Search Results for author:
Found 350 papers, 159 papers with code
PP-YOLO: An Effective and Efficient Implementation of Object Detector
We mainly try to combine various existing tricks that almost not increase the number of model parameters and FLOPs, to achieve the goal of improving the accuracy of detector as much as possible while ensuring that the speed is almost unchanged.
Ranked #123 on
Object Detection
on COCO test-dev
(using extra training data)
QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions
We propose a new end-to-end neural acoustic model for automatic speech recognition.
Ranked #33 on
Speech Recognition
on LibriSpeech test-clean
Speech Recognition
Audio and Speech Processing
A Fast and Robust BERT-based Dialogue State Tracker for Schema-Guided Dialogue Dataset
Dialog State Tracking (DST) is one of the most crucial modules for goal-oriented dialogue systems.
BioMegatron: Larger Biomedical Domain Language Model
There has been an influx of biomedical domain-specific language models, showing language models pre-trained on biomedical text perform better on biomedical domain benchmarks than those trained on general domain text corpora such as Wikipedia and Books.
Ranked #1 on
Named Entity Recognition (NER)
on BC5CDR-disease
Shallow Fusion of Weighted Finite-State Transducer and Language Model for Text Normalization
First, a non-deterministic WFST outputs all normalization candidates, and then a neural language model picks the best one -- similar to shallow fusion for automatic speech recognition.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Conformer-based Target-Speaker Automatic Speech Recognition for Single-Channel Audio
We propose CONF-TSASR, a non-autoregressive end-to-end time-frequency domain architecture for single-channel target-speaker automatic speech recognition (TS-ASR).
NeMo Inverse Text Normalization: From Development To Production
Inverse text normalization (ITN) converts spoken-domain automatic speech recognition (ASR) output into written-domain text to improve the readability of the ASR output.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Fast Wavenet Generation Algorithm
This paper presents an efficient implementation of the Wavenet generation process called Fast Wavenet.
Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks
We propose NovoGrad, an adaptive stochastic gradient descent method with layer-wise gradient normalization and decoupled weight decay.
Backdoor Attacks Against Dataset Distillation
A model trained on this smaller distilled dataset can attain comparable performance to a model trained on the original training dataset.
AUTOVC: Zero-Shot Voice Style Transfer with Only Autoencoder Loss
On the other hand, CVAE training is simple but does not come with the distribution-matching property of a GAN.
Unsupervised Speech Decomposition via Triple Information Bottleneck
Speech information can be roughly decomposed into four components: language content, timbre, pitch, and rhythm.
Fast Generation for Convolutional Autoregressive Models
In this work, we describe a method to speed up generation in convolutional autoregressive models.
ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakers
Self-supervised learning in speech involves training a speech representation network on a large-scale unannotated speech corpus, and then applying the learned representations to downstream tasks.
PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation
The need for fine-grained perception in autonomous driving systems has resulted in recently increased research on online semantic segmentation of single-scan LiDAR.
Ranked #11 on
Robust 3D Semantic Segmentation
on nuScenes-C
Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation
Panoptic segmentation presents a new challenge in exploiting the merits of both detection and segmentation, with the aim of unifying instance segmentation and semantic segmentation in a single framework.
Unified Mandarin TTS Front-end Based on Distilled BERT Model
The front-end module in a typical Mandarin text-to-speech system (TTS) is composed of a long pipeline of text processing components, which requires extensive efforts to build and is prone to large accumulative model size and cascade errors.
Dilated Recurrent Neural Networks
To provide a theory-based quantification of the architecture's advantages, we introduce a memory capacity measure, the mean recurrent length, which is more suitable for RNNs with long skip connections than existing measures.
Ranked #24 on
Sequential Image Classification
on Sequential MNIST
DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings
We propose DiffCSE, an unsupervised contrastive learning framework for learning sentence embeddings.
Ranked #13 on
Semantic Textual Similarity
on STS16
Global Rhythm Style Transfer Without Text Transcriptions
In this paper, we propose AutoPST, which can disentangle global prosody style from speech without relying on any text transcriptions.
A Survey of Visual Transformers
Transformer, an attention-based encoder-decoder model, has already revolutionized the field of natural language processing (NLP).
"Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models
The misuse of large language models (LLMs) has garnered significant attention from the general public and LLM vendors.
Polyper: Boundary Sensitive Polyp Segmentation
We present a new boundary sensitive framework for polyp segmentation, called Polyper.
Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models
Based on this finding, we further propose a simple, light-weight image editing algorithm where the mixing weights of the two text embeddings are optimized for style matching and content preservation.
TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation
We have demonstrated that the proposed TALLRec framework can significantly enhance the recommendation capabilities of LLMs in the movie and book domains, even with a limited dataset of fewer than 100 samples.
The Lottery Ticket Hypothesis for Pre-trained BERT Networks
For a range of downstream tasks, we indeed find matching subnetworks at 40% to 90% sparsity.
Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
Hence, we propose a curriculum-style learning approach to minimize the domain gap in urban scenery semantic segmentation.
Ranked #27 on
Image-to-Image Translation
on SYNTHIA-to-Cityscapes
A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes
Hence, we propose a curriculum-style learning approach to minimizing the domain gap in urban scene semantic segmentation.
Ranked #26 on
Image-to-Image Translation
on SYNTHIA-to-Cityscapes
MGTBench: Benchmarking Machine-Generated Text Detection
Extensive evaluations on public datasets with curated texts generated by various powerful LLMs such as ChatGPT-turbo and Claude demonstrate the effectiveness of different detection methods.
SpeechSplit 2.0: Unsupervised speech disentanglement for voice conversion Without tuning autoencoder Bottlenecks
SpeechSplit can perform aspect-specific voice conversion by disentangling speech into content, rhythm, pitch, and timbre using multiple autoencoders in an unsupervised manner.
ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models
In addition, we propose the first effective defense mechanisms against such broader class of membership inference attacks that maintain a high level of utility of the ML model.
Causal Intervention for Leveraging Popularity Bias in Recommendation
This work studies an unexplored problem in recommendation -- how to leverage popularity bias to improve the recommendation accuracy.
Modality-aware Mutual Learning for Multi-modal Medical Image Segmentation
To this end, we propose a novel mutual learning (ML) strategy for effective and robust multi-modal liver tumor segmentation.
mmFormer: Multimodal Medical Transformer for Incomplete Multimodal Learning of Brain Tumor Segmentation
Concretely, we propose a novel multimodal Medical Transformer (mmFormer) for incomplete multimodal learning with three main components: the hybrid modality-specific encoders that bridge a convolutional encoder and an intra-modal Transformer for both local and global context modeling within each modality; an inter-modal Transformer to build and align the long-range correlations across modalities for modality-invariant features with global semantics corresponding to tumor region; a decoder that performs a progressive up-sampling and fusion with the modality-invariant features to generate robust segmentation.
Ranked #65 on
Semantic Segmentation
on NYU Depth v2
ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models
As a result, we lack a comprehensive picture of the risks caused by the attacks, e. g., the different scenarios they can be applied to, the common factors that influence their performance, the relationship among them, or the effectiveness of possible defenses.
Harnessing the Spatial-Temporal Attention of Diffusion Models for High-Fidelity Text-to-Image Synthesis
We then impose spatial attention control by combining the attention over the entire text description and that over the local description of the particular object in the corresponding pixel region of that object.
The Lottery Tickets Hypothesis for Supervised and Self-supervised Pre-training in Computer Vision Models
We extend the scope of LTH and question whether matching subnetworks still exist in pre-trained computer vision models, that enjoy the same downstream transfer performance.
Point Cloud GAN
In this paper, we first show a straightforward extension of existing GAN algorithm is not applicable to point clouds, because the constraint required for discriminators is undefined for set data.
Invariant Rationalization
Selective rationalization improves neural network interpretability by identifying a small subset of input features -- the rationale -- that best explains or supports the prediction.
Structure-Aware NeRF without Posed Camera via Epipolar Constraint
This two-stage strategy is not convenient to use and degrades the performance because the error in the pose extraction can propagate to the view synthesis.
How to Retrain Recommender System? A Sequential Meta-Learning Method
Nevertheless, normal training on new data only may easily cause overfitting and forgetting issues, since the new data is of a smaller scale and contains fewer information on long-term user preference.
Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models
COPAINT also uses the Bayesian framework to jointly modify both revealed and unrevealed regions, but approximates the posterior distribution in a way that allows the errors to gradually drop to zero throughout the denoising steps, thus strongly penalizing any mismatches with the reference image.
GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models
In addition, we propose the first generic attack model that can be instantiated in a large range of settings and is applicable to various kinds of deep generative models.
Generating Visually Aligned Sound from Videos
During testing, the audio forwarding regularizer is removed to ensure that REGNET can produce purely aligned sound only from visual features.
MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples
Specifically, given a black-box access to the target classifier, the attacker trains a binary classifier, which takes a data sample's confidence score vector predicted by the target classifier as an input and predicts the data sample to be a member or non-member of the target classifier's training dataset.
LF-YOLO: A Lighter and Faster YOLO for Weld Defect Detection of X-ray Image
To further prove the ability of our method, we test it on public dataset MS COCO, and the results show that our LF-YOLO has a outstanding versatility detection performance.
When Machine Unlearning Jeopardizes Privacy
More importantly, we show that our attack in multiple cases outperforms the classical membership inference attack on the original ML model, which indicates that machine unlearning can have counterproductive effects on privacy.
ACN: Adversarial Co-training Network for Brain Tumor Segmentation with Missing Modalities
Specifically, ACN adopts a novel co-training network, which enables a coupled learning process for both full modality and missing modality to supplement each other's domain and feature representations, and more importantly, to recover the `missing' information of absent modalities.
Unsupervised Text-to-Speech Synthesis by Unsupervised Automatic Speech Recognition
An unsupervised text-to-speech synthesis (TTS) system learns to generate speech waveforms corresponding to any written sentence in a language by observing: 1) a collection of untranscribed speech waveforms in that language; 2) a collection of texts written in that language without access to any transcribed speech.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
WAVPROMPT: Towards Few-Shot Spoken Language Understanding with Frozen Language Models
We show that WavPrompt is a few-shot learner that can perform speech understanding tasks better than a naive text baseline.
Graph Unlearning
In this paper, we propose GraphEraser, a novel machine unlearning framework tailored to graph data.
A Bi-Step Grounding Paradigm for Large Language Models in Recommendation Systems
As the focus on Large Language Models (LLMs) in the field of recommendation intensifies, the optimization of LLMs for recommendation purposes (referred to as LLM4Rec) assumes a crucial role in augmenting their effectiveness in providing recommendations.
Is ChatGPT Fair for Recommendation? Evaluating Fairness in Large Language Model Recommendation
The remarkable achievements of Large Language Models (LLMs) have led to the emergence of a novel recommendation paradigm -- Recommendation via LLM (RecLLM).
AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N
To facilitate this research, here we introduce RICE-N, a multi-region integrated assessment model that simulates the global climate and economy, and which can be used to design and evaluate the strategic outcomes for different negotiation and agreement frameworks.
Fine-Grained Neural Network Explanation by Identifying Input Features with Predictive Information
We propose a method to identify features with predictive information in the input domain.
Model Stealing Attacks Against Inductive Graph Neural Networks
Graph neural networks (GNNs), a new family of machine learning (ML) models, have been proposed to fully leverage graph data to build powerful applications.
Linking Emergent and Natural Languages via Corpus Transfer
In this work, we propose a novel way to establish such a link by corpus transfer, i. e. pretraining on a corpus of emergent language for downstream natural language tasks, which is in contrast to prior work that directly transfers speaker and listener parameters.
SAP-DETR: Bridging the Gap Between Salient Points and Queries-Based Transformer Detector for Fast Model Convergency
To bridge the gap between the reference points of salient queries and Transformer detectors, we propose SAlient Point-based DETR (SAP-DETR) by treating object detection as a transformation from salient points to instance objects.
RULER: What's the Real Context Size of Your Long-Context Language Models?
Despite achieving nearly perfect accuracy in the vanilla NIAH test, all models exhibit large performance drops as the context length increases.
CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendation
In pursuit of superior recommendations for both cold and warm start scenarios, we introduce CoLLM, an innovative LLMRec methodology that seamlessly incorporates collaborative information into LLMs for recommendation.
NL2TL: Transforming Natural Languages to Temporal Logics using Large Language Models
Then, we finetune T5 models on the lifted versions (i. e., the specific Atomic Propositions (AP) are hidden) of the NL and TL.
AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkers
Rather than using LLMs to directly plan task sub-goals, we instead perform few-shot translation from natural language task descriptions to an intermediate task representation that can then be consumed by a TAMP algorithm to jointly solve the task and motion plan.
Modality-Agnostic Attention Fusion for visual search with text feedback
Image retrieval with natural language feedback offers the promise of catalog search based on fine-grained visual features that go beyond objects and binary attributes, facilitating real-world applications such as e-commerce.
BiFSMNv2: Pushing Binary Neural Networks for Keyword Spotting to Real-Network Performance
We highlight that benefiting from the compact architecture and optimized hardware kernel, BiFSMNv2 can achieve an impressive 25. 1x speedup and 20. 2x storage-saving on edge hardware.
Accurate LoRA-Finetuning Quantization of LLMs via Information Retention
This paper proposes a novel IR-QLoRA for pushing quantized LLMs with LoRA to be highly accurate through information retention.
Inference Attacks Against Graph Neural Networks
Second, given a subgraph of interest and the graph embedding, we can determine with high confidence that whether the subgraph is contained in the target graph.
MetaAdapt: Domain Adaptive Few-Shot Misinformation Detection via Meta Learning
As such, MetaAdapt can learn how to adapt the misinformation detection model and exploit the source data for improved performance in the target domain.
Membership Inference Attacks by Exploiting Loss Trajectory
Machine learning models are vulnerable to membership inference attacks in which an adversary aims to predict whether or not a particular sample was contained in the target model's training dataset.
UnGANable: Defending Against GAN-based Face Manipulation
Extensive experiments on four popular GAN models trained on two benchmark face datasets show that UnGANable achieves remarkable effectiveness and utility performance, and outperforms multiple baseline methods.
How to Prove Your Model Belongs to You: A Blind-Watermark based Framework to Protect Intellectual Property of DNN
To fill these gaps, in this paper, we propose a novel intellectual property protection (IPP) framework based on blind-watermark for watermarking deep neural networks that meet the requirements of security and feasibility.
Improving Device-Edge Cooperative Inference of Deep Learning via 2-Step Pruning
Since the output data size of a DNN layer can be larger than that of the raw data, offloading intermediate data between layers can suffer from high transmission latency under limited wireless bandwidth.
Adversarial Support Alignment
Furthermore, we show that our approach can be viewed as a limit of existing notions of alignment by increasing transportation assignment tolerance.
Pseudo Label-Guided Model Inversion Attack via Conditional Generative Adversarial Network
At first, a top-n selection strategy is proposed to provide pseudo-labels for public data, and use pseudo-labels to guide the training of the cGAN.
Affinity Fusion Graph-based Framework for Natural Image Segmentation
The proposed framework combines adjacency-graphs and kernel spectral clustering based graphs (KSC-graphs) according to a new definition named affinity nodes of multi-scale superpixels.
BiFSMN: Binary Neural Network for Keyword Spotting
Then, to allow the instant and adaptive accuracy-efficiency trade-offs at runtime, we also propose a Thinnable Binarization Architecture to further liberate the acceleration potential of the binarized network from the topology perspective.
Correcting Diffusion Generation through Resampling
Despite diffusion models' superior capabilities in modeling complex distributions, there are still non-trivial distributional discrepancies between generated and ground-truth images, which has resulted in several notable problems in image generation, including missing object errors in text-to-image generation and low image quality.
Membership Leakage in Label-Only Exposures
However, recent research has shown that ML models are vulnerable to attacks against their training data.
Membership Inference Attacks Against Recommender Systems
In this paper, we make the first attempt on quantifying the privacy leakage of recommender systems through the lens of membership inference.
TumorCP: A Simple but Effective Object-Level Data Augmentation for Tumor Segmentation
Experiments on kidney tumor segmentation task demonstrate that TumorCP surpasses the strong baseline by a remarkable margin of 7. 12% on tumor Dice.
Addressing Confounding Feature Issue for Causal Recommendation
We demonstrate DCR on the backbone model of neural factorization machine (NFM), showing that DCR leads to more accurate prediction of user preference with small inference time cost.
Data Poisoning Attacks Against Multimodal Encoders
Extensive evaluations on different datasets and model architectures show that all three attacks can achieve significant attack performance while maintaining model utility in both visual and linguistic modalities.
Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models
Our evaluation result shows that 24% of the generated images using DreamBooth are hateful meme variants that present the features of the original hateful meme and the target individual/community; these generated images are comparable to hateful meme variants collected from the real world.
A Game Theoretic Approach to Class-wise Selective Rationalization
Selection of input features such as relevant pieces of text has become a common technique of highlighting how complex neural predictors operate.
Deep Symbolic Superoptimization Without Human Knowledge
Deep symbolic superoptimization refers to the task of applying deep learning methods to simplify symbolic expressions.
Auto-NBA: Efficient and Effective Search Over the Joint Space of Networks, Bitwidths, and Accelerators
The key challenges include (1) the dilemma of whether to explode the memory consumption due to the huge joint space or achieve sub-optimal designs, (2) the discrete nature of the accelerator design space that is coupled yet different from that of the networks and bitwidths, and (3) the chicken and egg problem associated with network-accelerator co-search, i. e., co-search requires operation-wise hardware cost, which is lacking during search as the optimal accelerator depending on the whole network is still unknown during search.
Speech Denoising with Auditory Models
Contemporary speech enhancement predominantly relies on audio transforms that are trained to reconstruct a clean speech waveform.
Fairness Reprogramming
Specifically, FairReprogram considers the case where models can not be changed and appends to the input a set of perturbations, called the fairness trigger, which is tuned towards the fairness criteria under a min-max formulation.
Amplifying Membership Exposure via Data Poisoning
In this paper, we investigate the third type of exploitation of data poisoning - increasing the risks of privacy leakage of benign training samples.
Losses Can Be Blessings: Routing Self-Supervised Speech Representations Towards Efficient Multilingual and Multitask Speech Processing
We believe S$^3$-Router has provided a new perspective for practical deployment of speech SSL models.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
PromptBoosting: Black-Box Text Classification with Ten Forward Passes
Instead of directly optimizing in prompt space, PromptBoosting obtains a small pool of prompts via a gradient-free approach and then constructs a large pool of weak learners by pairing these prompts with different elements of the LM's output distribution.
You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content
We find that prompt learning achieves around 10\% improvement in the toxicity classification task compared to the baselines, while for the toxic span detection task we find better performance to the best baseline (0. 643 vs. 0. 640 in terms of $F_1$-score).
Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks
Deep Neural Networks (DNNs) are known to be vulnerable to adversarial attacks, i. e., an imperceptible perturbation to the input can mislead DNNs trained on clean images into making erroneous predictions.
SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoders
Recent research has shown that the machine learning model's copyright is threatened by model stealing attacks, which aim to train a surrogate model to mimic the behavior of a given model.
S$^2$ME: Spatial-Spectral Mutual Teaching and Ensemble Learning for Scribble-supervised Polyp Segmentation
Furthermore, to produce reliable mixed pseudo labels, which enhance the effectiveness of ensemble learning, we introduce a novel adaptive pixel-wise fusion technique based on the entropy guidance from the spatial and spectral branches.
Semi-supervised Cardiac Image Segmentation via Label Propagation and Style Transfer
Accurate segmentation of cardiac structures can assist doctors to diagnose diseases, and to improve treatment planning, which is highly demanded in the clinical practice.
Teacher Model Fingerprinting Attacks Against Transfer Learning
To this end, we propose a teacher model fingerprinting attack to infer the origin of a student model, i. e., the teacher model it transfers from.
Semi-Leak: Membership Inference Attacks Against Semi-supervised Learning
The results show that early stopping can mitigate the membership inference attack, but with the cost of model's utility degradation.
EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site Prediction
Predicting the binding sites of the target proteins plays a fundamental role in drug discovery.
FATRER: Full-Attention Topic Regularizer for Accurate and Robust Conversational Emotion Recognition
This paper concentrates on the understanding of interlocutors' emotions evoked in conversational utterances.
Ranked #17 on
Emotion Recognition in Conversation
on IEMOCAP
Rethinking Cooperative Rationalization: Introspective Extraction and Complement Control
Moreover, we explicitly control the rationale complement via an adversary so as not to leave any useful information out of the selection.
Quantifying and Mitigating Privacy Risks of Contrastive Learning
Our experimental results show that contrastive models trained on image datasets are less vulnerable to membership inference attacks but more vulnerable to attribute inference attacks compared to supervised models.
Dual Memory Aggregation Network for Event-Based Object Detection with Learnable Representation
To fully exploit information with event streams to detect objects, a dual-memory aggregation network (DMANet) is proposed to leverage both long and short memory along event streams to aggregate effective information for object detection.
RealPoint3D: Point Cloud Generation from a Single Image with Complex Background
Then, the image together with the retrieved shape model is fed into the proposed network to generate the fine-grained 3D point cloud.
Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders
Self-supervised representation learning techniques have been developing rapidly to make full use of unlabeled images.
Data-Efficient Double-Win Lottery Tickets from Robust Pre-training
For example, on downstream CIFAR-10/100 datasets, we identify double-win matching subnetworks with the standard, fast adversarial, and adversarial pre-training from ImageNet, at 89. 26%/73. 79%, 89. 26%/79. 03%, and 91. 41%/83. 22% sparsity, respectively.
On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learning
The dissemination of hateful memes online has adverse effects on social media platforms and the real world.
TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization
Robustness evaluation against adversarial examples has become increasingly important to unveil the trustworthiness of the prevailing deep models in natural language processing (NLP).
Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion Models
Recent advancements in diffusion models have notably improved the perceptual quality of generated images in text-to-image synthesis tasks.
decoupleQ: Towards 2-bit Post-Training Uniform Quantization via decoupling Parameters into Integer and Floating Points
However, existing quantization schemes suffer from significant accuracy degradation at very low bits, or require some additional computational overhead when deployed, making it difficult to be applied to large-scale applications in industry.
SACoD: Sensor Algorithm Co-Design Towards Efficient CNN-powered Intelligent PhlatCam
PhlatCam, with its form factor potentially reduced by orders of magnitude, has emerged as a promising solution to the first aforementioned challenge, while the second one remains a bottleneck.
On the Privacy Risks of Cell-Based NAS Architectures
Existing studies on neural architecture search (NAS) mainly focus on efficiently and effectively searching for network architectures with better performance.
A Plot is Worth a Thousand Words: Model Information Stealing Attacks via Scientific Plots
Given the simplicity and effectiveness of the attack method, our study indicates scientific plots indeed constitute a valid side channel for model information stealing attacks.
Reformulating CTR Prediction: Learning Invariant Feature Interactions for Recommendation
However, such a manner inevitably learns unstable feature interactions, i. e., the ones that exhibit strong correlations in historical data but generalize poorly for future serving.
Faster OreFSDet : A Lightweight and Effective Few-shot Object Detector for Ore Images
For the ore particle size detection, obtaining a sizable amount of high-quality ore labeled data is time-consuming and expensive.
SeeDS: Semantic Separable Diffusion Synthesizer for Zero-shot Food Detection
To tackle this, we propose the Semantic Separable Diffusion Synthesizer (SeeDS) framework for Zero-Shot Food Detection (ZSFD).
Ranked #1 on
Generalized Zero-Shot Object Detection
on MS-COCO
CAMOU: Learning Physical Vehicle Camouflages to Adversarially Attack Detectors in the Wild
In particular, we learn a camouflage pattern to hide vehicles from being detected by state-of-the-art convolutional neural network based detectors.
$t$-$k$-means: A Robust and Stable $k$-means Variant
$k$-means algorithm is one of the most classical clustering methods, which has been widely and successfully used in signal processing.
Towards Interpreting Recurrent Neural Networks through Probabilistic Abstraction
In this work, we propose an approach to extract probabilistic automata for interpreting an important class of neural networks, i. e., recurrent neural networks.
Explaining COVID-19 and Thoracic Pathology Model Predictions by Identifying Informative Input Features
Neural networks have demonstrated remarkable performance in classification and regression tasks on chest X-rays.
Voting for the right answer: Adversarial defense for speaker verification
Automatic speaker verification (ASV) is a well developed technology for biometric identification, and has been ubiquitous implemented in security-critic applications, such as banking and access control.
Learning Rich Features for Gait Recognition by Integrating Skeletons and Silhouettes
Gait recognition captures gait patterns from the walking sequence of an individual for identification.
Topogivity: A Machine-Learned Chemical Rule for Discovering Topological Materials
Topological materials present unconventional electronic properties that make them attractive for both basic science and next-generation technological applications.
Efficient Real-time Path Planning with Self-evolving Particle Swarm Optimization in Dynamic Scenarios
Particle Swarm Optimization (PSO) has demonstrated efficacy in addressing static path planning problems.
A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations
Backpropagation-based visualizations have been proposed to interpret convolutional neural networks (CNNs), however a theory is missing to justify their behaviors: Guided backpropagation (GBP) and deconvolutional network (DeconvNet) generate more human-interpretable but less class-sensitive visualizations than saliency map.
BCORLE($\lambda$): An Offline Reinforcement Learning and Evaluation Framework for Coupons Allocation in E-commerce Market
Further, a novel offline reinforcement learning method and an off-policy evaluation algorithm are proposed for policy learning and policy evaluation, respectively.
Improving Neural Radiance Fields with Depth-aware Optimization for Novel View Synthesis
Through these explicit constraints and the implicit constraint from NeRF, our method improves the view synthesis as well as the 3D-scene geometry performance of NeRF at the same time.
Prediction then Correction: An Abductive Prediction Correction Method for Sequential Recommendation
To improve the accuracy of these models, some researchers have attempted to simulate human analogical reasoning to correct predictions for testing data by drawing analogies with the prediction errors of similar training data.
Spatial-information Guided Adaptive Context-aware Network for Efficient RGB-D Semantic Segmentation
Efficient RGB-D semantic segmentation has received considerable attention in mobile robots, which plays a vital role in analyzing and recognizing environmental information.
Ranked #57 on
Semantic Segmentation
on NYU Depth v2
VGMShield: Mitigating Misuse of Video Generative Models
Together with fake video detection and tracing, our multi-faceted set of solutions can effectively mitigate misuse of video generative models.
Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing
Aligned large language models (LLMs) are vulnerable to jailbreaking attacks, which bypass the safeguards of targeted LLMs and fool them into generating objectionable content.
Effective Tensor Completion via Element-wise Weighted Low-rank Tensor Train with Overlapping Ket Augmentation
Accordingly, a novel formulation for tensor completion and an effective optimization algorithm, called as tensor completion by parallel weighted matrix factorization via tensor train (TWMac-TT), is proposed.
FACE-AUDITOR: Data Auditing in Facial Recognition Systems
Few-shot-based facial recognition systems have gained increasing attention due to their scalability and ability to work with a few face images during the model deployment phase.
NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models
Such attacks can be easily affected by retraining on downstream tasks and with different prompting strategies, limiting the transferability of backdoor attacks.
Generated Graph Detection
Graph generative models become increasingly effective for data distribution approximation and data augmentation.
Certified Robustness for Large Language Models with Self-Denoising
This largely falls into the study of certified robust LLMs, i. e., all predictions of LLM are certified to be correct in a local region around the input.
Decomposing Uncertainty for Large Language Models through Input Clarification Ensembling
Uncertainty decomposition refers to the task of decomposing the total uncertainty of a model into data (aleatoric) uncertainty, resulting from the inherent complexity or ambiguity of the data, and model (epistemic) uncertainty, resulting from the lack of knowledge in the model.
A Concise but High-performing Network for Image Guided Depth Completion in Autonomous Driving
Depth completion is a crucial task in autonomous driving, aiming to convert a sparse depth map into a dense depth prediction.
PRompt Optimization in Multi-Step Tasks (PROMST): Integrating Human Feedback and Preference Alignment
Prompt optimization aims to find the best prompt to a large language model (LLM) for a given task.
Advancing the Robustness of Large Language Models through Self-Denoised Smoothing
Although large language models (LLMs) have achieved significant success, their vulnerability to adversarial perturbations, including recent jailbreak attacks, has raised considerable concerns.
SQL Generation via Machine Reading Comprehension
Text-to-SQL systems offers natural language interfaces to databases, which can automatically generates SQL queries given natural language questions.
Efficient Segmentation with Texture in Ore Images Based on Box-supervised Approach
At the same time, the ore distribution is stacked, and it is difficult to identify the complete features.
LabelCraft: Empowering Short Video Recommendations with Automated Label Crafting
Through meta-learning techniques, LabelCraft effectively addresses the bi-level optimization hurdle posed by the recommender and labeling models, enabling the automatic acquisition of intricate label generation mechanisms. Extensive experiments on real-world datasets corroborate LabelCraft's excellence across varied operational metrics, encompassing usage time, user engagement, and retention.
Multi-stage malaria parasite recognition by deep learning
The proposed method showed higher accuracy and effectiveness in publicly available microscopic images of multi-stage malaria parasites compared to a wide range of state-of-the-art approaches.
Augment before You Try: Knowledge-Enhanced Table Question Answering via Table Expansion
Table question answering is a popular task that assesses a model's ability to understand and interact with structured data.
Understanding Interlocking Dynamics of Cooperative Rationalization
The selection mechanism is commonly integrated into the model itself by specifying a two-component cascaded system consisting of a rationale generator, which makes a binary selection of the input features (which is the rationale), and a predictor, which predicts the output based only on the selected features.
Adaptive Fusion Affinity Graph with Noise-free Online Low-rank Representation for Natural Image Segmentation
To reduce time complexity while improving performance, a sparse representation of global nodes based on noise-free online low-rank representation is used to obtain a global graph at each scale.
Rethinking Missing Data: Aleatoric Uncertainty-Aware Recommendation
A standard choice is treating the missing data as negative training samples and estimating interaction likelihood between user-item pairs along with the observed interactions.
Mitigating Spurious Correlations for Self-supervised Recommendation
This objective requires to 1) automatically mask spurious features without supervision, and 2) block the negative effect transmission from spurious features to other features during SSL.
Prompt Stealing Attacks Against Text-to-Image Generation Models
In this paper, we perform the first study on understanding the threat of a novel attack, namely prompt stealing attack, which aims to steal prompts from generated images by text-to-image generation models.
Generated Distributions Are All You Need for Membership Inference Attacks Against Generative Models
Several membership inference attacks (MIAs) have been proposed to exhibit the privacy vulnerability of generative models by classifying a query image as a training dataset member or nonmember.
Synthesizing Knowledge-enhanced Features for Real-world Zero-shot Food Detection
The complexity of food semantic attributes further makes it more difficult for current ZSD methods to distinguish various food categories.
Prospect Personalized Recommendation on Large Language Model-based Agent Platform
Additionally, we prospect the evolution of Rec4Agentverse and conceptualize it into three stages based on the enhancement of the interaction and information exchange among Agent Items, Agent Recommender, and the user.
Paraphrase and Solve: Exploring and Exploiting the Impact of Surface Form on Mathematical Reasoning in Large Language Models
This paper studies the relationship between the surface form of a mathematical problem and its solvability by large language models.
Gradient-Leaks: Understanding and Controlling Deanonymization in Federated Learning
At the core of FL is a network of anonymous user devices sharing training information (model parameter updates) computed locally on personal data.
KNPTC: Knowledge and Neural Machine Translation Powered Chinese Pinyin Typo Correction
In contrast to previous work, KNPTC is able to integrate explicit knowledge into NMT for pinyin typo correction, and is able to learn to correct a variety of typos without the guidance of manually selected constraints or languagespecific features.
Fully Convolutional Grasp Detection Network with Oriented Anchor Box
The feature extractor is a deep convolutional neural network.
Deep Learning Based Speech Beamforming
On the other hand, deep learning based enhancement approaches are able to learn complicated speech distributions and perform efficient inference, but they are unable to deal with variable number of input channels.
Local Contrast Learning
We focus on one-shot classification by deep learning approach based on a small quantity of training samples.
Infinite-Label Learning with Semantic Output Codes
We develop a new statistical machine learning paradigm, named infinite-label learning, to annotate a data point with more than one relevant labels from a candidate set, which pools both the finite labels observed at training and a potentially infinite number of previously unseen labels.
Deep LSTM for Large Vocabulary Continuous Speech Recognition
It is a competitive framework that LSTM models of more than 7 layers are successfully trained on Shenma voice search data in Mandarin and they outperform the deep LSTM models trained by conventional approach.
Streaming Recommender Systems
The increasing popularity of real-world recommender systems produces data continuously and rapidly, and it becomes more realistic to study recommender systems under streaming scenarios.
Fast Zero-Shot Image Tagging
The well-known word analogy experiments show that the recent word vectors capture fine-grained linguistic regularities in words by linear vector offsets, but it is unclear how well the simple vector offsets can encode visual regularities over words.
Ranked #5 on
Multi-label zero-shot learning
on Open Images V4
HDRFusion: HDR SLAM using a low-cost auto-exposure RGB-D sensor
We describe a new method for comparing frame appearance in a frame-to-model 3-D mapping and tracking system using an low dynamic range (LDR) RGB-D camera which is robust to brightness changes caused by auto exposure.
MLCapsule: Guarded Offline Deployment of Machine Learning as a Service
In this paper, we propose MLCapsule, a guarded offline deployment of machine learning as a service.
Efficient Metropolitan Traffic Prediction Based on Graph Recurrent Neural Network
Traffic prediction is a fundamental and vital task in Intelligence Transportation System (ITS), but it is very challenging to get high accuracy while containing low computational complexity due to the spatiotemporal characteristics of traffic flow, especially under the metropolitan circumstances.
Sentiment Lexicon Expansion Based on Neural PU Learning, Double Dictionary Lookup, and Polarity Association
Although many sentiment lexicons in different languages exist, most are not comprehensive.
Adaptive Learning of Local Semantic and Global Structure Representations for Text Classification
This paper focuses on learning both local semantic and global structure representations for text classification.
Scene Text Recognition Using Part-Based Tree-Structured Character Detection
Scene text recognition has inspired great interests from the computer vision community in recent years.
Based on Graph-VAE Model to Predict Student's Score
In this paper, the graph neural network matrix filling model (Graph-VAE) based on deep learning can automatically extract features without a large amount of prior knowledge.
Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning
As data generation is a continuous process, this leads to ML model owners updating their models frequently with newly-collected data in an online learning scenario.
VAE-based regularization for deep speaker embedding
Deep speaker embedding has achieved state-of-the-art performance in speaker recognition.
Language in Our Time: An Empirical Analysis of Hashtags
Second, we observe that a non-negligible proportion of hashtags exhibit large semantic displacement.
AlphaStock: A Buying-Winners-and-Selling-Losers Investment Strategy using Interpretable Deep Reinforcement Attention Networks
Recent years have witnessed the successful marriage of finance innovations and AI techniques in various finance applications including quantitative trading (QT).
Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Data
To this end, we propose a new approach of domain randomization and pyramid consistency to learn a model with high generalizability.
An Online Reinforcement Learning Approach to Quality-Cost-Aware Task Allocation for Multi-Attribute Social Sensing
Social sensing has emerged as a new sensing paradigm where humans (or devices on their behalf) collectively report measurements about the physical world.
Deciphering Interactions in Causal Networks without Parametric Assumptions
With the assumption that the effect is a mathematical function of the cause in a causal relationship, FunChisq, a chi-square test defined on a non-parametric representation of interactions, infers network topology considering both interaction directionality and nonlinearity.
Molecular Networks
A System-Level Solution for Low-Power Object Detection
As a case study, we evaluate our object detection system on a real-world surveillance video with input size of 512x512, and it turns out that the system can achieve an inference speed of 18 fps at the cost of 6. 9W (with display) with an mAP of 66. 4 verified on the PASCAL VOC 2012 dataset.
An Efficient and Margin-Approaching Zero-Confidence Adversarial Attack
The second paradigm, called the zero-confidence attack, finds the smallest perturbation needed to cause mis-classification, also known as the margin of an input feature.
Semantic Feature Attention Network for Liver Tumor Segmentation in Large-scale CT database
In the SFAN, a Semantic Attention Transmission (SAT) module is designed to select discriminative low-level localization details with the guidance of neighboring high-level semantic information.
A hybrid text normalization system using multi-head self-attention for mandarin
In this paper, we propose a hybrid text normalization system using multi-head self-attention.
A unified sequence-to-sequence front-end model for Mandarin text-to-speech synthesis
In Mandarin text-to-speech (TTS) system, the front-end text processing module significantly influences the intelligibility and naturalness of synthesized speech.
Training Deep Networks with Stochastic Gradient Normalized by Layerwise Adaptive Second Moments
We propose NovoGrad, an adaptive stochastic gradient descent method with layer-wise gradient normalization and decoupled weight decay.
Citation Recommendations Considering Content and Structural Context Embedding
The number of academic papers being published is increasing exponentially in recent years, and recommending adequate citations to assist researchers in writing papers is a non-trivial task.
Optimizing seed inputs in fuzzing with machine learning
Our experiments on a set of widely used PDF viewers demonstrate that the improved seed inputs produced by our framework could significantly increase the code coverage of the target program and the likelihood of detecting program crashes.
Cryptography and Security
Face Hallucination with Finishing Touches
The coarse-level FHnet generates a frontal coarse HR face and then the fine-level FHnet makes use of the facial component appearance prior, i. e., fine-grained facial components, to attain a frontal HR face image with authentic details.
Copy and Paste GAN: Face Hallucination from Shaded Thumbnails
This paper proposes a Copy and Paste Generative Adversarial Network (CPGAN) to recover authentic high-resolution (HR) face images while compensating for low and non-uniform illumination.
Overview of the CCKS 2019 Knowledge Graph Evaluation Track: Entity, Relation, Event and QA
Knowledge graph models world knowledge as concepts, entities, and the relationships between them, which has been widely used in many real-world tasks.
Dynamic Backdoor Attacks Against Machine Learning Models
Triggers generated by our techniques can have random patterns and locations, which reduce the efficacy of the current backdoor detection mechanisms.
Reinterpretation of LHC Results for New Physics: Status and Recommendations after Run 2
We report on the status of efforts to improve the reinterpretation of searches and measurements at the LHC in terms of models for new physics, in the context of the LHC Reinterpretation Forum.
High Energy Physics - Phenomenology High Energy Physics - Experiment
Adaptive Multiscale Illumination-Invariant Feature Representation for Undersampled Face Recognition
Then, the illumination level is referenced to construct the high performance LEF as well realize adaptive fusion for multiple scales LEFs for the face image, performing JLEF-feature.
Deep Attentive Generative Adversarial Network for Photo-Realistic Image De-Quantization
In addition, due to the adversarial learning framework can reliably produce high quality natural images, the specified content loss as well as the adversarial loss are back-propagated to optimize the training of model.
Improved YOLOv3 Object Classification in Intelligent Transportation System
The technology of vehicle and driver detection in Intelligent Transportation System(ITS) is a hot topic in recent years.
ByteSing: A Chinese Singing Voice Synthesis System Using Duration Allocated Encoder-Decoder Acoustic Models and WaveRNN Vocoders
This paper presents ByteSing, a Chinese singing voice synthesis (SVS) system based on duration allocated Tacotron-like acoustic models and WaveRNN neural vocoders.
A New Data Normalization Method to Improve Dialogue Generation by Minimizing Long Tail Effect
Most generation models are based on language models.
Stealing Links from Graph Neural Networks
In this work, we propose the first attacks to steal a graph from the outputs of a GNN model that is trained on the graph.
FA-GANs: Facial Attractiveness Enhancement with Generative Adversarial Networks on Frontal Faces
To the best of our knowledge, we are the first to enhance the facial attractiveness with GANs in both geometry and appearance aspects.
Reliable Federated Learning for Mobile Networks
Based on this metric, a reliable worker selection scheme is proposed for federated learning tasks.
Cryptography and Security
BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvements
In this paper, we perform a systematic investigation of backdoor attack on NLP models, and propose BadNL, a general NLP backdoor attack framework including novel attack methods.
