Search Results for author:
Found 164 papers, 66 papers with code
Enhancing Self-Attention with Knowledge-Assisted Attention Maps
Large-scale pre-trained language models have attracted extensive attentions in the research community and shown promising results on various tasks of natural language processing.
Skywork-VL Reward: An Effective Reward Model for Multimodal Understanding and Reasoning
We propose Skywork-VL Reward, a multimodal reward model that provides reward signals for both multimodal understanding and reasoning tasks.
Learning Unknown Spoof Prompts for Generalized Face Anti-Spoofing Using Only Real Face Images
Experimental results on nine datasets demonstrate that the learned prompts effectively transfer the knowledge of vision-language models, enabling state-of-the-art generalization ability against diverse unknown attack types across unseen target domains without using any spoof face images.
Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning
We present Skywork R1V2, a next-generation multimodal reasoning model and a major leap forward from its predecessor, Skywork R1V.
LeetCodeDataset: A Temporal Dataset for Robust Evaluation and Efficient Training of Code LLMs
We introduce LeetCodeDataset, a high-quality benchmark for evaluating and training code-generation models, addressing two key challenges in LLM research: the lack of reasoning-focused coding benchmarks and self-contained training testbeds.
A Comprehensive Survey of Reward Models: Taxonomy, Applications, Challenges, and Future
Reward Model (RM) has demonstrated impressive potential for enhancing Large Language Models (LLM), as RM can serve as a proxy for human preferences, providing signals to guide LLMs' behavior in various tasks.
Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning
We introduce Seed1. 5-Thinking, capable of reasoning through thinking before responding, resulting in improved performance on a wide range of benchmarks.
Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedback
This work highlights the importance of careful data construction and provides practical methods to overcome performance barriers in RLHF.
Dereflection Any Image with Diffusion Priors and Diversified Data
Reflection removal of a single image remains a highly challenging task due to the complex entanglement between target scenes and unwanted reflections.
Ranked #1 on
Reflection Removal
on Nature
Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding
Multi-modal Large Language Models (MLLMs) have introduced a novel dimension to document understanding, i. e., they endow large language models with visual comprehension capabilities; however, how to design a suitable image-text pre-training task for bridging the visual and language modality in document-level MLLMs remains underexplored.
A Token-level Text Image Foundation Model for Document Understanding
In recent years, general visual foundation models (VFMs) have witnessed increasing adoption, particularly as image encoders for popular multi-modal large language models (MLLMs).
MDN: Mamba-Driven Dualstream Network For Medical Hyperspectral Image Segmentation
Medical Hyperspectral Imaging (MHSI) offers potential for computational pathology and precision medicine.
AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence
Current approaches for training Process Reward Models (PRMs) often involve breaking down responses into multiple reasoning steps using rule-based techniques, such as using predefined placeholder tokens or setting the reasoning step's length into a fixed size.
Unveiling the Mystery of Weight in Large Foundation Models: Gaussian Distribution Never Fades
We find that transformation weights can be derived from Gaussian noise, and they primarily serve to increase the standard deviation of pre-trained weights, with their standard deviation growing with layer depth.
Enhancing Visual Representation for Text-based Person Searching
Prior works adopt image and text encoders pre-trained on unimodal data to extract global and local features from image and text respectively, and then global-local alignment is achieved explicitly.
LiftImage3D: Lifting Any Single Image to 3D Gaussians with Video Generation Priors
Single-image 3D reconstruction remains a fundamental challenge in computer vision due to inherent geometric ambiguities and limited viewpoint information.
Realistic Surgical Simulation from Monocular Videos
To build a surgical simulation environment, we maintain a canonical 3D scene composed of 3D Gaussians coupled with a deformation field to represent a dynamic surgical scene.
Technical Report for Soccernet 2023 -- Dense Video Captioning
In the task of dense video captioning of Soccernet dataset, we propose to generate a video caption of each soccer action and locate the timestamp of the caption.
Label Filling via Mixed Supervision for Medical Image Segmentation from Noisy Annotations
The fundamental idea of label filling is to supervise the segmentation model by a subset of pixels with trustworthy labels, meanwhile filling labels of other pixels by mixed supervision.
On the Training Convergence of Transformers for In-Context Classification of Gaussian Mixtures
While transformers have demonstrated impressive capacities for in-context learning (ICL) in practice, theoretical understanding of the underlying mechanism enabling transformers to perform ICL is still in its infant stage.
RMB: Comprehensively Benchmarking Reward Models in LLM Alignment
However, the current evaluation of RMs may not directly correspond to their alignment performance due to the limited distribution of evaluation data and evaluation methods that are not closely related to alignment objectives.
Boosting Deductive Reasoning with Step Signals In RLHF
Logical reasoning is a crucial task for Large Language Models (LLMs), enabling them to tackle complex problems.
Beyond Scalar Reward Model: Learning Generative Judge from Preference Data
Conventionally, preference data is learned and encoded into a scalar reward model that connects a value head with an LLM to produce a scalar score as preference or reward.
Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknown
Reward models (RM) play a critical role in aligning generations of large language models (LLM) to human expectations.
Policy Filtration in RLHF to Fine-Tune LLM for Code Generation
Reinforcement learning from human feedback (RLHF) is one of the key techniques that helps large language models (LLMs) to follow instructions and provide helpful and harmless responses.
Task-Specific Directions: Definition, Exploration, and Utilization in Parameter Efficient Fine-Tuning
Additionally, based on our exploration of TSD, we focus on an important issue in PEFT: the initialization of LoRA.
LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models
Large language models (LLMs) face significant challenges in handling long-context tasks because of their limited effective context window size during pretraining, which restricts their ability to generalize over extended sequences.
3D-Consistent Human Avatars with Sparse Inputs via Gaussian Splatting and Contrastive Learning
Existing approaches for human avatar generation--both NeRF-based and 3D Gaussian Splatting (3DGS) based--struggle with maintaining 3D consistency and exhibit degraded detail reconstruction, particularly when training with sparse inputs.
Topology-aware Human Avatars with Semantically-guided Gaussian Splatting
To capture the explicit topological structure of the human body, we employ a 3D network that integrates both topological and geometric associations for human avatar deformation.
Leveraging Web-Crawled Data for High-Quality Fine-Tuning
Most large language models are fine-tuned using either expensive human-annotated data or GPT-4 generated data which cannot guarantee performance in certain domains.
UniProcessor: A Text-induced Unified Low-level Image Processor
In this paper, we propose a text-induced unified image processor for low-level vision tasks, termed UniProcessor, which can effectively process various degradation types and levels, and support multimodal control.
PosFormer: Recognizing Complex Handwritten Mathematical Expression with Position Forest Transformer
To overcome this challenge, we propose a position forest transformer (PosFormer) for HMER, which jointly optimizes two tasks: expression recognition and position recognition, to explicitly enable position-aware symbol feature representation learning.
See Further for Parameter Efficient Fine-tuning by Standing on the Shoulders of Decomposition
The rapid expansion of large foundation models within the pre-training and fine-tuning framework has underscored that larger models often yield better results.
Parameter-efficient Fine-tuning in Hyperspherical Space for Open-vocabulary Semantic Segmentation
Since the PEFT strategy is conducted symmetrically to the two CLIP modalities, the misalignment between them is mitigated.
Open Vocabulary Semantic Segmentation
Open-Vocabulary Semantic Segmentation
+2
Safety Control of Service Robots with LLMs and Embodied Knowledge Graphs
Safety limitations in service robotics across various industries have raised significant concerns about the need for robust mechanisms ensuring that robots adhere to safe practices, thereby preventing actions that might harm humans or cause property damage.
Vertical Federated Learning for Effectiveness, Security, Applicability: A Survey
Vertical Federated Learning (VFL) is a privacy-preserving distributed learning paradigm where different parties collaboratively learn models using partitioned features of shared samples, without leaking private data.
FLoRA: Low-Rank Core Space for N-dimension
To tackle the diversity of dimensional spaces across different foundation models and provide a more precise representation of the changes within these spaces, this paper introduces a generalized parameter-efficient fine-tuning framework, FLoRA, designed for various dimensional parameter space.
Tendency-driven Mutual Exclusivity for Weakly Supervised Incremental Semantic Segmentation
However, a scenario usually arises where a pixel is concurrently predicted as an old class by the pre-trained segmentation model and a new class by the seed areas.
FecTek: Enhancing Term Weight in Lexicon-Based Retrieval with Feature Context and Term-level Knowledge
To effectively enrich the feature context representations of term weight, the Feature Context Module (FCM) is introduced, which leverages the power of BERT's representation to determine dynamic weights for each element in the embedding.
EndoGSLAM: Real-Time Dense Reconstruction and Tracking in Endoscopic Surgeries using Gaussian Splatting
Precise camera tracking, high-fidelity 3D tissue reconstruction, and real-time online visualization are critical for intrabody medical imaging devices such as endoscopes and capsule robots.
Improving Reinforcement Learning from Human Feedback Using Contrastive Rewards
Reinforcement learning from human feedback (RLHF) is the mainstream paradigm used to align large language models (LLMs) with human preferences.
Overcoming Reward Overoptimization via Adversarial Policy Optimization with Lightweight Uncertainty Estimation
We introduce Adversarial Policy Optimization (AdvPO), a novel solution to the pervasive issue of reward over-optimization in Reinforcement Learning from Human Feedback (RLHF) for Large Language Models (LLMs).
GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splatting
Then we construct a Gaussian repair model based on diffusion models to supplement the omitted object information, where Gaussians are further refined.
Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning
In this paper, we propose R$^3$: Learning Reasoning through Reverse Curriculum Reinforcement Learning (RL), a novel method that employs only outcome supervision to achieve the benefits of process supervision for large language models.
StepCoder: Improve Code Generation with Reinforcement Learning from Compiler Feedback
The advancement of large language models (LLMs) has significantly propelled the field of code generation.
ViTree: Single-path Neural Tree for Step-wise Interpretable Fine-grained Visual Categorization
As computer vision continues to advance and finds widespread applications across various domains, the need for interpretability in deep learning models becomes paramount.
Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback
This reliance limits the applicability of RLHF and hinders the development of professional assistants tailored to diverse human preferences.
Secrets of RLHF in Large Language Models Part II: Reward Modeling
We introduce a series of novel methods to mitigate the influence of incorrect and ambiguous preferences in the dataset and fully leverage high-quality preference data.
Human-Instruction-Free LLM Self-Alignment with Limited Samples
The key idea is to first retrieve high-quality samples related to the target domain and use them as In-context Learning examples to generate more samples.
Efficient Deformable Tissue Reconstruction via Orthogonal Neural Plane
Intraoperative imaging techniques for reconstructing deformable tissues in vivo are pivotal for advanced surgical systems.
Appeal: Allow Mislabeled Samples the Chance to be Rectified in Partial Label Learning
In partial label learning (PLL), each instance is associated with a set of candidate labels among which only one is ground-truth.
LoRAMoE: Alleviate World Knowledge Forgetting in Large Language Models via MoE-Style Plugin
Supervised fine-tuning (SFT) is a crucial step for large language models (LLMs), enabling them to align with human instructions and enhance their capabilities in downstream tasks.
Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectors
Existing scene text detection methods typically rely on extensive real data for training.
Segment Any 3D Gaussians
This is achieved by attaching an scale-gated affinity feature to each 3D Gaussian to endow it a new property towards multi-granularity segmentation.
Parameter Efficient Fine-tuning via Cross Block Orchestration for Segment Anything Model
Parameter-efficient fine-tuning (PEFT) is an effective methodology to unleash the potential of large foundation models in novel scenarios with limited training data.
All Data on the Table: Novel Dataset and Benchmark for Cross-Modality Scientific Information Extraction
To close this gap in data availability and enable cross-modality IE, while alleviating labeling costs, we propose a semi-supervised pipeline for annotating entities in text, as well as entities and relations in tables, in an iterative procedure.
Stochastic Smoothed Gradient Descent Ascent for Federated Minimax Optimization
In recent years, federated minimax optimization has attracted growing interest due to its extensive applications in various machine learning tasks.
Improving Generalization of Alignment with Human Preferences through Group Invariant Learning
In this work, we propose a novel approach that can learn a consistent policy via RL across various data groups or domains.
Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback
Reinforcement learning from human feedback serves as a crucial bridge, aligning large language models with human and societal values.
SoccerNet 2023 Challenges Results
More information on the tasks, challenges, and leaderboards are available on https://www. soccer-net. org.
SAM-PARSER: Fine-tuning SAM Efficiently by Parameter Space Reconstruction
Most existing fine-tuning methods attempt to bridge the gaps among different scenarios by introducing a set of new parameters to modify SAM's original parameter space.
Joint Gaze-Location and Gaze-Object Detection
In contrast, we reframe the gaze following detection task as detecting human head locations and their gaze followings simultaneously, aiming at jointly detect human gaze location and gaze object in a unified and single-stage pipeline.
Agglomerative Transformer for Human-Object Interaction Detection
We propose an agglomerative Transformer (AGER) that enables Transformer-based human-object interaction (HOI) detectors to flexibly exploit extra instance-level cues in a single-stage and end-to-end manner for the first time.
Secrets of RLHF in Large Language Models Part I: PPO
Therefore, we explore the PPO-max, an advanced version of PPO algorithm, to efficiently improve the training stability of the policy model.
Bid Optimization for Offsite Display Ad Campaigns on eCommerce
Online retailers often use third-party demand-side-platforms (DSPs) to conduct offsite advertising and reach shoppers across the Internet on behalf of their advertisers.
Neural LerPlane Representations for Fast 4D Reconstruction of Deformable Tissues
Reconstructing deformable tissues from endoscopic stereo videos in robotic surgery is crucial for various clinical applications.
Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation
In semi-supervised medical image segmentation, there exist empirical mismatch problems between labeled and unlabeled data distribution.
Image Segmentation
Semi-supervised Medical Image Segmentation
+1
Segment Anything in 3D with Radiance Fields
The Segment Anything Model (SAM) emerges as a powerful vision foundation model to generate high-quality 2D segmentation results.
NeRFVS: Neural Radiance Fields for Free View Synthesis via Geometry Scaffolds
We present NeRFVS, a novel neural radiance fields (NeRF) based method to enable free navigation in a room.
Masked Autoencoders as Image Processors
Recently, masked autoencoders (MAE) for feature pre-training have further unleashed the potential of Transformers, leading to state-of-the-art performances on various high-level vision tasks.
Ranked #4 on
Image Defocus Deblurring
on DPD (Dual-view)
USAGE: A Unified Seed Area Generation Paradigm for Weakly Supervised Semantic Segmentation
Seed area generation is usually the starting point of weakly supervised semantic segmentation (WSSS).
RePreM: Representation Pre-training with Masked Model for Reinforcement Learning
Inspired by the recent success of sequence modeling in RL and the use of masked language model for pre-training, we propose a masked model for pre-training in RL, RePreM (Representation Pre-training with Masked Model), which trains the encoder combined with transformer blocks to predict the masked states or actions in a trajectory.
Finding Lookalike Customers for E-Commerce Marketing
Customer-centric marketing campaigns generate a large portion of e-commerce website traffic for Walmart.
MagicNet: Semi-Supervised Multi-Organ Segmentation via Magic-Cube Partition and Recovery
Our strategy encourages unlabeled images to learn organ semantics in relative locations from the labeled images (cross-branch) and enhances the learning ability for small organs (within-branch).
A K-variate Time Series Is Worth K Words: Evolution of the Vanilla Transformer Architecture for Long-term Multivariate Time Series Forecasting
In this study, we point out that the current tokenization strategy in MTSF Transformer architectures ignores the token uniformity inductive bias of Transformers.
A Transformer-Based User Satisfaction Prediction for Proactive Interaction Mechanism in DuerOS
Moreover, they are trained and evaluated on the benchmark datasets with adequate labels, which are expensive to obtain in a commercial dialogue system.
TD3 with Reverse KL Regularizer for Offline Reinforcement Learning from Mixed Datasets
There are two challenges for this setting: 1) The optimal trade-off between optimizing the RL signal and the behavior cloning (BC) signal changes on different states due to the variation of the action coverage induced by different behavior policies.
Joint Open Knowledge Base Canonicalization and Linking
However, noun phrases (NPs) and relation phrases (RPs) in OKBs are not canonicalized and often appear in different paraphrased textual variants, which leads to redundant and ambiguous facts.
Low-resource Personal Attribute Prediction from Conversation
Previous studies often rely on a relative number of resources such as labeled utterances and external data, yet the attribute knowledge embedded in unlabeled utterances is underutilized and their performance of predicting some difficult personal attributes is still unsatisfactory.
Self-supervised Character-to-Character Distillation for Text Recognition
Therefore, exploring the robust text feature representations on unlabeled real images by self-supervised learning is a good solution.
Skeleton2Humanoid: Animating Simulated Characters for Physically-plausible Motion In-betweening
Stage I introduces a test time adaptation strategy, which improves the physical plausibility of synthesized human skeleton motions by optimizing skeleton joint locations.
Deep Learning Based Page Creation for Improving E-Commerce Organic Search Traffic
Organic search comprises a large portion of the total traffic for e-commerce companies.
TEDL: A Two-stage Evidential Deep Learning Method for Classification Uncertainty Quantification
In this paper, we propose TEDL, a two-stage learning approach to quantify uncertainty for deep learning models in classification tasks, inspired by our findings in experimenting with Evidential Deep Learning (EDL) method, a recently proposed uncertainty quantification approach based on the Dempster-Shafer theory.
SwiftPruner: Reinforced Evolutionary Pruning for Efficient Ad Relevance
Remarkably, under our latency requirement of 1900us on CPU, SwiftPruner achieves a 0. 86% higher AUC than the state-of-the-art uniform sparse baseline for BERT-Mini on a large scale real-world dataset.
Personal Attribute Prediction from Conversations
Personal knowledge bases (PKBs) are critical to many applications, such as Web-based chatbots and personalized recommendation.
Learning Entity Linking Features for Emerging Entities
Entity linking (EL) is the process of linking entity mentions appearing in text with their corresponding entities in a knowledge base.
Unsupervised Domain Adaptation through Shape Modeling for Medical Image Segmentation
Previous methods proposed Variational Autoencoder (VAE) based models to learn the distribution of shape for a particular organ and used it to automatically evaluate the quality of a segmentation prediction by fitting it into the learned shape distribution.
A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction
Next, we summarize the existing label-efficient image segmentation methods from a unified perspective that discusses an important question: how to bridge the gap between weak supervision and dense prediction -- the current methods are mostly based on heuristic priors, such as cross-pixel similarity, cross-label constraint, cross-view consistency, and cross-image relation.
Multi-View Clustering for Open Knowledge Base Canonicalization
In this paper, we propose CMVC, a novel unsupervised framework that leverages these two views of knowledge jointly for canonicalizing OKBs without the need of manually annotated labels.
Video-based Human-Object Interaction Detection from Tubelet Tokens
We present a novel vision Transformer, named TUTOR, which is able to learn tubelet tokens, served as highly-abstracted spatiotemporal representations, for video-based human-object interaction (V-HOI) detection.
Community Question Answering Entity Linking via Leveraging Auxiliary Data
Community Question Answering (CQA) platforms contain plenty of CQA texts (i. e., questions and answers corresponding to the question) where named entities appear ubiquitously.
ChildPredictor: A Child Face Prediction Framework with Disentangled Learning
On this basis, we formulate predictions as a mapping from parents' genetic factors to children's genetic factors, and disentangle them from external and variety factors.
Age-Invariant Face Recognition
Image-to-Image Translation
+3
Saliency in Augmented Reality
Therefore, in this paper, we mainly analyze the interaction effect between background (BG) scenes and AR contents, and study the saliency prediction problem in AR.
CP2: Copy-Paste Contrastive Pretraining for Semantic Segmentation
Recent advances in self-supervised contrastive learning yield good image-level representation, which favors classification tasks but usually neglects pixel-level detailed information, leading to unsatisfactory transfer performance to dense prediction tasks such as semantic segmentation.
Iwin: Human-Object Interaction Detection via Transformer with Irregular Windows
Iwin Transformer is a hierarchical Transformer which progressively performs token representation learning and token agglomeration within irregular windows.
End-to-End Human-Gaze-Target Detection with Transformers
In contrast, we redefine the HGT detection task as detecting human head locations and their gaze targets, simultaneously.
ContrastMask: Contrastive Learning to Segment Every Thing
In this framework, annotated masks of seen categories and pseudo masks of unseen categories serve as a prior for contrastive learning, where features from the mask regions (foreground) are pulled together, and are contrasted against those from the background, and vice versa.
Geometric Synthesis: A Free lunch for Large-scale Palmprint Recognition Model Pretraining
In this paper, by observing that palmar creases are the key information to deep-learning-based palmprint recognition, we propose to synthesize training data by manipulating palmar creases.
Self-supervised Implicit Glyph Attention for Text Recognition
Supervised attention can alleviate the above issue, but it is character category-specific, which requires extra laborious character-level bounding box annotations and would be memory-intensive when handling languages with larger character categories.
Ranked #2 on
Scene Text Recognition
on ICDAR 2003
External Attention Assisted Multi-Phase Splenic Vascular Injury Segmentation with Limited Data
The spleen is one of the most commonly injured solid organs in blunt abdominal trauma.
Consensus Synergizes with Memory: A Simple Approach for Anomaly Segmentation in Urban Scenes
Anomaly segmentation is a crucial task for safety-critical applications, such as autonomous driving in urban scenes, where the goal is to detect out-of-distribution (OOD) objects with categories which are unseen during training.
Ranked #10 on
Anomaly Detection
on Fishyscapes L&F
Intriguing Findings of Frequency Selection for Image Deblurring
Blur was naturally analyzed in the frequency domain, by estimating the latent sharp image and the blur kernel given a blurry image.
Ranked #5 on
Deblurring
on RealBlur-R (trained on GoPro)
iBOT: Image BERT Pre-Training with Online Tokenizer
We present a self-supervised framework iBOT that can perform masked prediction with an online tokenizer.
Ranked #4 on
Unsupervised Image Classification
on ImageNet
Image BERT Pre-training with Online Tokenizer
The success of language Transformers is primarily attributed to the pretext task of masked language modeling (MLM), where texts are first tokenized into semantically meaningful pieces.
Entity Linking Meets Deep Learning: Techniques and Solutions
Entity linking (EL) is the process of linking entity mentions appearing in web text with their corresponding entities in a knowledge base.
Inductive Matrix Completion Using Graph Autoencoder
However, without node content (i. e., side information) for training, the user (or item) specific representation can not be learned in the inductive setting, that is, a model trained on one group of users (or items) cannot adapt to new users (or items).
Ranked #3 on
Recommendation Systems
on MovieLens 1M
An Efficient Group-based Search Engine Marketing System for E-Commerce
With the increasing scale of search engine marketing, designing an efficient bidding system is becoming paramount for the success of e-commerce companies.
Dual Attention Guided Gaze Target Detection in the Wild
In the third stage, we use the generated dual attention as guidance to perform two sub-tasks: (1) identifying whether the gaze target is inside or out of the image; (2) locating the target if inside.
The Medical Segmentation Decathlon
Segmentation is so far the most widely investigated medical image processing task, but the various segmentation challenges have typically been organized in isolation, such that algorithm development was driven by the need to tackle a single specific clinical problem.
Making CNNs Interpretable by Building Dynamic Sequential Decision Forests with Top-down Hierarchy Learning
In this paper, we propose a generic model transfer scheme to make Convlutional Neural Networks (CNNs) interpretable, while maintaining their high classification accuracy.
Glance-and-Gaze Vision Transformer
It is motivated by the Glance and Gaze behavior of human beings when recognizing objects in natural scenes, with the ability to efficiently model both long-range dependencies and local context.
Learning Inductive Attention Guidance for Partially Supervised Pancreatic Ductal Adenocarcinoma Prediction
We instantiate both the global and the local classifiers by multiple instance learning (MIL), where the attention guidance, indicating roughly where the PDAC regions are, is the key to bridging them: For global MIL based normal/PDAC classification, attention serves as a weight for each instance (voxel) during MIL pooling, which eliminates the distraction from the background; For local MIL based semi-supervised PDAC segmentation, the attention guidance is inductive, which not only provides bag-level pseudo-labels to training data without per-voxel annotations for MIL training, but also acts as a proxy of an instance-level classifier.
Toward Tweet Entity Linking with Heterogeneous Information Networks
The task of linking an entity mention in a tweet with its corresponding entity in a heterogeneous information network is of great importance, for the purpose of enriching heterogeneous information networks with the abundant and fresh knowledge embedded in tweets.
SpecTr: Spectral Transformer for Hyperspectral Pathology Image Segmentation
Hyperspectral imaging (HSI) unlocks the huge potential to a wide variety of applications relied on high-precision pathology image segmentation, such as computational pathology and precision medicine.
Looking Here or There? Gaze Following in 360-Degree Images
Specifically, the local region is obtained as a 2D cone-shaped field along the 2D projection of the sight line starting at the human subject's head position, and the distant region is obtained by searching along the sight line in 3D sphere space.
Batch Normalization with Enhanced Linear Transformation
Batch normalization (BN) is a fundamental unit in modern deep networks, in which a linear transformation module was designed for improving BN's flexibility of fitting complex data distributions.
Volumetric Medical Image Segmentation: A 3D Deep Coarse-to-fine Framework and Its Adversarial Examples
Although deep neural networks have been a dominant method for many 2D vision tasks, it is still challenging to apply them to 3D tasks, such as medical image segmentation, due to the limited amount of annotated 3D data and limited computational resources.
AutoADR: Automatic Model Design for Ad Relevance
We add the model designed by AutoADR as a sub-model into the production Ad Relevance model.
Shape-Texture Debiased Neural Network Training
To prevent models from exclusively attending on a single cue in representation learning, we augment training data with images with conflicting shape and texture information (eg, an image of chimpanzee shape but with lemon texture) and, most importantly, provide the corresponding supervisions from shape and texture simultaneously.
Ranked #1 on
Image Classification
on ImageNet
(Hardware Burden metric)
CO2: Consistent Contrast for Unsupervised Visual Representation Learning
Regarding the similarity of the query crop to each crop from other images as "unlabeled", the consistency term takes the corresponding similarity of a positive crop as a pseudo label, and encourages consistency between these two similarities.
Auxiliary-task Based Deep Reinforcement Learning for Participant Selection Problem in Mobile Crowdsourcing
Therefore, it is crucial to design a participant selection algorithm that applies to different MCS systems to achieve multiple goals.
Towards Unsupervised Learning for Instrument Segmentation in Robotic Surgery with Cycle-Consistent Adversarial Networks
Surgical tool segmentation in endoscopic images is an important problem: it is a crucial step towards full instrument pose estimation and it is used for integration of pre- and intra-operative images into the endoscopic view.
Statistical Issues and Recommendations for Clinical Trials Conducted During the COVID-19 Pandemic
The COVID-19 pandemic has had and continues to have major impacts on planned and ongoing clinical trials.
Domain Adaptive Relational Reasoning for 3D Multi-Organ Segmentation
In this paper, we present a novel unsupervised domain adaptation (UDA) method, named Domain Adaptive Relational Reasoning (DARR), to generalize 3D multi-organ segmentation models to medical data collected from different scanners and/or protocols (domains).
Segmentation for Classification of Screening Pancreatic Neuroendocrine Tumors
This work presents comprehensive results to detect in the early stage the pancreatic neuroendocrine tumors (PNETs), a group of endocrine tumors arising in the pancreas, which are the second common type of pancreatic cancer, by checking the abdominal CT scans.
Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation
The ability to detect failures and anomalies are fundamental requirements for building reliable systems for computer vision applications, especially safety-critical applications of semantic segmentation, such as autonomous driving and medical image analysis.
Ranked #10 on
Anomaly Detection
on Road Anomaly
(using extra training data)
Detecting Pancreatic Ductal Adenocarcinoma in Multi-phase CT Scans via Alignment Ensemble
Pancreatic ductal adenocarcinoma (PDAC) is one of the most lethal cancers among the population.
Deep Distance Transform for Tubular Structure Segmentation in CT Scans
Tubular structure segmentation in medical images, e. g., segmenting vessels in CT scans, serves as a vital step in the use of computers to aid in screening early stages of related diseases.
Deeply Shape-guided Cascade for Instance Segmentation
The key to a successful cascade architecture for precise instance segmentation is to fully leverage the relationship between bounding box detection and mask segmentation across multiple stages.
Rethinking Normalization and Elimination Singularity in Neural Networks
To address this issue, we propose BatchChannel Normalization (BCN), which uses batch knowledge to avoid the elimination singularities in the training of channel-normalized models.
TDAPNet: Prototype Network with Recurrent Top-Down Attention for Robust Object Classification under Partial Occlusion
Despite deep convolutional neural networks' great success in object classification, it suffers from severe generalization performance drop under occlusion due to the inconsistency between training and testing data.
Deep Differentiable Random Forests for Age Estimation
Both of them connect split nodes to the top layer of convolutional neural networks (CNNs) and deal with inhomogeneous data by jointly learning input-dependent data partitions at the split nodes and age distributions at the leaf nodes.
Learning to Find Correlated Features by Maximizing Information Flow in Convolutional Neural Networks
We argue that the discard of the correlated discriminative information is partially caused by the fact that the minimization of the classification loss doesn't ensure to learn the overall discriminative information but only the most discriminative information.
Stability and Optimization Error of Stochastic Gradient Descent for Pairwise Learning
From this fundamental trade-off, we obtain lower bounds for the optimization error of SGD algorithms and the excess expected risk over a class of pairwise losses.
Micro-Batch Training with Batch-Channel Normalization and Weight Standardization
Batch Normalization (BN) has become an out-of-box technique to improve deep network training.
Ranked #79 on
Instance Segmentation
on COCO minival
Learning from Adversarial Features for Few-Shot Classification
Then we use the adversarial region attention to aggregate the feature maps to obtain the adversarial features.
Learning to generate filters for convolutional neural networks
In this paper, we propose to generate sample-specific filters for convolutional layers in the forward pass.
Robust Face Detection via Learning Small Faces on Hard Images
In this paper, we propose that the robustness of a face detector against hard faces can be improved by learning small faces on hard images.
Ranked #7 on
Face Detection
on WIDER Face (Hard)
Generating Attention from Classifier Activations for Fine-grained Recognition
Recent advances in fine-grained recognition utilize attention maps to localize objects of interest.
Tackling Early Sparse Gradients in Softmax Activation Using Leaky Squared Euclidean Distance
However, we find that choosing squared Euclidean distance may cause distance explosion leading gradients to be extremely sparse in the early stage of back propagation.
PCL: Proposal Cluster Learning for Weakly Supervised Object Detection
The iterative instance classifier refinement is implemented online using multiple streams in convolutional neural networks, where the first is an MIL network and the others are for instance classifier refinement supervised by the preceding one.
Ranked #1 on
Weakly Supervised Object Detection
on ImageNet
Hifi: Hierarchical feature integration for skeleton detection
In natural images, the scales (thickness) of object skeletons may dramatically vary among objects and object parts.
Resisting Large Data Variations via Introspective Transformation Network
Experimental results verify that our approach significantly improves the ability of deep networks to resist large variations between training and testing data and achieves classification accuracy improvements on several benchmark datasets, including MNIST, affNIST, SVHN, CIFAR-10 and miniImageNet.
Abdominal multi-organ segmentation with organ-attention networks and statistical fusion
To address these challenges, we introduce a novel framework for multi-organ segmentation by using organ-attention networks with reverse connections (OAN-RCs) which are applied to 2D views, of the 3D CT volume, and output estimates which are combined by statistical fusion exploiting structural similarity.
Semi-Supervised Multi-Organ Segmentation via Deep Multi-Planar Co-Training
In multi-organ segmentation of abdominal CT scans, most existing fully supervised deep learning algorithms require lots of voxel-wise annotations, which are usually difficult, expensive, and slow to obtain.
Training Multi-organ Segmentation Networks with Sample Selection by Relaxed Upper Confident Bound
Based on the fact that very hard samples might have annotation errors, we propose a new sample selection policy, named Relaxed Upper Confident Bound (RUCB).
Deep Co-Training for Semi-Supervised Image Recognition
We present Deep Co-Training, a deep learning based method inspired by the Co-Training framework.
Hi-Fi: Hierarchical Feature Integration for Skeleton Detection
In natural images, the scales (thickness) of object skeletons may dramatically vary among objects and object parts, making object skeleton detection a challenging problem.
Ranked #2 on
Object Skeleton Detection
on SK-LARGE
Deep Regression Forests for Age Estimation
Age estimation from facial images is typically cast as a nonlinear regression problem.
Ranked #6 on
Age Estimation
on FGNET
A 3D Coarse-to-Fine Framework for Volumetric Medical Image Segmentation
In this paper, we adopt 3D Convolutional Neural Networks to segment volumetric medical images.
Single-Shot Object Detection with Enriched Semantics
Our motivation is to enrich the semantics of object detection features within a typical deep detector, by a semantic segmentation branch and a global activation module.
Gradually Updated Neural Networks for Large-Scale Image Recognition
Our method is by introducing computation orderings to the channels within convolutional layers or blocks, based on which we gradually compute the outputs in a channel-wise manner.
Few-Shot Image Recognition by Predicting Parameters from Activations
In this paper, we are interested in the few-shot learning problem.
ScaleNet: Guiding Object Proposal Generation in Supermarkets and Beyond
We argue that estimation of object scales in images is helpful for generating object proposals, especially for supermarket images where object scales are usually within a small range.
Multi-stage Multi-recursive-input Fully Convolutional Networks for Neuronal Boundary Detection
This design is biologically-plausible, as it likes a human visual system to compare different possible segmentation solutions to address the ambiguous boundary issue.
Label Distribution Learning Forests
This paper presents label distribution learning forests (LDLFs) - a novel label distribution learning algorithm based on differentiable decision trees, which have several advantages: 1) Decision trees have the potential to model any general form of label distributions by a mixture of leaf node predictions.
Ranked #11 on
Age Estimation
on MORPH album2 (Caucasian)
A Fixed-Point Model for Pancreas Segmentation in Abdominal CT Scans
Deep neural networks have been widely adopted for automatic organ segmentation from abdominal CT scans.
Learning Residual Images for Face Attribute Manipulation
The transformation networks are responsible for the attribute manipulation and its dual operation and the discriminative network is used to distinguish the generated images from real images.
DeepSkeleton: Learning Multi-task Scale-associated Deep Side Outputs for Object Skeleton Extraction in Natural Images
By observing the relationship between the receptive field sizes of the different layers in the network and the skeleton scales they can capture, we introduce two scale-associated side outputs to each stage of the network.
Shape Recognition by Bag of Skeleton-associated Contour Parts
Contour and skeleton are two complementary representations for shape recognition.
Multi-Oriented Text Detection with Fully Convolutional Networks
In this paper, we propose a novel approach for text detec- tion in natural images.
Ranked #40 on
Scene Text Detection
on ICDAR 2015
Object Skeleton Extraction in Natural Images by Fusing Scale-associated Deep Side Outputs
Object skeleton is a useful cue for object detection, complementary to the object contour, as it provides a structural representation to describe the relationship among object parts.
DeepContour: A Deep Convolutional Feature Learned by Positive-Sharing Loss for Contour Detection
Contour detection serves as the basis of a variety of computer vision tasks such as image segmentation and object recognition.
Symmetry-Based Text Line Detection in Natural Scenes
Recently, a variety of real-world applications have triggered huge demand for techniques that can extract textual information from natural scenes.
