论文检索

Wei Fang, Yuxing Tang, Heng Guo, Mingze Yuan, Tony C. W. Mok, Ke Yan, Jiawen Yao, Xin Chen, Zaiyi Liu, Le Lu 等

In the realm of medical 3D data such as CT and MRI images prevalent anisotropic resolution is characterized by high intra-slice but diminished inter-slice resolution. The lowered resolution between adjacent slices poses challenges hindering optimal viewing experiences and impeding the development of robust downstream analysis algorithms. Various volumetric super-resolution algorithms aim to surmount these challenges enhancing inter-slice resolution and overall 3D medical imaging quality. However existing approaches confront inherent challenges: 1) often tailored to specific upsampling factors lacking flexibility for diverse clinical scenarios; 2) newly generated slices frequently suffer from over-smoothing degrading fine details and leading to inter-slice inconsistency. In response this study presents CycleINR a novel enhanced Implicit Neural Representation model for 3D medical data volumetric super-resolution. Leveraging the continuity of the learned implicit function the CycleINR model can achieve results with arbitrary up-sampling rates eliminating the need for separate training. Additionally we enhance the grid sampling in CycleINR with a local attention mechanism and mitigate over-smoothing by integrating cycle-consistent loss. We introduce a new metric Slice-wise Noise Level Inconsistency (SNLI) to quantitatively assess inter-slice noise level inconsistency. The effectiveness of our approach is demonstrated through image quality evaluations on an in-house dataset and a downstream task analysis on the Medical Segmentation Decathlon liver tumor dataset.

Xu Zheng, Lin Wang

In this paper we make the first attempt at achieving the cross-modal (i.e. image-to-events) adaptation for event-based object recognition without accessing any labeled source image data owning to privacy and commercial issues. Tackling this novel problem is non-trivial due to the novelty of event cameras and the distinct modality gap between images and events. In particular as only the source model is available a hurdle is how to extract the knowledge from the source model by only using the unlabeled target event data while achieving knowledge transfer. To this end we propose a novel framework dubbed EventDance for this unsupervised source-free cross-modal adaptation problem. Importantly inspired by event-to-video reconstruction methods we propose a reconstruction-based modality bridging (RMB) module which reconstructs intensity frames from events in a self-supervised manner. This makes it possible to build up the surrogate images to extract the knowledge (i.e. labels) from the source model. We then propose a multi-representation knowledge adaptation (MKA) module that transfers the knowledge to target models learning events with multiple representation types for fully exploring the spatiotemporal information of events. The two modules connecting the source and target models are mutually updated so as to achieve the best performance. Experiments on three benchmark datasets with two adaption settings show that EventDance is on par with prior methods utilizing the source data.

Qiyuan Dai, Sibei Yang

Referring image segmentation (RIS) aims to precisely segment referents in images through corresponding natural language expressions yet relying on cost-intensive mask annotations. Weakly supervised RIS thus learns from image-text pairs to pixel-level semantics which is challenging for segmenting fine-grained masks. A natural approach to enhancing segmentation precision is to empower weakly supervised RIS with the image segmentation foundation model SAM. Nevertheless we observe that simply integrating SAM yields limited benefits and can even lead to performance regression due to the inevitable noise issues and challenges in excessive focus on object parts. In this paper we present an innovative framework Point PrompTing (PPT) incorporated with the proposed multi-source curriculum learning strategy to address these challenges. Specifically the core of PPT is a point generator that not only harnesses CLIP's text-image alignment capability and SAM's powerful mask generation ability but also generates negative point prompts to address the noisy and excessive focus issues inherently and effectively. In addition we introduce a curriculum learning strategy with object-centric images to help PPT gradually learn from simpler yet precise semantic alignment to more complex RIS. Experiments demonstrate that our PPT significantly and consistently outperforms prior weakly supervised techniques on mIoU by 11.34% 14.14% and 6.97% across RefCOCO RefCOCO+ and G-Ref respectively.

Yiwei Bao, Feng Lu

Deep-learning-based gaze estimation approaches often suffer from notable performance degradation in unseen target domains. One of the primary reasons is that the Fully Connected layer is highly prone to overfitting when mapping the high-dimensional image feature to 3D gaze. In this paper we propose Analytical Gaze Generalization framework (AGG) to improve the generalization ability of gaze estimation models without touching target domain data. The AGG consists of two modules the Geodesic Projection Module (GPM) and the Sphere-Oriented Training (SOT). GPM is a generalizable replacement of FC layer which projects high-dimensional image features to 3D space analytically to extract the principle components of gaze. Then we propose Sphere-Oriented Training (SOT) to incorporate the GPM into the training process and further improve cross-domain performances. Experimental results demonstrate that the AGG effectively alleviate the overfitting problem and consistently improves the cross-domain gaze estimation accuracy in 12 cross-domain settings without requiring any target domain data. The insight from the Analytical Gaze Generalization framework has the potential to benefit other regression tasks with physical meanings.

Hao Ai, Lin Wang

360 depth estimation has recently received great attention for 3D reconstruction owing to its omnidirectional field of view (FoV). Recent approaches are predominantly focused on cross-projection fusion with geometry-based re-projection: they fuse 360 images with equirectangular projection (ERP) and another projection type e.g. cubemap projection to estimate depth with the ERP format. However these methods suffer from 1) limited local receptive fields making it hardly possible to capture large FoV scenes and 2) prohibitive computational cost caused by the complex cross-projection fusion module design. In this paper we propose Elite360D a novel framework that inputs the ERP image and icosahedron projection (ICOSAP) point set which is undistorted and spatially continuous. Elite360D is superior in its capacity in learning a representation from a local-with-global perspective. With a flexible ERP image encoder it includes an ICOSAP point encoder and a Bi-projection Bi-attention Fusion (B2F) module (totally 1M parameters). Specifically the ERP image encoder can take various perspective image-trained backbones (e.g. ResNet Transformer) to extract local features. The point encoder extracts the global features from the ICOSAP. Then the B2F module captures the semantic- and distance-aware dependencies between each pixel of the ERP feature and the entire ICOSAP feature set. Without specific backbone design and obvious computational cost increase Elite360D outperforms the prior arts on several benchmark datasets.

Yingyan Xu, Prashanth Chandran, Sebastian Weiss, Markus Gross, Gaspard Zoss, Derek Bradley

An increasingly common approach for creating photo-realistic digital avatars is through the use of volumetric neural fields. The original neural radiance field (NeRF) allowed for impressive novel view synthesis of static heads when trained on a set of multi-view images and follow up methods showed that these neural representations can be extended to dynamic avatars. Recently new variants also surpassed the usual drawback of baked-in illumination in neural representations showing that static neural avatars can be relit in any environment. In this work we simultaneously tackle both the motion and illumination problem proposing a new method for relightable and animatable neural heads. Our method builds on a proven dynamic avatar approach based on a mixture of volumetric primitives combined with a recently-proposed lightweight hardware setup for relightable neural fields and includes a novel architecture that allows relighting dynamic neural avatars performing unseen expressions in any environment even with nearfield illumination and viewpoints.

Zequn Zeng, Yan Xie, Hao Zhang, Chiyu Chen, Bo Chen, Zhengjue Wang

Zero-shot image captioning (IC) without well-paired image-text data can be categorized into two main types: training-free and text-only-training methods. While both types integrate pre-trained vision-language models such as CLIP for image-text similarity evaluation and a pre-trained language model (LM) for caption generation their distinction lies in the utilization of textual corpus for LM training. Despite achieving promising performance on certain metrics existing methods commonly suffer from drawbacks. Training-free methods often generate hallucinations whereas text-only-training methods may lack generalization capability. To address these challenges we propose a novel Memory-Augmented zero-shot image Captioning framework (MeaCap). This framework equipped with a textual memory incorporates a retrieve-then-filter module to extract key concepts highly relevant to the image. By leveraging our proposed memory-augmented visual-related fusion score within a keywords-to-sentence LM MeaCap generates concept-centered captions that exhibit high consistency with the image with reduced hallucinations and enriched world knowledge. MeaCap achieves state-of-the-art performance across various zero-shot IC settings. Our code is publicly available at https://github.com/joeyz0z/MeaCap.

Xin Kong, Shikun Liu, Xiaoyang Lyu, Marwan Taher, Xiaojuan Qi, Andrew J. Davison

We introduce EscherNet a multi-view conditioned diffusion model for view synthesis. EscherNet learns implicit and generative 3D representations coupled with a specialised camera positional encoding allowing precise and continuous relative control of the camera transformation between an arbitrary number of reference and target views. EscherNet offers exceptional generality flexibility and scalability in view synthesis --- it can generate more than 100 consistent target views simultaneously on a single consumer-grade GPU despite being trained with a fixed number of 3 reference views to 3 target views. As a result EscherNet not only addresses zero-shot novel view synthesis but also naturally unifies single- and multi-image 3D reconstruction combining these diverse tasks into a single cohesive framework. Our extensive experiments demonstrate that EscherNet achieves state-of-the-art performance in multiple benchmarks even when compared to methods specifically tailored for each individual problem. This remarkable versatility opens up new directions for designing scalable neural architectures for 3D vision. Project page: https://kxhit.github.io/EscherNet.

Yuhang Zhou, Zhongyun Hua

Deep neural networks have demonstrated susceptibility to adversarial attacks. Adversarial defense techniques often focus on one-shot setting to maintain robustness against attack. However new attacks can emerge in sequences in real-world deployment scenarios. As a result it is crucial for a defense model to constantly adapt to new attacks but the adaptation process can lead to catastrophic forgetting of previously defended against attacks. In this paper we discuss for the first time the concept of continual adversarial defense under a sequence of attacks and propose a lifelong defense baseline called Anisotropic & Isotropic Replay (AIR) which offers three advantages: (1) Isotropic replay ensures model consistency in the neighborhood distribution of new data indirectly aligning the output preference between old and new tasks. (2) Anisotropic replay enables the model to learn a compromise data manifold with fresh mixed semantics for further replay constraints and potential future attacks. (3) A straightforward regularizer mitigates the 'plasticity-stability' trade-off by aligning model output between new and old tasks. Experiment results demonstrate that AIR can approximate or even exceed the empirical performance upper bounds achieved by Joint Training.

Linus Scheibenreif, Michael Mommert, Damian Borth

As large-scale foundation models become publicly available for different domains efficiently adapting them to individual downstream applications and additional data modalities has turned into a central challenge. For example foundation models for geospatial and satellite remote sensing applications are commonly trained on large optical RGB or multi-spectral datasets although data from a wide variety of heterogeneous sensors are available in the remote sensing domain. This leads to significant discrepancies between pre-training and downstream target data distributions for many important applications. Fine-tuning large foundation models to bridge that gap incurs high computational cost and can be infeasible when target datasets are small. In this paper we address the question of how large pre-trained foundational transformer models can be efficiently adapted to downstream remote sensing tasks involving different data modalities or limited dataset size. We present a self-supervised adaptation method that boosts downstream linear evaluation accuracy of different foundation models by 4-6% (absolute) across 8 remote sensing datasets while outperforming full fine-tuning when training only 1-2% of the model parameters. Our method significantly improves label efficiency and increases few-shot accuracy by 6-10% on different datasets.

Xin Fan, Xiaolin Wang, Jiaxin Gao, Jia Wang, Zhongxuan Luo, Risheng Liu

One-shot medical image segmentation (MIS) aims to cope with the expensive time-consuming and inherent human bias annotations. One prevalent method to address one-shot MIS is joint registration and segmentation (JRS) with a shared encoder which mainly explores the voxel-wise correspondence between the labeled data and unlabeled data for better segmentation. However this method omits underlying connections between task-specific decoders for segmentation and registration leading to unstable training. In this paper we propose a novel Bi-level Learning of Task-Specific Decoders for one-shot MIS employing a pretrained fixed shared encoder that is proved to be more quickly adapted to brand-new datasets than existing JRS without fixed shared encoder paradigm. To be more specific we introduce a bi-level optimization training strategy considering registration as a major objective and segmentation as a learnable constraint by leveraging inter-task coupling dependencies. Furthermore we design an appearance conformity constraint strategy that learns the backward transformations generating the fake labeled data used to perform data augmentation instead of the labeled image to avoid performance degradation caused by inconsistent styles between unlabeled data and labeled data in previous methods. Extensive experiments on the brain MRI task across ABIDE ADNI and PPMI datasets demonstrate that the proposed Bi-JROS outperforms state-of-the-art one-shot MIS methods for both segmentation and registration tasks. The code will be available at https://github.com/Coradlut/Bi-JROS.

Jiabao Wang, Yuming Chen, Zhaohui Zheng, Xiang Li, Ming-Ming Cheng, Qibin Hou

Knowledge Distillation (KD) has been validated as an effective model compression technique for learning compact object detectors. Existing state-of-the-art KD methods for object detection are mostly based on feature imitation. In this paper we present a general and effective prediction mimicking distillation scheme called CrossKD which delivers the intermediate features of the student's detection head to the teacher's detection head. The resulting cross-head predictions are then forced to mimic the teacher's predictions. This manner relieves the student's head from receiving contradictory supervision signals from the annotations and the teacher's predictions greatly improving the student's detection performance. Moreover as mimicking the teacher's predictions is the target of KD CrossKD offers more task-oriented information in contrast with feature imitation. On MS COCO with only prediction mimicking losses applied our CrossKD boosts the average precision of GFL ResNet-50 with 1x training schedule from 40.2 to 43.7 outperforming all existing KD methods. In addition our method also works well when distilling detectors with heterogeneous backbones.

Yujie Xue, Ruihui Li, Fan Wu, Zhuo Tang, Kenli Li, Mingxing Duan

Camera-based Semantic Scene Completion (SSC) is to infer the full geometry of objects and scenes from only 2D images. The task is particularly challenging for those invisible areas due to the inherent occlusions and lighting ambiguity. Existing works ignore the information missing or ambiguous in those shaded and occluded areas resulting in distorted geometric prediction. To address this issue we propose a novel method Bi-SSC bidirectional geometric semantic fusion for camera-based 3D semantic scene completion. The key insight is to use the neighboring structure of objects in the image and the spatial differences from different perspectives to compensate for the lack of information in occluded areas. Specifically we introduce a spatial sensory fusion module with multiple association attention to improve semantic correlation in geometric distributions. This module works within single view and across stereo views to achieve global spatial consistency. Experimental results demonstrate that Bi-SSC outperforms state-of-the-art camera-based methods on SemanticKITTI particularly excelling in those invisible and shaded areas.

Pengfei Zhu, Yang Sun, Bing Cao, Qinghua Hu

General image fusion aims at integrating important information from multi-source images. However due to the significant cross-task gap the respective fusion mechanism varies considerably in practice resulting in limited performance across subtasks. To handle this problem we propose a novel task-customized mixture of adapters (TC-MoA) for general image fusion adaptively prompting various fusion tasks in a unified model. We borrow the insight from the mixture of experts (MoE) taking the experts as efficient tuning adapters to prompt a pre-trained foundation model. These adapters are shared across different tasks and constrained by mutual information regularization ensuring compatibility with different tasks while complementarity for multi-source images. The task-specific routing networks customize these adapters to extract task-specific information from different sources with dynamic dominant intensity performing adaptive visual feature prompt fusion. Notably our TC-MoA controls the dominant intensity bias for different fusion tasks successfully unifying multiple fusion tasks in a single model. Extensive experiments show that TC-MoA outperforms the competing approaches in learning commonalities while retaining compatibility for general image fusion (multi-modal multi-exposure and multi-focus) and also demonstrating striking controllability on more generalization experiments. The code is available at https://github.com/YangSun22/TC-MoA.

Haiyang Xu, Yu Lei, Zeyuan Chen, Xiang Zhang, Yue Zhao, Yilin Wang, Zhuowen Tu

We present Bayesian Diffusion Models (BDM) a prediction algorithm that performs effective Bayesian inference by tightly coupling the top-down (prior) information with the bottom-up (data-driven) procedure via joint diffusion processes. We demonstrate the application of BDM on the 3D shape reconstruction task. Compared to standard deep learning data-driven approaches relying on supervised data our BDM can bring in rich prior information trained in an unsupervised manner to improve the bottom-up 3D reconstruction. As opposed to the traditional Bayesian frameworks where explicitly learned prior and data-driven distributions are required for gradient computation and combination BDM performs a seamless fusion of the two via coupled diffusion processes with learned gradient computation networks. The specialty of our Bayesian Diffusion Models (BDM) lies in its capability to engage the active and effective information exchange and fusion of the top-down and bottom-up processes where each itself is a diffusion process. We demonstrate state-of-the-art results on both synthetic and real-world benchmarks for 3D shape reconstruction. Project link: https://mlpc-ucsd.github.io/BDM

Yongxian Wei, Zixuan Hu, Zhenyi Wang, Li Shen, Chun Yuan, Dacheng Tao

Data-Free Meta-Learning (DFML) aims to extract knowledge from a collection of pre-trained models without requiring the original data presenting practical benefits in contexts constrained by data privacy concerns. Current DFML methods primarily focus on the data recovery from these pre-trained models. However they suffer from slow recovery speed and overlook gaps inherent in heterogeneous pre-trained models. In response to these challenges we introduce the Faster and Better Data-Free Meta-Learning (FREE) framework which contains: (i) a meta-generator for rapidly recovering training tasks from pre-trained models; and (ii) a meta-learner for generalizing to new unseen tasks. Specifically within the module Faster Inversion via Meta-Generator each pre-trained model is perceived as a distinct task. The meta-generator can rapidly adapt to a specific task in just five steps significantly accelerating the data recovery. Furthermore we propose Better Generalization via Meta-Learner and introduce an implicit gradient alignment algorithm to optimize the meta-learner. This is achieved as aligned gradient directions alleviate potential conflicts among tasks from heterogeneous pre-trained models. Empirical experiments on multiple benchmarks affirm the superiority of our approach marking a notable speed-up (20x) and performance enhancement (1.42% 4.78%) in comparison to the state-of-the-art.

Fei Deng, Qifei Wang, Wei Wei, Tingbo Hou, Matthias Grundmann

Reward finetuning has emerged as a promising approach to aligning foundation models with downstream objectives. Remarkable success has been achieved in the language domain by using reinforcement learning (RL) to maximize rewards that reflect human preference. However in the vision domain existing RL-based reward finetuning methods are limited by their instability in large-scale training rendering them incapable of generalizing to complex unseen prompts. In this paper we propose Proximal Reward Difference Prediction (PRDP) enabling stable black-box reward finetuning for diffusion models for the first time on large-scale prompt datasets with over 100K prompts. Our key innovation is the Reward Difference Prediction (RDP) objective that has the same optimal solution as the RL objective while enjoying better training stability. Specifically the RDP objective is a supervised regression objective that tasks the diffusion model with predicting the reward difference of generated image pairs from their denoising trajectories. We theoretically prove that the diffusion model that obtains perfect reward difference prediction is exactly the maximizer of the RL objective. We further develop an online algorithm with proximal updates to stably optimize the RDP objective. In experiments we demonstrate that PRDP can match the reward maximization ability of well-established RL-based methods in small-scale training. Furthermore through large-scale training on text prompts from the Human Preference Dataset v2 and the Pick-a-Pic v1 dataset PRDP achieves superior generation quality on a diverse set of complex unseen prompts whereas RL-based methods completely fail.

Khawar Islam, Muhammad Zaigham Zaheer, Arif Mahmood, Karthik Nandakumar

Recently a number of image-mixing-based augmentation techniques have been introduced to improve the generalization of deep neural networks. In these techniques two or more randomly selected natural images are mixed together to generate an augmented image. Such methods may not only omit important portions of the input images but also introduce label ambiguities by mixing images across labels resulting in misleading supervisory signals. To address these limitations we propose DIFFUSEMIX a novel data augmentation technique that leverages a diffusion model to reshape training images supervised by our bespoke conditional prompts. First concatenation of a partial natural image and its generated counterpart is obtained which helps in avoiding the generation of unrealistic images or label ambiguities. Then to enhance resilience against adversarial attacks and improves safety measures a randomly selected structural pattern from a set of fractal images is blended into the concatenated image to form the final augmented image for training. Our empirical results on seven different datasets reveal that DIFFUSEMIX achieves superior performance compared to existing state- of-the-art methods on tasks including general classification fine-grained classification fine-tuning data scarcity and adversarial robustness.

Haoran Xu, Peixi Peng, Guang Tan, Yuan Li, Xinhai Xu, Yonghong Tian

We explore visual reinforcement learning (RL) using two complementary visual modalities: frame-based RGB camera and event-based Dynamic Vision Sensor (DVS). Existing multi-modality visual RL methods often encounter challenges in effectively extracting task-relevant information from multiple modalities while suppressing the increased noise only using indirect reward signals instead of pixel-level supervision. To tackle this we propose a Decomposed Multi-Modality Representation (DMR) framework for visual RL. It explicitly decomposes the inputs into three distinct components: combined task-relevant features (co-features) RGB-specific noise and DVS-specific noise. The co-features represent the full information from both modalities that is relevant to the RL task; the two noise components each constrained by a data reconstruction loss to avoid information leak are contrasted with the co-features to maximize their difference. Extensive experiments demonstrate that by explicitly separating the different types of information our approach achieves substantially improved policy performance compared to state-of-the-art approaches.

You Huang, Zongyu Lan, Liujuan Cao, Xianming Lin, Shengchuan Zhang, Guannan Jiang, Rongrong Ji

The Segment Anything Model (SAM) marks a notable milestone in segmentation models highlighted by its robust zero-shot capabilities and ability to handle diverse prompts. SAM follows a pipeline that separates interactive segmentation into image preprocessing through a large encoder and interactive inference via a lightweight decoder ensuring efficient real-time performance. However SAM faces stability issues in challenging samples upon this pipeline. These issues arise from two main factors. Firstly the image preprocessing disables SAM to dynamically use image-level zoom-in strategies to refocus on the target object during interaction. Secondly the lightweight decoder struggles to sufficiently integrate interactive information with image embeddings. To address these two limitations we propose FocSAM with a pipeline redesigned on two pivotal aspects. First we propose Dynamic Window Multi-head Self-Attention (Dwin-MSA) to dynamically refocus SAM's image embeddings on the target object. Dwin-MSA localizes attention computations around the target object enhancing object-related embeddings with minimal computational overhead. Second we propose Pixel-wise Dynamic ReLU (P-DyReLU) to enable sufficient integration of interactive information from a few initial clicks that have significant impacts on the overall segmentation results. Experimentally FocSAM augments SAM's interactive segmentation performance to match the existing state-of-the-art method in segmentation quality requiring only about 5.6% of this method's inference time on CPUs. Code is available at https://github.com/YouHuang67/focsam.