Search Results for author:
Found 219 papers, 106 papers with code
Neural Architecture Search in a Proxy Validation Loss Landscape
This paper searches for the optimal neural architecture by minimizing a proxy of validation loss.
On Dropping Clusters to Regularize Graph Convolutional Neural Networks
Dropout has been widely adopted to regularize graph convolutional networks (GCNs) by randomly zeroing entries of the node feature vectors and obtains promising performance on various tasks.
Mitigating Data Poisoning in Text Classification with Differential Privacy
NLP models are vulnerable to data poisoning attacks.
Learning Visual Abstract Reasoning through Dual-Stream Networks
Visual abstract reasoning tasks present challenges for deep neural networks, exposing limitations in their capabilities.
Unsupervised Multi-view UAV Image Geo-localization via Iterative Rendering
As such, our unsupervised paradigm naturally avoids the problem of region-specific overfitting, enabling generic CVGL for UAV images without feature fine-tuning or data-driven training.
FLMarket: Enabling Privacy-preserved Pre-training Data Pricing for Federated Learning
Federated Learning (FL), as a mainstream privacy-preserving machine learning paradigm, offers promising solutions for privacy-critical domains such as healthcare and finance.
Harnessing Vision Foundation Models for High-Performance, Training-Free Open Vocabulary Segmentation
Specifically, we introduce Trident, a training-free framework that first splices features extracted by CLIP and DINO from sub-images, then leverages SAM's encoder to create a correlation matrix for global aggregation, enabling a broadened receptive field for effective segmentation.
Investigating Memorization in Video Diffusion Models
Diffusion models, widely used for image and video generation, face a significant limitation: the risk of memorizing and reproducing training data during inference, potentially generating unauthorized copyrighted content.
Exploring Local Memorization in Diffusion Models via Bright Ending Attention
Furthermore, driven by our observation that local memorization significantly underperforms in existing tasks of measuring, detecting, and mitigating memorization in diffusion models compared to global memorization, we propose a simple yet effective method to integrate BE and the results of the new localization task into these existing frameworks.
Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Model
Existing data attribution methods for diffusion models typically quantify the contribution of a training sample by evaluating the change in diffusion loss when the sample is included or excluded from the training process.
Consistency Calibration: Improving Uncertainty Calibration via Consistency among Perturbed Neighbors
Calibration is crucial in deep learning applications, especially in fields like healthcare and autonomous driving, where accurate confidence estimates are vital for decision-making.
Feature Clipping for Uncertainty Calibration
As the first calibration technique based on feature modification, feature clipping offers a novel approach to improving model calibration, showing significant improvements over both post-hoc and train-time calibration methods and pioneering a new avenue for feature-based model calibration.
MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model
This simulation relies on the finest structured data in financial market like orders thus building the finest realistic simulation.
FusionSAM: Latent Space driven Segment Anything Model for Multimodal Fusion and Segmentation
In this paper, we introduce SAM into multimodal image segmentation for the first time, proposing a novel framework that combines Latent Space Token Generation (LSTG) and Fusion Mask Prompting (FMP) modules to enhance SAM's multimodal fusion and segmentation capabilities.
Training-free Long Video Generation with Chain of Diffusion Model Experts
It can generate high-quality videos with chain of off-the-shelf diffusion model experts, each expert responsible for a decoupled subtask.
Compress Guidance in Conditional Diffusion Sampling
We found that enforcing guidance throughout the sampling process is often counterproductive due to the model-fitting issue, where samples are 'tuned' to match the classifier's parameters rather than generalizing the expected condition.
Efficient Image-to-Image Diffusion Classifier for Adversarial Robustness
To alleviate this issue, we redesign the diffusion framework from generating high-quality images to predicting distinguishable image labels.
VSSD: Vision Mamba with Non-Causal State Space Duality
Recently, State Space Duality (SSD), an improved variant of SSMs, was introduced in Mamba2 to enhance model performance and efficiency.
Enhancing Fine-grained Object Detection in Aerial Images via Orthogonal Mapping
This letter introduces Orthogonal Mapping (OM), a simple yet effective method aimed at addressing the challenge of semantic confusion inherent in FGOD.
Training-free Composite Scene Generation for Layout-to-Image Synthesis
Recent breakthroughs in text-to-image diffusion models have significantly advanced the generation of high-fidelity, photo-realistic images from textual descriptions.
Surgical Triplet Recognition via Diffusion Model
In this paper, we propose DiffTriplet, a new generative framework for surgical triplet recognition employing the diffusion model, which predicts surgical triplets via iterative denoising.
Ranked #1 on
Action Triplet Recognition
on CholecT45 (cross-val)
Locating and Extracting Relational Concepts in Large Language Models
In this paper, we identify hidden states that can express entity and relational concepts through causal mediation analysis in fact recall processes.
JavaBench: A Benchmark of Object-Oriented Code Generation for Evaluating Large Language Models
First, we noticed that regarding project-level Java programming, LLMs are far behind undergraduate students (no project can be correctly completed by any studied LLMs, and at most 41. 17% Pass@5 in a more relaxed evaluation).
GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer
Cross-modal transformers have demonstrated superiority in various vision tasks by effectively integrating different modalities.
Ranked #1 on
Semantic Segmentation
on DELIVER
Pruning for Robust Concept Erasing in Diffusion Models
Experimental results show a significant enhancement in our model's ability to resist adversarial inputs, achieving nearly a 40% improvement in erasing the NSFW content and a 30% improvement in erasing artwork style.
Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model
To improve the performance of SSMs in vision tasks, a multi-scan strategy is widely adopted, which leads to significant redundancy of SSMs.
Detecting Every Object from Events
Object detection is critical in autonomous driving, and it is more practical yet challenging to localize objects of unknown categories: an endeavour known as Class-Agnostic Object Detection (CAOD).
NeRF2Points: Large-Scale Point Cloud Generation From Street Views' Radiance Field Optimization
Neural Radiance Fields (NeRF) have emerged as a paradigm-shifting methodology for the photorealistic rendering of objects and environments, enabling the synthesis of novel viewpoints with remarkable fidelity.
Towards Memorization-Free Diffusion Models
Pretrained diffusion models and their outputs are widely accessible due to their exceptional capacity for synthesizing high-quality images and their open-source nature.
ConGeo: Robust Cross-view Geo-localization across Ground View Variations
Cross-view geo-localization aims at localizing a ground-level query image by matching it to its corresponding geo-referenced aerial view.
Learning Cross-view Visual Geo-localization without Ground Truth
We observe that training on unlabeled cross-view images presents significant challenges, including the need to establish relationships within unlabeled data and reconcile view discrepancies between uncertain queries and references.
Collage Prompting: Budget-Friendly Visual Recognition with GPT-4V
Based on the observation that the accuracy of GPT-4V's image recognition varies significantly with the order of images within the collage prompt, our method further learns to optimize the arrangement of images for maximum recognition accuracy.
Understanding Robustness of Visual State Space Models for Image Classification
VMamba exhibits exceptional generalizability with out-of-distribution data but shows scalability weaknesses against natural adversarial examples and common corruptions.
EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba
Inspired by this, this work proposes to explore the potential of visual state space models in light-weight model design and introduce a novel efficient model variant dubbed EfficientVMamba.
LocalMamba: Visual State Space Model with Windowed Selective Scan
This paper posits that the key to enhancing Vision Mamba (ViM) lies in optimizing scan directions for sequence modeling.
Active Generation for Image Classification
Recently, the growing capabilities of deep generative models have underscored their potential in enhancing image classification accuracy.
MG-TSD: Multi-Granularity Time Series Diffusion Models with Guided Learning Process
However, the effective utilization of their strong modeling ability in the probabilistic time series forecasting task remains an open question, partially due to the challenge of instability arising from their stochastic nature.
Data-efficient Large Vision Models through Sequential Autoregression
Training general-purpose vision models on purely sequential visual data, eschewing linguistic inputs, has heralded a new frontier in visual understanding.
Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models
Recent advancements in large language models have sparked interest in their extraordinary and near-superhuman capabilities, leading researchers to explore methods for evaluating and optimizing these abilities, which is called superalignment.
Accelerated Cloud for Artificial Intelligence (ACAI)
Training an effective Machine learning (ML) model is an iterative process that requires effort in multiple dimensions.
Visual Imitation Learning with Calibrated Contrastive Representation
Adversarial Imitation Learning (AIL) allows the agent to reproduce expert behavior with low-dimensional states and actions.
MG-TSD: Multi-Granularity Time Series Diffusion Models with Guided Learning Process Download PDF
To address this challenge, we introduce a novel Multi-Granularity Time Series Diffusion (MG-TSD) model, which achieves state-of-the-art predictive performance by leveraging the inherent granularity levels within the data as given targets at intermediate diffusion steps to guide the learning process of diffusion models.
Random Entangled Tokens for Adversarially Robust Vision Transformer
Recognizing the challenge posed by the structural disparities between ViTs and CNNs we introduce a novel module input-independent random entangled self-attention (II-ReSA).
Hybrid Proposal Refiner: Revisiting DETR Series from the Faster R-CNN Perspective
We systematically adapt the Faster R-CNN towards the Deformable DETR by integrating or repurposing each component of Deformable DETR and note that Deformable DETR's improved performance over Faster R-CNN is attributed to the adoption of advanced modules such as a superior proposal refiner (e. g. deformable attention rather than RoI Align).
Residual Learning in Diffusion Models
This gap results in a residual in the generated images adversely impacting the image quality.
Not All Steps are Equal: Efficient Generation with Progressive Diffusion Models
In the initial stage, a base denoising model is trained to encompass all timesteps.
Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Models
We conduct a deep analysis of the three hierarchical features inherent in visual HOI detectors and propose a method for high-level relation extraction aimed at VL foundation models, which we call HO prompt-based learning.
One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation
To tackle the challenge in distilling heterogeneous models, we propose a simple yet effective one-for-all KD framework called OFA-KD, which significantly improves the distillation performance between heterogeneous architectures.
Rethinking Scale Imbalance in Semi-supervised Object Detection for Aerial Images
This paper focuses on the scale imbalance problem of semi-supervised object detection(SSOD) in aerial images.
Imitation Learning from Purified Demonstrations
In the first step, we apply a forward diffusion process to smooth potential noises in imperfect demonstrations by introducing additional noise.
DiffNAS: Bootstrapping Diffusion Models by Prompting for Better Architectures
Diffusion models have recently exhibited remarkable performance on synthetic data.
Parameter-Saving Adversarial Training: Reinforcing Multi-Perturbation Robustness via Hypernetworks
Adversarial training serves as one of the most popular and effective methods to defend against adversarial perturbations.
MM-NeRF: Multimodal-Guided 3D Multi-Style Transfer of Neural Radiance Field
3D style transfer aims to generate stylized views of 3D scenes with specified styles, which requires high-quality generating and keeping multi-view consistency.
Stealthy Physical Masked Face Recognition Attack via Adversarial Style Optimization
Moreover, to ameliorate the phenomenon of sub-optimization with one fixed style, we propose to discover the optimal style given a target through style optimization in a continuous relaxation manner.
Boosting Diffusion Models with an Adaptive Momentum Sampler
Our proposed sampler can be readily applied to a pre-trained diffusion model, utilizing momentum mechanisms and adaptive updating to smooth the reverse sampling process and ensure stable generation, resulting in outputs of enhanced quality.
A Benchmark Study on Calibration
As far as we are aware, our research represents the first large-scale investigation into calibration properties and the premier study of calibration issues within NAS.
CoNe: Contrast Your Neighbours for Supervised Image Classification
Moreover, to further boost the performance, we propose ``distributional consistency" as a more informative regularization to enable similar instances to have a similar probability distribution.
Microstructure-Empowered Stock Factor Extraction and Utilization
To address these challenges, we propose a novel framework that aims to effectively extract essential factors from order flow data for diverse downstream tasks across different granularities and scenarios.
SimMatchV2: Semi-Supervised Learning with Graph Consistency
Semi-Supervised image classification is one of the most fundamental problem in computer vision, which significantly reduces the need for human labor.
Model Synthesis for Zero-Shot Model Attribution
The design of the synthesis technique is motivated by observations on how the basic generative model's architecture building blocks and parameters influence fingerprint patterns, and it is validated through two designed metrics that examine synthetic models' fidelity and diversity.
Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detection
Human-Object Interaction (HOI) detection is a challenging computer vision task that requires visual models to address the complex interactive relationship between humans and objects and predict HOI triplets.
What Can Simple Arithmetic Operations Do for Temporal Modeling?
We conduct comprehensive ablation studies on the instantiation of ATMs and demonstrate that this module provides powerful temporal modeling capability at a low computational cost.
Ranked #4 on
Action Recognition
on Something-Something V1
Neural Architecture Retrieval
With the increasing number of new neural architecture designs and substantial existing neural architectures, it becomes difficult for the researchers to situate their contributions compared with existing neural architectures or establish the connections between their designs and other relevant ones.
Learning Structure-Guided Diffusion Model for 2D Human Pose Estimation
One of the mainstream schemes for 2D human pose estimation (HPE) is learning keypoints heatmaps by a neural network.
GPT Self-Supervision for a Better Data Annotator
In the one-shot tuning phase, we sample a data from the support set as part of the prompt for GPT to generate a textual summary, which is then used to recover the original data.
VanillaKD: Revisit the Power of Vanilla Knowledge Distillation from Small Scale to Large Scale
The tremendous success of large models trained on extensive datasets demonstrates that scale is a key ingredient in achieving superior results.
Knowledge Diffusion for Distillation
To address this, we propose to denoise student features using a diffusion model trained by teacher features.
Dual Focal Loss for Calibration
While different variants of focal loss have been explored, it is difficult to find a balance between over-confidence and under-confidence.
Can GPT-4 Perform Neural Architecture Search?
We investigate the potential of GPT-4~\cite{gpt4} to perform Neural Architecture Search (NAS) -- the task of designing effective neural architectures.
Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection
Despite the exploration of adaptive label assignment in recent oriented object detectors, the extreme geometry shape and limited feature of oriented tiny objects still induce severe mismatch and imbalance issues.
Ranked #4 on
Oriented Object Detection
on DOTA 2.0
Diffusion Action Segmentation
Temporal action segmentation is crucial for understanding long-form videos.
Ranked #2 on
Action Segmentation
on GTEA
PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformers
To handle the variances of objects as time proceeds, a novel scheme of progressive decoding is used to update pose and shape queries at each frame.
Ranked #29 on
3D Human Pose Estimation
on 3DPW
Thin Films on the Skin, but not Frictional Agents, Attenuate the Percept of Pleasantness to Brushed Stimuli
Brushed stimuli are perceived as pleasant when stroked lightly on the skin surface of a touch receiver at certain velocities.
Two-in-one Knowledge Distillation for Efficient Facial Forgery Detection
More specifically, knowledge distillation on both the spatial and frequency branches has degraded performance than distillation only on the spatial branch.
Unlabeled Imperfect Demonstrations in Adversarial Imitation Learning
The trajectories of an initial agent policy could be closer to those non-optimal expert demonstrations, but within the framework of adversarial imitation learning, agent policy will be optimized to cheat the discriminator and produce trajectories that are similar to those optimal expert demonstrations.
Calibrating a Deep Neural Network with Its Predecessors
However, early stopping, as a well-known technique to mitigate overfitting, fails to calibrate networks.
Anti-Compression Contrastive Facial Forgery Detection
To enhance the performance for such models, we consider the weak compressed and strong compressed data as two views of the original data and they should have similar representation and relationships with other samples.
Beyond Pretrained Features: Noisy Image Modeling Provides Adversarial Defense
Experimental results demonstrate that, in terms of adversarial robustness, NIM is superior to MIM thanks to its effective denoising capability.
Speech4Mesh: Speech-Assisted Monocular 3D Facial Reconstruction for Speech-Driven 3D Facial Animation
Besides, we also verify that the proposed framework is able to explicitly control the emotion of the animated talking face.
Adversarial Robustness via Random Projection Filters
Deep Neural Networks show superior performance in various tasks but are vulnerable to adversarial attacks.
Private Image Generation With Dual-Purpose Auxiliary Classifier
However, apart from this standard utility, we identify the "reversed utility" as another crucial aspect, which computes the accuracy on generated data of a classifier trained using real data, dubbed as real2gen accuracy (r2g%).
Trade-Off Between Robustness and Accuracy of Vision Transformers
Although deep neural networks (DNNs) have shown great successes in computer vision tasks, they are vulnerable to perturbations on inputs, and there exists a trade-off between the natural accuracy and robustness to such perturbations, which is mainly caused by the existence of robust non-predictive features and non-robust predictive features.
Personalized Image Generation for Color Vision Deficiency Population
Approximately, 350 million people, a proportion of 8%, suffer from color vision deficiency (CVD).
Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution
Video Super-Resolution (VSR) aims to restore high-resolution (HR) videos from low-resolution (LR) videos.
Ranked #4 on
Video Super-Resolution
on REDS4- 4x upscaling
ContraFeat: Contrasting Deep Features for Semantic Discovery
In this paper, we propose a model that automates this process and achieves state-of-the-art semantic discovery performance.
FastMIM: Expediting Masked Image Modeling Pre-training for Vision
This paper presents FastMIM, a simple and generic framework for expediting masked image modeling with the following two steps: (i) pre-training vision backbones with low-resolution input images; and (ii) reconstructing Histograms of Oriented Gradients (HOG) feature instead of original RGB values of the input images.
GhostNetV2: Enhance Cheap Operation with Long-Range Attention
The convolutional operation can only capture local information in a window region, which prevents performance from being further improved.
Boosting Semi-Supervised Semantic Segmentation with Probabilistic Representations
In prevalent pixel-wise contrastive learning solutions, the model maps pixels to deterministic representations and regularizes them in the latent space.
Learning Differential Operators for Interpretable Time Series Modeling
In this work, we propose an learning framework that can automatically obtain interpretable PDE models from sequential data.
Motion Robust High-Speed Light-Weighted Object Detection With Event Camera
In this work, we propose a motion robust and high-speed detection pipeline which better leverages the event data.
RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detection
Then, instead of assigning samples with IoU or center sampling strategy, a new Receptive Field Distance (RFD) is proposed to directly measure the similarity between the Gaussian receptive field and ground truth.
Ranked #2 on
Object Detection
on AI-TOD
Spatial-Channel Token Distillation for Vision MLPs
Recently, neural architectures with all Multi-layer Perceptrons (MLPs) have attracted great research interest from the computer vision community.
Ranked #532 on
Image Classification
on ImageNet
LightViT: Towards Light-Weight Convolution-Free Vision Transformers
Vision transformers (ViTs) are usually considered to be less light-weight than convolutional neural networks (CNNs) due to the lack of inductive bias.
Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark
Tiny object detection (TOD) in aerial images is challenging since a tiny object only contains a few pixels.
Masked Distillation with Receptive Tokens
To obtain a group of masks, the receptive tokens are learned via the regular task loss but with teacher fixed, and we also leverage a Dice loss to enrich the diversity of learned masks.
Knowledge Distillation from A Stronger Teacher
In this paper, we show that simply preserving the relations between the predictions of teacher and student would suffice, and propose a correlation-based loss to capture the intrinsic inter-class relations from the teacher explicitly.
Ranked #3 on
Knowledge Distillation
on ImageNet
(using extra training data)
Searching for Network Width with Bilaterally Coupled Network
In BCNet, each channel is fairly trained and responsible for the same amount of network widths, thus each network width can be evaluated more accurately.
DyRep: Bootstrapping Training with Dynamic Re-parameterization
Structural re-parameterization (Rep) methods achieve noticeable improvements on simple VGG-style networks.
Weak Augmentation Guided Relational Self-Supervised Learning
Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations.
Ranked #64 on
Self-Supervised Image Classification
on ImageNet
SimMatch: Semi-supervised Learning with Similarity Matching
Learning with few labeled data has been a longstanding problem in the computer vision and machine learning research community.
Multi-Tailed Vision Transformer for Efficient Inference
To satisfy the sequential input of Transformer, the tail of ViT first splits each image into a sequence of visual tokens with a fixed length.
Relational Surrogate Loss Learning
Evaluation metrics in machine learning are often hardly taken as loss functions, as they could be non-differentiable and non-decomposable, e. g., average precision and F1 score.
GhostNets on Heterogeneous Devices via Cheap Operations
The proposed C-Ghost module can be taken as a plug-and-play component to upgrade existing convolutional neural networks.
DeepFake Disrupter: The Detector of DeepFake Is My Friend
We argue that the detectors do not share a similar perspective as human eyes, which might still be spoofed by the disrupted data.
An Empirical Study of Adder Neural Networks for Object Detection
Adder neural networks (AdderNets) have shown impressive performance on image classification with only addition operations, which are more energy efficient than traditional convolutional neural networks built with multiplications.
Handling Long-tailed Feature Distribution in AdderNets
Adder neural networks (ANNs) are designed for low energy cost which replace expensive multiplications in convolutional neural networks (CNNs) with cheaper additions to yield energy-efficient neural networks and hardware accelerations.
Towards Stable and Robust AdderNets
Adder neural network (AdderNet) replaces the original convolutions with massive multiplications by cheap additions while achieving comparable performance thus yields a series of energy-efficient neural networks.
GreedyNASv2: Greedier Search with a Greedy Path Filter
In this paper, we leverage an explicit path filter to capture the characteristics of paths and directly filter those weak ones, so that the search can be thus implemented on the shrunk space more greedily and efficiently.
An Image Patch is a Wave: Phase-Aware Vision MLP
To dynamically aggregate tokens, we propose to represent each token as a wave function with two parts, amplitude and phase.
PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices
We investigate the applicability of the anchor-free strategy on lightweight object detection models.
Ranked #1 on
Object Detection
on MSCOCO
A Normalized Gaussian Wasserstein Distance for Tiny Object Detection
Our key observation is that Intersection over Union (IoU) based metrics such as IoU itself and its extensions are very sensitive to the location deviation of the tiny objects, and drastically deteriorate the detection performance when used in anchor-based detectors.
Ranked #3 on
Object Detection
on AI-TOD
Weakly Supervised Contrastive Learning
Specifically, our proposed framework is based on two projection heads, one of which will perform the regular instance discrimination task.
Learning Versatile Convolution Filters for Efficient Visual Recognition
A series of secondary filters can be derived from a primary filter with the help of binary masks.
Hire-MLP: Vision MLP via Hierarchical Rearrangement
Previous vision MLPs such as MLP-Mixer and ResMLP accept linearly flattened image patches as input, making them inflexible for different input sizes and hard to capture spatial information.
DeepFake MNIST+: A DeepFake Facial Animation Dataset
It includes 10, 000 facial animation videos in ten different actions, which can spoof the recent liveness detectors.
Neural Architecture Dilation for Adversarial Robustness
With the tremendous advances in the architecture and scale of convolutional neural networks (CNNs) over the past few decades, they can easily reach or even exceed the performance of humans in certain tasks.
ReSSL: Relational Self-Supervised Learning with Weak Augmentation
Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations.
Ranked #82 on
Self-Supervised Image Classification
on ImageNet
As Easy as 1, 2, 3: Behavioural Testing of NMT Systems for Numerical Translation
Mistranslated numbers have the potential to cause serious effects, such as financial loss or medical misinformation.
CMT: Convolutional Neural Networks Meet Vision Transformers
Vision transformers have been successfully applied to image recognition tasks due to their ability to capture long-range dependencies within an image.
Putting words into the system's mouth: A targeted attack on neural machine translation using monolingual data poisoning
Neural machine translation systems are known to be vulnerable to adversarial test inputs, however, as we show in this paper, these systems are also vulnerable to training attacks.
Augmented Shortcuts for Vision Transformers
Transformer models have achieved great progress on computer vision tasks recently.
ViTAS: Vision Transformer Architecture Search
Vision transformers (ViTs) inherited the success of NLP but their structures have not been sufficiently investigated and optimized for visual tasks.
ReNAS: Relativistic Evaluation of Neural Architecture Search
An effective and efficient architecture performance evaluation scheme is essential for the success of Neural Architecture Search (NAS).
Positive-Unlabeled Data Purification in the Wild for Object Detection
In this paper, we present a positive-unlabeled learning based scheme to expand training data by purifying valuable images from massive unlabeled ones, where the original training data are viewed as positive data and the unlabeled images in the wild are unlabeled data.
Learning Student Networks in the Wild
Experiments on various datasets demonstrate that the student networks learned by the proposed method can achieve comparable performance with those using the original dataset.
K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernets
The operation weight for each path is represented as a convex combination of items in a dictionary with a simplex code.
Commutative Lie Group VAE for Disentanglement Learning
Instead, we propose to encode the data variations with groups, a structure not only can equivariantly represent variations, but can also be adaptively optimized to preserve the properties of data variations.
Patch Slimming for Efficient Vision Transformers
We first identify the effective patches in the last layer and then use them to guide the patch selection process of previous layers.
Ranked #8 on
Efficient ViTs
on ImageNet-1K (with DeiT-T)
Universal Adder Neural Networks
The widely-used convolutions in deep neural networks are exactly cross-correlation to measure the similarity between input feature and convolution filters, which involves massive multiplications between float values.
BCNet: Searching for Network Width with Bilaterally Coupled Network
In BCNet, each channel is fairly trained and responsible for the same amount of network widths, thus each network width can be evaluated more accurately.
Where and What? Examining Interpretable Disentangled Representations
We thus impose a perturbation on a certain dimension of the latent code, and expect to identify the perturbation along this dimension from the generated images so that the encoding of simple variations can be enforced.
Distilling Object Detectors via Decoupled Features
To this end, we present a novel distillation algorithm via decoupled features (DeFeat) for learning a better student detector.
Joint Distribution across Representation Space for Out-of-Distribution Detection
Specifically, We construct a generative model, called Latent Sequential Gaussian Mixture (LSGM), to depict how the in-distribution latent features are generated in terms of the trace of DNN inference across representation spaces.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Prioritized Architecture Sampling with Monto-Carlo Tree Search
One-shot neural architecture search (NAS) methods significantly reduce the search cost by considering the whole search space as one network, which only needs to be trained once.
Learning Frequency-aware Dynamic Network for Efficient Super-Resolution
Extensive experiments conducted on benchmark SISR models and datasets show that the frequency-aware dynamic network can be employed for various SISR neural architectures to obtain the better tradeoff between visual quality and computational complexity.
Manifold Regularized Dynamic Network Pruning
Then, the manifold relationship between instances and the pruned sub-networks will be aligned in the training procedure.
LocalDrop: A Hybrid Regularization for Deep Neural Networks
In neural networks, developing regularization algorithms to settle overfitting is one of the major study areas.
Learning Frequency Domain Approximation for Binary Neural Networks
Binary neural networks (BNNs) represent original full-precision weights and activations into 1-bit with sign function.
Hero: On the Chaos When PATH Meets Modules
The results showed that \textsc{Hero} achieved a high detection rate of 98. 5\% on a DM issue benchmark and found 2, 422 new DM issues in 2, 356 popular Golang projects.
Software Engineering
REST: Relational Event-driven Stock Trend Forecasting
To remedy the first shortcoming, we propose to model the stock context and learn the effect of event information on the stocks under different contexts.
Locally Free Weight Sharing for Network Width Search
In this paper, to better evaluate each width, we propose a locally free weight sharing strategy (CafeNet) accordingly.
PTN: A Poisson Transfer Network for Semi-supervised Few-shot Learning
Second, the extra unlabeled samples are employed to transfer the knowledge from base classes to novel classes through contrastive learning.
Finite particle number description of neutron matter using the unitary correlation operator and high-momentum pair methods
The central short-range correlation coming from the short-range repulsion in the NN interaction is treated by the unitary correlation operator method (UCOM) and the tensor correlation and spin-orbit effects are described by the two-particle two-hole (2p2h) excitations of nucleon pairs, in which the two nucleons with a large relative momentum are regarded as a high-momentum pair (HM).
Nuclear Theory
Assessing Social License to Operate from the Public Discourse on Social Media
Our experimental results show that SIRTA is highly effective in distilling stances from social posts for SLO level assessment, and that the continuous monitoring of SLO levels afforded by SIRTA enables the early detection of critical SLO changes.
