.
Differentiable Product Quantization for End-to-End Embedding Compression
Embedding layers are commonly used to map discrete symbols into continuous embedding vectors that reflect their semantic meanings.
Few-Shot Representation Learning for Out-Of-Vocabulary Words
Existing approaches for learning word embeddings often assume there are sufficient occurrences for each word in the corpus, such that the representation of words can be accurately estimated from their contexts.
Pre-Training Graph Neural Networks for Generic Structural Feature Extraction
With the proposed pre-training procedure, the generic structural information is learned and preserved, thus the pre-trained GNN requires less amount of labeled data and fewer domain-specific features to achieve high performance on different downstream tasks.
Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification
In this work, we propose a dissection of GNNs on graph classification into two parts: 1) the graph filtering, where graph-based neighbor aggregations are performed, and 2) the set function, where a set of hidden node features are composed for prediction.
Ranked #1 on
Graph Classification
on RE-M12K
Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity
We introduce a novel approach to graph-level representation learning, which is to embed an entire graph into a vector space where the embeddings of two graphs preserve their graph-graph proximity.
Ranked #1 on
Graph Classification
on Web
Doubly Sparse: Sparse Mixture of Sparse Experts for Efficient Softmax Inference
In this paper, we present a novel softmax inference speedup method, Doubly Sparse Softmax (DS-Softmax), that leverages sparse mixture of sparse experts to efficiently retrieve top-k classes.
Self-Supervised GANs via Auxiliary Rotation Loss
In this work we exploit two popular unsupervised learning techniques, adversarial training and self-supervision, and take a step towards bridging the gap between conditional and unconditional GANs.
Ranked #6 on
Image Generation
on CelebA-HQ 128x128
Self-Supervised GAN to Counter Forgetting
To counter forgetting, we encourage the discriminator to maintain useful representations by adding a self-supervision.
On Self Modulation for Generative Adversarial Networks
Training Generative Adversarial Networks (GANs) is notoriously challenging.
Adaptive Mixture of Low-Rank Factorizations for Compact Neural Modeling
Modern deep neural networks have a large amount of weights, which make them difficult to deploy on computation constrained devices such as mobile phones.
SimGNN: A Neural Network Approach to Fast Graph Similarity Computation
Our model achieves better generalization on unseen graphs, and in the worst case runs in quadratic time with respect to the number of nodes in two graphs.
Ranked #1 on
Graph Similarity
on IMDb
Task-oriented Dialogue System for Automatic Diagnosis
In this paper, we make a move to build a dialogue system for automatic diagnosis.
Learning K-way D-dimensional Discrete Codes for Compact Embedding Representations
Conventional embedding methods directly associate each symbol with a continuous embedding vector, which is equivalent to applying a linear transformation based on a "one-hot" encoding of the discrete symbols.
HeteroMed: Heterogeneous Information Network for Medical Diagnosis
To the best of our knowledge, this is the first study to use Heterogeneous Information Network for modeling clinical data and disease diagnosis.
Learning K-way D-dimensional Discrete Code For Compact Embedding Representations
Conventional embedding methods directly associate each symbol with a continuous embedding vector, which is equivalent to applying linear transformation based on "one-hot" encoding of the discrete symbols.
On Sampling Strategies for Neural Network-based Collaborative Filtering
In this paper, we propose a general neural network-based recommendation framework, which subsumes several existing state-of-the-art recommendation algorithms, and address the efficiency issue by investigating sampling strategies in the stochastic gradient descent training for the framework.
Joint Text Embedding for Personalized Content-based Recommendation
While latent factors of items can be learned effectively from user interaction data, in many cases, such data is not available, especially for newly emerged items.
Ideology Detection for Twitter Users with Heterogeneous Types of Links
The problem of ideology detection is to study the latent (political) placement for people, which is traditionally studied on politicians according to their voting behaviors.
Social and Information Networks
Task-Guided and Path-Augmented Heterogeneous Network Embedding for Author Identification
To address the challenges, we propose a task-guided and path-augmented heterogeneous network embedding model.
Entity Embedding-based Anomaly Detection for Heterogeneous Categorical Events
Anomaly detection plays an important role in modern data-driven security applications, such as detecting suspicious access to a socket from a process.
Dropout Training for SVMs with Data Augmentation
Empirical results on several real datasets demonstrate the effectiveness of dropout training on significantly boosting the classification accuracy of both linear and nonlinear SVMs.
