Search Results for author:
Found 214 papers, 139 papers with code
API-Net: Robust Generative Classifier via a Single Discriminator
On the contrary, a discriminative classifier only models the conditional distribution of labels given inputs, but benefits from effective optimization owing to its succinct structure.
SSCGAN: Facial Attribute Editing via Style Skip Connections
Each connection extracts the style feature of the latent feature maps in the encoder and then performs a residual learning based mapping function in the global information space guided by the target attributes.
Enabling Deep Residual Networks for Weakly Supervised Object Detection
Weakly supervised object detection (WSOD) has attracted extensive research attention due to its great flexibility of exploiting large-scale image-level annotation for detector training.
I&S-ViT: An Inclusive & Stable Method for Pushing the Limit of Post-Training ViTs Quantization
Albeit the scalable performance of vision transformers (ViTs), the dense computational costs (training & inference) undermine their position in industrial applications.
Semi-Supervised Panoptic Narrative Grounding
Remarkably, our SS-PNG-NW+ outperforms fully-supervised models with only 30% and 50% supervision data, exceeding their performance by 0. 8% and 1. 1% respectively.
NICE: Improving Panoptic Narrative Detection and Segmentation with Cascading Collaborative Learning
To address this, we introduce two cascading modules based on the barycenter of the mask, which are Coordinate Guided Aggregation (CGA) and Barycenter Driven Localization (BDL), responsible for segmentation and detection, respectively.
JM3D & JM3D-LLM: Elevating 3D Representation with Joint Multi-modal Cues
The rising importance of 3D representation learning, pivotal in computer vision, autonomous driving, and robotics, is evident.
Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs
Inspired by the Dynamic Sparse Training, DSnoT minimizes the reconstruction error between the dense and sparse LLMs, in the fashion of performing iterative weight pruning-and-growing on top of sparse LLMs.
AutoDiffusion: Training-Free Optimization of Time Steps and Architectures for Automated Diffusion Model Acceleration
Therefore, we propose to search the optimal time steps sequence and compressed model architecture in a unified framework to achieve effective image generation for diffusion models without any further training.
Towards Unified Token Learning for Vision-Language Tracking
In this paper, we present a simple, flexible and effective vision-language (VL) tracking pipeline, termed \textbf{MMTrack}, which casts VL tracking as a token generation task.
DLIP: Distilling Language-Image Pre-training
Furthermore, DLIP succeeds in retaining more than 95% of the performance with 22. 4% parameters and 24. 8% FLOPs compared to the teacher model and accelerates inference speed by 2. 7x.
A Unified Framework for 3D Point Cloud Visual Grounding
This elaborate design enables 3DRefTR to achieve both well-performing 3DRES and 3DREC capacities with only a 6% additional latency compared to the original 3DREC model.
M3PS: End-to-End Multi-Grained Multi-Modal Attribute-Aware Product Summarization in E-commerce
Furthermore, we model product attributes based on both text and image modalities so that multi-modal product characteristics can be manifested in the generated summaries.
HODN: Disentangling Human-Object Feature for HOI Detection
However, these methods ignore the relationship among humans, objects, and interactions: 1) human features are more contributive than object ones to interaction prediction; 2) interactive information disturbs the detection of objects but helps human detection.
Continual Face Forgery Detection via Historical Distribution Preserving
In this paper, we focus on a novel and challenging problem: Continual Face Forgery Detection (CFFD), which aims to efficiently learn from new forgery attacks without forgetting previous ones.
Pseudo-label Alignment for Semi-supervised Instance Segmentation
Through extensive experiments conducted on the COCO and Cityscapes datasets, we demonstrate that PAIS is a promising framework for semi-supervised instance segmentation, particularly in cases where labeled data is severely limited.
Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D Representation
Insufficient synergy neglects the idea that a robust 3D representation should align with the joint vision-language space, rather than independently aligning with each modality.
Improving Human-Object Interaction Detection via Virtual Image Learning
Human-Object Interaction (HOI) detection aims to understand the interactions between humans and objects, which plays a curtail role in high-level semantic understanding tasks.
Towards General Visual-Linguistic Face Forgery Detection
To address this issues, in this paper, we propose a novel paradigm named Visual-Linguistic Face Forgery Detection(VLFFD), which uses fine-grained sentence-level prompts as the annotation.
Systematic Investigation of Sparse Perturbed Sharpness-Aware Minimization Optimizer
Sharpness-Aware Minimization (SAM) is a popular solution that smooths the loss landscape by minimizing the maximized change of training loss when adding a perturbation to the weight.
Approximated Prompt Tuning for Vision-Language Pre-trained Models
Prompt tuning is a parameter-efficient way to deploy large-scale pre-trained models to downstream tasks by adding task-specific tokens.
MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models
Multimodal Large Language Model (MLLM) relies on the powerful LLM to perform multimodal tasks, showing amazing emergent abilities in recent studies, such as writing poems based on an image.
Spatial Re-parameterization for N:M Sparsity
This paper presents a Spatial Re-parameterization (SpRe) method for the N:M sparsity in CNNs.
STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection
To solve this problem, we propose a Self-adapTive Ambiguity Reduction (STAR) loss by exploiting the properties of semantic ambiguity.
Ranked #1 on
Face Alignment
on 300W
Adapting Pre-trained Language Models to Vision-Language Tasks via Dynamic Visual Prompting
In addition, we also experiment DVP with the recently popular adapter approach to keep the most parameters of PLMs intact when adapting to VL tasks, helping PLMs achieve a quick shift between single- and multi-modal tasks.
DiffRate : Differentiable Compression Rate for Efficient Vision Transformers
Token compression aims to speed up large-scale vision transformers (e. g. ViTs) by pruning (dropping) or merging tokens.
CamoDiffusion: Camouflaged Object Detection via Conditional Diffusion Models
Due to the stochastic sampling process of diffusion, our model is capable of sampling multiple possible predictions from the mask distribution, avoiding the problem of overconfident point estimation.
MultiQuant: A Novel Multi-Branch Topology Method for Arbitrary Bit-width Network Quantization
However, in this paper, we investigate existing methods and observe a significant accumulation of quantization errors caused by frequent bit-width switching of weights and activations, leading to limited performance.
Distribution-Flexible Subset Quantization for Post-Quantizing Super-Resolution Networks
Compared to the common iterative exhaustive search algorithm, our strategy avoids the enumeration of all possible combinations in the universal set, reducing the time complexity from exponential to linear.
InterFormer: Real-time Interactive Image Segmentation
Interactive image segmentation enables annotators to efficiently perform pixel-level annotation for segmentation tasks.
Latent Feature Relation Consistency for Adversarial Robustness
Deep neural networks have been applied in many computer vision tasks and achieved state-of-the-art performance.
X-Mesh: Towards Fast and Accurate Text-driven 3D Stylization via Dynamic Textual Guidance
Text-driven 3D stylization is a complex and crucial task in the fields of computer vision (CV) and computer graphics (CG), aimed at transforming a bare mesh to fit a target text.
CAT:Collaborative Adversarial Training
By revisiting the previous methods, we find different adversarial training methods have distinct robustness for sample instances.
You Only Segment Once: Towards Real-Time Panoptic Segmentation
To reduce the computational overhead, we design a feature pyramid aggregator for the feature map extraction, and a separable dynamic decoder for the panoptic kernel generation.
Solving Oscillation Problem in Post-Training Quantization Through a Theoretical Perspective
In particular, we first formulate the oscillation in PTQ and prove the problem is caused by the difference in module capacity.
Attention Disturbance and Dual-Path Constraint Network for Occluded Person Re-Identification
Occluded person re-identification (Re-ID) aims to address the potential occlusion problem when matching occluded or holistic pedestrians from different camera views.
Active Teacher for Semi-Supervised Object Detection
In this paper, we study teacher-student learning from the perspective of data initialization and propose a novel algorithm called Active Teacher(Source code are available at: \url{https://github. com/HunterJ-Lin/ActiveTeacher}) for semi-supervised object detection (SSOD).
DistilPose: Tokenized Pose Regression with Heatmap Distillation
Specifically, DistilPose maximizes the transfer of knowledge from the teacher model (heatmap-based) to the student model (regression-based) through Token-distilling Encoder (TDE) and Simulated Heatmaps.
Towards End-to-end Semi-supervised Learning for One-stage Object Detection
In addition to this challenge, we also reveal two key issues in one-stage SSOD, which are low-quality pseudo-labeling and multi-task optimization conflict, respectively.
Towards Efficient Visual Adaption via Structural Re-parameterization
Experimental results show the superior performance and efficiency of RepAdapter than the state-of-the-art PETL methods.
Bi-directional Masks for Efficient N:M Sparse Training
We focus on addressing the dense backward propagation issue for training efficiency of N:M fine-grained sparsity that preserves at most N out of M consecutive weights and achieves practical speedups supported by the N:M sparse tensor core.
Towards Local Visual Modeling for Image Captioning
In this paper, we study the local visual modeling with grid features for image captioning, which is critical for generating accurate and detailed captions.
Real-Time Image Demoireing on Mobile Devices
In this paper, we launch the first study on accelerating demoireing networks and propose a dynamic demoireing acceleration method (DDA) towards a real-time deployment on mobile devices.
Spectral Aware Softmax for Visible-Infrared Person Re-Identification
Based on the observation and analysis of SA-Softmax, we modify the SA-Softmax with the Feature Mask and Absolute-Similarity Term to alleviate the ambiguous optimization during model training.
Exploring Invariant Representation for Visible-Infrared Person Re-Identification
Cross-spectral person re-identification, which aims to associate identities to pedestrians across different spectra, faces a main challenge of the modality discrepancy.
Unsupervised Domain Adaptation on Person Re-Identification via Dual-level Asymmetric Mutual Learning
The knowledge transfer between two networks is based on an asymmetric mutual learning manner.
RefTeacher: A Strong Baseline for Semi-Supervised Referring Expression Comprehension
In this paper, we present the first attempt of semi-supervised learning for REC and propose a strong baseline method called RefTeacher.
Category-aware Allocation Transformer for Weakly Supervised Object Localization
Weakly supervised object localization (WSOL) aims to localize objects based on only image-level labels as supervision.
RefCLIP: A Universal Teacher for Weakly Supervised Referring Expression Comprehension
Based on RefCLIP, we further propose the first model-agnostic weakly supervised training scheme for existing REC models, where RefCLIP acts as a mature teacher to generate pseudo-labels for teaching common REC models.
Automatic Network Pruning via Hilbert-Schmidt Independence Criterion Lasso under Information Bottleneck Principle
In this paper, we try to solve this problem by introducing a principled and unified framework based on Information Bottleneck (IB) theory, which further guides us to an automatic pruning approach.
Discriminator-Cooperated Feature Map Distillation for GAN Compression
In contrast to conventional pixel-to-pixel match methods in feature map distillation, our DCD utilizes teacher discriminator as a transformation to drive intermediate results of the student generator to be perceptually close to corresponding outputs of the teacher generator.
SMMix: Self-Motivated Image Mixing for Vision Transformers
Due to the subtle designs of the self-motivated paradigm, our SMMix is significant in its smaller training overhead and better performance than other CutMix variants.
Exploring Content Relationships for Distilling Efficient GANs
This paper proposes a content relationship distillation (CRD) to tackle the over-parameterized generative adversarial networks (GANs) for the serviceability in cutting-edge devices.
Shadow Removal by High-Quality Shadow Synthesis
Specifically, the encoder extracts the shadow feature of a region identity which is then paired with another region identity to serve as the generator input to synthesize a pseudo image.
Self-supervised Graph Representation Learning for Black Market Account Detection
This paper illustrates our BMA detection system SGRL (Self-supervised Graph Representation Learning) used in WeChat, a representative MMMA with over a billion users.
Meta Architecture for Point Cloud Analysis
However, the lack of a unified framework to interpret those networks makes any systematic comparison, contrast, or analysis challenging, and practically limits healthy development of the field.
Ranked #7 on
Semantic Segmentation
on S3DIS
Exploiting the Partly Scratch-off Lottery Ticket for Quantization-Aware Training
In QAT, the contemporary experience is that all quantized weights are updated for an entire training process.
Make Sharpness-Aware Minimization Stronger: A Sparsified Perturbation Approach
One of the popular solutions is Sharpness-Aware Minimization (SAM), which smooths the loss landscape via minimizing the maximized change of training loss when adding a perturbation to the weight.
ECO-TR: Efficient Correspondences Finding Via Coarse-to-Fine Refinement
In this paper, we propose an efficient structure named Efficient Correspondence Transformer (ECO-TR) by finding correspondences in a coarse-to-fine manner, which significantly improves the efficiency of functional correspondence model.
Exploring Target Representations for Masked Autoencoders
Masked autoencoders have become popular training paradigms for self-supervised visual representation learning.
LAB-Net: LAB Color-Space Oriented Lightweight Network for Shadow Removal
Finally, the LSA modules are further developed to fully use the prior information in non-shadow regions to cleanse the shadow regions.
CycleTrans: Learning Neutral yet Discriminative Features for Visible-Infrared Person Re-Identification
Visible-infrared person re-identification (VI-ReID) is a task of matching the same individuals across the visible and infrared modalities.
Dynamic Prototype Mask for Occluded Person Re-Identification
Although person re-identification has achieved an impressive improvement in recent years, the common occlusion case caused by different obstacles is still an unsettled issue in real application scenarios.
Cycle Encoding of a StyleGAN Encoder for Improved Reconstruction and Editability
The recently proposed pivotal tuning model makes significant progress towards reconstruction and editability, by using a two-step approach that first inverts the input image into a latent code, called pivot code, and then alters the generator so that the input image can be accurately mapped into the pivot code.
Clover: Towards A Unified Video-Language Alignment and Fusion Model
We then introduce \textbf{Clover}\textemdash a Correlated Video-Language pre-training method\textemdash towards a universal Video-Language model for solving multiple video understanding tasks with neither performance nor efficiency compromise.
Ranked #1 on
Video Question Answering
on LSMDC-FiB
X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval
However, cross-grained contrast, which is the contrast between coarse-grained representations and fine-grained representations, has rarely been explored in prior research.
Ranked #10 on
Video Retrieval
on MSVD
Privacy-Preserving Face Recognition with Learnable Privacy Budgets in Frequency Domain
This paper proposes a privacy-preserving face recognition method using differential privacy in the frequency domain.
Learning Best Combination for Efficient N:M Sparsity
In this paper, we show that the N:M learning can be naturally characterized as a combinatorial problem which searches for the best combination candidate within a finite collection.
Super Vision Transformer
Experimental results on ImageNet demonstrate that our SuperViT can considerably reduce the computational costs of ViT models with even performance increase.
Shadow-Aware Dynamic Convolution for Shadow Removal
Inspired by the fact that the color mapping of the non-shadow region is easier to learn, our SADC processes the non-shadow region with a lightweight convolution module in a computationally cheap manner and recovers the shadow region with a more complicated convolution module to ensure the quality of image reconstruction.
PyramidCLIP: Hierarchical Feature Alignment for Vision-language Model Pretraining
Large-scale vision-language pre-training has achieved promising results on downstream tasks.
A Closer Look at Branch Classifiers of Multi-exit Architectures
Multi-exit architectures consist of a backbone and branch classifiers that offer shortened inference pathways to reduce the run-time of deep neural networks.
A Survivor in the Era of Large-Scale Pretraining: An Empirical Study of One-Stage Referring Expression Comprehension
But the most encouraging finding is that with much less training overhead and parameters, SimREC can still achieve better performance than a set of large-scale pre-trained models, e. g., UNITER and VILLA, portraying the special role of REC in existing V&L research.
Towards Lightweight Transformer via Group-wise Transformation for Vision-and-Language Tasks
Despite the exciting performance, Transformer is criticized for its excessive parameters and computation cost.
PixelFolder: An Efficient Progressive Pixel Synthesis Network for Image Generation
Pixel synthesis is a promising research paradigm for image generation, which can well exploit pixel-wise prior knowledge for generation.
SeqTR: A Simple yet Universal Network for Visual Grounding
In this paper, we propose a simple yet universal network termed SeqTR for visual grounding tasks, e. g., phrase localization, referring expression comprehension (REC) and segmentation (RES).
Training-free Transformer Architecture Search
Recently, Vision Transformer (ViT) has achieved remarkable success in several computer vision tasks.
ARM: Any-Time Super-Resolution Method
To that effect, we construct an Edge-to-PSNR lookup table that maps the edge score of an image patch to the PSNR performance for each subnet, together with a set of computation costs for the subnets.
Global2Local: A Joint-Hierarchical Attention for Video Captioning
Recently, automatic video captioning has attracted increasing attention, where the core challenge lies in capturing the key semantic items, like objects and actions as well as their spatial-temporal correlations from the redundant frames and semantic content.
Factored Attention and Embedding for Unstructured-view Topic-related Ultrasound Report Generation
Echocardiography is widely used to clinical practice for diagnosis and treatment, e. g., on the common congenital heart defects.
Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks
However, these methods suffer from severe performance degradation when quantizing the SR models to ultra-low precision (e. g., 2-bit and 3-bit) with the low-cost layer-wise quantizer.
CF-ViT: A General Coarse-to-Fine Method for Vision Transformer
Our proposed CF-ViT is motivated by two important observations in modern ViT models: (1) The coarse-grained patch splitting can locate informative regions of an input image.
Boosting Crowd Counting via Multifaceted Attention
Secondly, we design the Local Attention Regularization to supervise the training of LRA by minimizing the deviation among the attention for different feature locations.
Pruning Networks with Cross-Layer Ranking & k-Reciprocal Nearest Filters
Then, we introduce a recommendation-based filter selection scheme where each filter recommends a group of its closest filters.
OptG: Optimizing Gradient-driven Criteria in Network Sparsity
We prove that supermask training is to accumulate the criteria of gradient-driven sparsity for both removed and preserved weights, and it can partly solve the independence paradox.
Winning solutions and post-challenge analyses of the ChaLearn AutoDL challenge 2019
Code submissions were executed on hidden tasks, with limited time and computational resources, pushing solutions that get results quickly.
What Hinders Perceptual Quality of PSNR-oriented Methods?
E. g, in EDSR, our proposed method achieves 3. 60$\times$ faster learning speed compared to a GAN-based method with a subtle degradation in visual quality.
Neural Architecture Search With Representation Mutual Information
Building upon RMI, we further propose a new search algorithm termed RMI-NAS, facilitating with a theorem to guarantee the global optimal of the searched architecture.
DIFNet: Boosting Visual Information Flow for Image Captioning
Current Image captioning (IC) methods predict textual words sequentially based on the input visual information from the visual feature extractor and the partially generated sentence information.
Dual Contrastive Learning for General Face Forgery Detection
With various facial manipulation techniques arising, face forgery detection has drawn growing attention due to security concerns.
Learning to Learn Transferable Attack
By treating the attack of both specific data and a modified model as a task, we expect the adversarial perturbations to adopt enough tasks for generalization.
IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization
In this paper, we observe an interesting phenomenon of intra-class heterogeneity in real data and show that existing methods fail to retain this property in their synthetic images, which causes a limited performance increase.
Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme
In this work, we revisit the role of discriminator in GAN compression and design a novel generator-discriminator cooperative compression scheme for GAN compression, termed GCC.
Towards Language-guided Visual Recognition via Dynamic Convolutions
Based on the LaConv module, we further build the first fully language-driven convolution network, termed as LaConvNet, which can unify the visual recognition and multi-modal reasoning in one forward structure.
Long-Range Feature Propagating for Natural Image Matting
Finally, we use the matting module which takes the image, trimap and context features to estimate the alpha matte.
Ranked #5 on
Image Matting
on Composition-1K
(using extra training data)
OMPQ: Orthogonal Mixed Precision Quantization
Instead of solving a problem of the original integer programming, we propose to optimize a proxy metric, the concept of network orthogonality, which is highly correlated with the loss of the integer programming but also easy to optimize with linear programming.
Prioritized Subnet Sampling for Resource-Adaptive Supernet Training
At the end of training, our PSS-Net retains the best subnet in each pool to entitle a fast switch of high-quality subnets for inference when the available resources vary.
Fine-grained Data Distribution Alignment for Post-Training Quantization
While post-training quantization receives popularity mostly due to its evasion in accessing the original complete training dataset, its poor performance also stems from scarce images.
Seminar Learning for Click-Level Weakly Supervised Semantic Segmentation
Annotation burden has become one of the biggest barriers to semantic segmentation.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
An Information Theory-inspired Strategy for Automatic Network Pruning
This practically limits the application of model compression when the model needs to be deployed on a wide range of devices.
Towards Robustness Against Natural Language Word Substitutions
Robustness against word substitutions has a well-defined and widely acceptable form, i. e., using semantically similar words as substitutions, and thus it is considered as a fundamental stepping-stone towards broader robustness in natural language processing.
Training Compact CNNs for Image Classification using Dynamic-coded Filter Fusion
Each filter in our DCFF is firstly given an inter-similarity distribution with a temperature parameter as a filter proxy, on top of which, a fresh Kullback-Leibler divergence based dynamic-coded criterion is proposed to evaluate the filter importance.
GuidedMix-Net: Learning to Improve Pseudo Masks Using Labeled Images as Reference
To take advantage of the labeled examples and guide unlabeled data learning, we further propose a mask generation module to generate high-quality pseudo masks for the unlabeled data.
Toward Joint Thing-and-Stuff Mining for Weakly Supervised Panoptic Segmentation
To date, learning weakly supervised panoptic segmentation (WSPS) with only image-level labels remains unexplored.
Discover Cross-Modality Nuances for Visible-Infrared Person Re-Identification
In this paper, we propose a joint Modality and Pattern Alignment Network (MPANet) to discover cross-modality nuances in different patterns for visible-infrared person Re-ID, which introduces a modality alleviation module and a pattern alignment module to jointly extract discriminative features.
RSTNet: Captioning With Adaptive Attention on Visual and Non-Visual Words
Then, we build a BERTbased language model to extract language context and propose Adaptive-Attention (AA) module on top of a transformer decoder to adaptively measure the contribution of visual and language cues before making decisions for word prediction.
HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping
In this work, we propose a high fidelity face swapping method, called HifiFace, which can well preserve the face shape of the source face and generate photo-realistic results.
Ranked #7 on
Face Swapping
on FaceForensics++
You Only Compress Once: Towards Effective and Elastic BERT Compression via Exploit-Explore Stochastic Nature Gradient
Motivated by the necessity of efficient inference across various constraints on BERT, we propose a novel approach, YOCO-BERT, to achieve compress once and deploy everywhere.
1xN Pattern for Pruning Convolutional Neural Networks
We also provide a workflow of filter rearrangement that first rearranges the weight matrix in the output channel dimension to derive more influential blocks for accuracy improvements and then applies similar rearrangement to the next-layer weights in the input channel dimension to ensure correct convolutional operations.
Towards Compact CNNs via Collaborative Compression
Channel pruning and tensor decomposition have received extensive attention in convolutional neural network compression.
Auxiliary learning induced graph convolutional networks
In this article, we propose a novel auxiliary learning induced graph convolutional network in a multi-task fashion.
Local Relation Learning for Face Forgery Detection
Specifically, we propose a Multi-scale Patch Similarity Module (MPSM), which measures the similarity between features of local regions and forms a robust and generalized similarity pattern.
ISTR: End-to-End Instance Segmentation with Transformers
However, such an upgrade is not applicable to instance segmentation, due to its significantly higher output dimensions compared to object detection.
Ranked #19 on
Instance Segmentation
on COCO test-dev
Black-Box Dissector: Towards Erasing-based Hard-Label Model Stealing Attack
We argue this is due to the lack of rich information in the probability prediction and the overfitting caused by hard labels.
Carrying out CNN Channel Pruning in a White Box
Specifically, to model the contribution of each channel to differentiating categories, we develop a class-wise mask for each channel, implemented in a dynamic training manner w. r. t.
Lottery Jackpots Exist in Pre-trained Models
Existing studies achieve the sparsity of neural networks via time-consuming weight training or complex searching on networks with expanded width, which greatly limits the applications of network pruning.
Learnable Expansion-and-Compression Network for Few-shot Class-Incremental Learning
By tentatively expanding network nodes, LEC-Net enlarges the representation capacity of features, alleviating feature drift of old network from the perspective of model regularization.
Distilling a Powerful Student Model via Online Knowledge Distillation
Besides, a self-distillation module is adopted to convert the feature map of deeper layers into a shallower one.
On Evolving Attention Towards Domain Adaptation
However, considering that the configuration of attention, i. e., the type and the position of attention module, affects the performance significantly, it is more generalized to optimize the attention configuration automatically to be specialized for arbitrary UDA scenario.
Ranked #1 on
Unsupervised Domain Adaptation
on Duke to Market
ReCU: Reviving the Dead Weights in Binary Neural Networks
We prove that reviving the "dead weights" by ReCU can result in a smaller quantization error.
Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detection
Few-shot object detection has made substantial progressby representing novel class objects using the feature representation learned upon a set of base class objects.
Ranked #14 on
Few-Shot Object Detection
on MS-COCO (10-shot)
Image-to-image Translation via Hierarchical Style Disentanglement
Recently, image-to-image translation has made significant progress in achieving both multi-label (\ie, translation conditioned on different labels) and multi-style (\ie, generation with diverse styles) tasks.
Disentanglement
Multimodal Unsupervised Image-To-Image Translation
+1
DeeperForensics Challenge 2020 on Real-World Face Forgery Detection: Methods and Results
This paper reports methods and results in the DeeperForensics Challenge 2020 on real-world face forgery detection.
SiMaN: Sign-to-Magnitude Network Binarization
In this paper, we show that our weight binarization provides an analytical solution by encoding high-magnitude weights into +1s, and 0s otherwise.
Aurora Guard: Reliable Face Anti-Spoofing via Mobile Lighting System
Face authentication on mobile end has been widely applied in various scenarios.
Network Pruning using Adaptive Exemplar Filters
Inspired by the face recognition community, we use a message passing algorithm Affinity Propagation on the weight matrices to obtain an adaptive number of exemplars, which then act as the preserved filters.
Dual-Level Collaborative Transformer for Image Captioning
Descriptive region features extracted by object detection networks have played an important role in the recent advancements of image captioning.
Aha! Adaptive History-Driven Attack for Decision-Based Black-Box Models
A common practice is to start from a large perturbation and then iteratively reduce it with a deterministic direction and a random one while keeping it adversarial.
Parallel Detection-and-Segmentation Learning for Weakly Supervised Instance Segmentation
Weakly supervised instance segmentation (WSIS) with only image-level labels has recently drawn much attention.
TRAR: Routing the Attention Spans in Transformer for Visual Question Answering
Due to the superior ability of global dependency modeling, Transformer and its variants have become the primary choice of many vision-and-language tasks.
Occlude Them All: Occlusion-Aware Attention Network for Occluded Person Re-ID
To avoid such problematic models in occluded person ReID, we propose the Occlusion-Aware Mask Network (OAMN).
EC-DARTS: Inducing Equalized and Consistent Optimization Into DARTS
EC-DARTS decouples different operations based on their categories to optimize the operation weights so that the operation gap between them is shrinked.
Improving Image Captioning by Leveraging Intra- and Inter-layer Global Representation in Transformer Network
The latter contains a Global Adaptive Controller that can adaptively fuse the global information into the decoder to guide the caption generation.
UWSOD: Toward Fully-Supervised-Level Capacity Weakly Supervised Object Detection
In this paper, we propose a unified WSOD framework, termed UWSOD, to develop a high-capacity general detection model with only image-level labels, which is self-contained and does not require external modules or additional supervision.
Fast Class-wise Updating for Online Hashing
To achieve fast online adaptivity, a class-wise updating method is developed to decompose the binary code learning and alternatively renew the hash functions in a class-wise fashion, which well addresses the burden on large amounts of training batches.
Learning Efficient GANs for Image Translation via Differentiable Masks and co-Attention Distillation
The latter simultaneously distills informative attention maps from both the generator and discriminator of a pre-trained model to the searched generator, effectively stabilizing the adversarial training of our light-weight model.
PAMS: Quantized Super-Resolution via Parameterized Max Scale
Specifically, most state-of-the-art SR models without batch normalization have a large dynamic quantization range, which also serves as another cause of performance drop.
Rotated Binary Neural Network
In this paper, for the first time, we explore the influence of angular bias on the quantization error and then introduce a Rotated Binary Neural Network (RBNN), which considers the angle alignment between the full-precision weight vector and its binarized version.
Removing the Background by Adding the Background: Towards Background Robust Self-supervised Video Representation Learning
Then we force the model to pull the feature of the distracting video and the feature of the original video closer, so that the model is explicitly restricted to resist the background influence, focusing more on the motion changes.
Enhancing Unsupervised Video Representation Learning by Decoupling the Scene and the Motion
Specifically, we construct a positive clip and a negative clip for each video.
Binarized Neural Architecture Search for Efficient Object Recognition
In this paper, binarized neural architecture search (BNAS), with a search space of binarized convolutions, is introduced to produce extremely compressed models to reduce huge computational cost on embedded devices for edge computing.
Dual Channel Hypergraph Collaborative Filtering
Second, the hypergraph structure is employed for modeling users and items with explicit hybrid high-order correlations.
Anti-Bandit Neural Architecture Search for Model Defense
Deep convolutional neural networks (DCNNs) have dominated as the best performers in machine learning, but can be challenged by adversarial attacks.
Learning Task-oriented Disentangled Representations for Unsupervised Domain Adaptation
This drawback limits the flexibility of UDA in complicated open-set tasks where no labels are shared between domains.
Dual Distribution Alignment Network for Generalizable Person Re-Identification
Domain generalization (DG) serves as a promising solution to handle person Re-Identification (Re-ID), which trains the model using labels from the source domain alone, and then directly adopts the trained model to the target domain without model updating.
Domain Generalization
Generalizable Person Re-identification
Multiple Expert Brainstorming for Domain Adaptive Person Re-identification
Often the best performing deep neural models are ensembles of multiple base-level networks, nevertheless, ensemble learning with respect to domain adaptive person re-ID remains unexplored.
Domain Adaptive Person Re-Identification
Ensemble Learning
+1
Cogradient Descent for Bilinear Optimization
Conventional learning methods simplify the bilinear model by regarding two intrinsically coupled factors independently, which degrades the optimization procedure.
Rethinking Performance Estimation in Neural Architecture Search
In this paper, we provide a novel yet systematic rethinking of PE in a resource constrained regime, termed budgeted PE (BPE), which precisely and effectively estimates the performance of an architecture sampled from an architecture space.
Projection & Probability-Driven Black-Box Attack
For reducing the solution space, we first model the adversarial perturbation optimization problem as a process of recovering frequency-sparse perturbations with compressed sensing, under the setting that random noise in the low-frequency space is more likely to be adversarial.
Filter Grafting for Deep Neural Networks: Reason, Method, and Cultivation
To gain a universal improvement on both valid and invalid filters, we compensate grafting with distillation (\textbf{Cultivation}) to overcome the drawback of grafting .
AD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-identification
Domain adaptive person re-identification (re-ID) is a challenging task, especially when person identities in target domains are unknown.
Ranked #7 on
Unsupervised Domain Adaptation
on Duke to Market
