论文检索

Applications

Che Liu, Cheng Ouyang, Sibo Cheng, Anand Shah, Wenjia Bai, Rossella Arcucci

Medical imaging tasks require an understanding of subtle and localized visual features due to the inherently detailed and area-specific nature of pathological patterns, which are crucial for clinical diagnosis. Although recent advances in medical vision-language pre-training (VLP) enable models to learn clinically relevant visual features by leveraging both medical images and their associated radiology reports, current medical VLP methods primarily focus on aligning images with entire reports. This focus hinders the learning of dense (pixel-level) visual features and is suboptimal for dense prediction tasks (e.g., medical image segmentation).To address this challenge, we propose a novel medical VLP framework, named **Global to Dense level representation learning (G2D)**, which aims to learn global and dense visual features simultaneously using only image-text pairs without extra annotations. In particular, G2D designs a **Pseudo Segmentation (PS)** task, which enables the model to learn dense visual features during VLP. Notably, generating PS masks can be performed on the fly during VLP, which does not incur extra trainable parameters. With this simple yet effective idea, G2D achieves superior performance across 5 medical imaging tasks and 25 diseases. Particularly, in the segmentation task which requires dense visual features, **G2D surpasses existing models even with just 1% of the training data for finetuning, compared to 100% used by other models**. The code can be found in https://github.com/cheliu-computation/G2D-NeurIPS24/tree/main.

zhengrui Xu, Guan'an Wang, Xiaowen Huang, Jitao Sang

The denoising model has been proven a powerful generative model but has little exploration of discriminative tasks. Representation learning is important in discriminative tasks, which is defined as *"learning representations (or features) of the data that make it easier to extract useful information when building classifiers or other predictors"*. In this paper, we propose a novel Denoising Model for Representation Learning (*DenoiseRep*) to improve feature discrimination with joint feature extraction and denoising. *DenoiseRep* views each embedding layer in a backbone as a denoising layer, processing the cascaded embedding layers as if we are recursively denoise features step-by-step. This unifies the frameworks of feature extraction and denoising, where the former progressively embeds features from low-level to high-level, and the latter recursively denoises features step-by-step. After that, *DenoiseRep* fuses the parameters of feature extraction and denoising layers, and *theoretically demonstrates* its equivalence before and after the fusion, thus making feature denoising computation-free. *DenoiseRep* is a label-free algorithm that incrementally improves features but also complementary to the label if available. Experimental results on various discriminative vision tasks, including re-identification (Market-1501, DukeMTMC-reID, MSMT17, CUHK-03, vehicleID), image classification (ImageNet, UB200, Oxford-Pet, Flowers), object detection (COCO), image segmentation (ADE20K) show stability and impressive improvements. We also validate its effectiveness on the CNN (ResNet) and Transformer (ViT, Swin, Vmamda) architectures.

Computer Vision · Segmentation

Qianxiong Xu, Xuanyi Liu, Lanyun Zhu, Guosheng Lin, Cheng Long, Ziyue Li, Rui Zhao

Many few-shot segmentation (FSS) methods use cross attention to fuse support foreground (FG) into query features, regardless of the quadratic complexity. A recent advance Mamba can also well capture intra-sequence dependencies, yet the complexity is only linear. Hence, we aim to devise a cross (attention-like) Mamba to capture inter-sequence dependencies for FSS. A simple idea is to scan on support features to selectively compress them into the hidden state, which is then used as the initial hidden state to sequentially scan query features. Nevertheless, it suffers from (1) support forgetting issue: query features will also gradually be compressed when scanning on them, so the support features in hidden state keep reducing, and many query pixels cannot fuse sufficient support features; (2) intra-class gap issue: query FG is essentially more similar to itself rather than to support FG, i.e., query may prefer not to fuse support features but their own ones from the hidden state, yet the success of FSS relies on the effective use of support information. To tackle them, we design a hybrid Mamba network (HMNet), including (1) a support recapped Mamba to periodically recap the support features when scanning query, so the hidden state can always contain rich support information; (2) a query intercepted Mamba to forbid the mutual interactions among query pixels, and encourage them to fuse more support features from the hidden state. Consequently, the support information is better utilized, leading to better performance. Extensive experiments have been conducted on two public benchmarks, showing the superiority of HMNet. The code is available at https://github.com/Sam1224/HMNet.

Time Series

Junru Chen, Tianyu Cao, Jing Xu, Jiahe Li, Zhilong Chen, Tao Xiao, YANG YANG

Time Series Classification (TSC) encompasses two settings: classifying entire sequences or classifying segmented subsequences. The raw time series for segmented TSC usually contain Multiple classes with Varying Duration of each class (MVD). Therefore, the characteristics of MVD pose unique challenges for segmented TSC, yet have been largely overlooked by existing works. Specifically, there exists a natural temporal dependency between consecutive instances (segments) to be classified within MVD. However, mainstream TSC models rely on the assumption of independent and identically distributed (i.i.d.), focusing on independently modeling each segment. Additionally, annotators with varying expertise may provide inconsistent boundary labels, leading to unstable performance of noise-free TSC models. To address these challenges, we first formally demonstrate that valuable contextual information enhances the discriminative power of classification instances. Leveraging the contextual priors of MVD at both the data and label levels, we propose a novel consistency learning framework Con4m, which effectively utilizes contextual information more conducive to discriminating consecutive segments in segmented TSC tasks, while harmonizing inconsistent boundary labels for training. Extensive experiments across multiple datasets validate the effectiveness of Con4m in handling segmented TSC tasks on MVD. The source code is available at https://github.com/MrNobodyCali/Con4m.

Computer Vision · Video Generation

Boxiao Pan, Zhan Xu, Chun-Hao Huang, Krishna Kumar Singh, Yang Zhou, Leonidas Guibas, Jimei Yang

We study a novel problem to automatically generate video background that tailors to foreground subject motion. It is an important problem for the movie industry and visual effects community, which traditionally requires tedious manual efforts to solve. To this end, we propose ActAnywhere, a video diffusion model that takes as input a sequence of foreground subject segmentation and an image of a novel background and generates a video of the subject interacting in this background. We train our model on a large-scale dataset of 2.4M videos of human-scene interactions. Through extensive evaluation, we show that our model produces videos with realistic foreground-background interaction while strictly following the guidance of the condition image. Our model generalizes to diverse scenarios including non-human subjects, gaming and animation clips, as well as videos with multiple moving subjects. Both quantitative and qualitative comparisons demonstrate that our model significantly outperforms existing methods, which fail to accomplish the studied task. Please visit our project webpage at https://actanywhere.github.io.

Xin Yang, YAN WENDING, Michael Bi Mi, Yuan Yuan, Robby Tan

Adverse weather conditions can significantly degrade the video frames, causing existing video semantic segmentation methods to produce erroneous predictions. In this work, we target adverse weather conditions and introduce an end-to-end domain adaptation strategy that leverages a fusion block, temporal-spatial teacher-student learning, and a temporal weather degradation augmentation approach. The fusion block integrates temporal information from adjacent frames at the feature level, trained end-to-end, eliminating the need for pretrained optical flow, distinguishing our method from existing approaches. Our teacher-student approach involves two teachers: one focuses on exploring temporal information from adjacent frames, and the other harnesses spatial information from the current frame. Finally, we apply temporal weather degradation augmentation to consecutive frames to more accurately represent adverse weather degradations. Our method achieves a performance of 25.4 and 33.0 mIoU on the adaptation from VIPER and Synthia to MVSS, respectively, representing an improvement of 4.3 and 5.8 mIoU over the existing state-of-the-art method.

Computer Vision

Zhixiong Nan, Li Xianghong, Tao Xiang, Jifeng Dai

This paper is motivated by an interesting phenomenon: the performance of object detection lags behind that of instance segmentation (i.e., performance imbalance) when investigating the intermediate results from the beginning transformer decoder layer of MaskDINO (i.e., the SOTA model for joint detection and segmentation). This phenomenon inspires us to think about a question: will the performance imbalance at the beginning layer of transformer decoder constrain the upper bound of the final performance? With this question in mind, we further conduct qualitative and quantitative pre-experiments, which validate the negative impact of detection-segmentation imbalance issue on the model performance. To address this issue, this paper proposes DI-MaskDINO model, the core idea of which is to improve the final performance by alleviating the detection-segmentation imbalance. DI-MaskDINO is implemented by configuring our proposed De-Imbalance (DI) module and Balance-Aware Tokens Optimization (BATO) module to MaskDINO. DI is responsible for generating balance-aware query, and BATO uses the balance-aware query to guide the optimization of the initial feature tokens. The balance-aware query and optimized feature tokens are respectively taken as the Query and Key&Value of transformer decoder to perform joint object detection and instance segmentation. DI-MaskDINO outperforms existing joint object detection and instance segmentation models on COCO and BDD100K benchmarks, achieving +1.2 $AP^{box}$ and +0.9 $AP^{mask}$ improvements compared to SOTA joint detection and segmentation model MaskDINO. In addition, DI-MaskDINO also obtains +1.0 $AP^{box}$ improvement compared to SOTA object detection model DINO and +3.0 $AP^{mask}$ improvement compared to SOTA segmentation model Mask2Former.

Computer Vision · Segmentation

Rongkun Zheng, Lu Qi, Xi Chen, Yi Wang, Kun Wang, Yu Qiao, Hengshuang Zhao

Recent DETR-based methods have advanced the development of Video Instance Segmentation (VIS) through transformers' efficiency and capability in modeling spatial and temporal information. Despite harvesting remarkable progress, existing works follow asynchronous designs, which model video sequences via either video-level queries only or adopting query-sensitive cascade structures, resulting in difficulties when handling complex and challenging video scenarios. In this work, we analyze the cause of this phenomenon and the limitations of the current solutions, and propose to conduct synchronized modeling via a new framework named SyncVIS. Specifically, SyncVIS explicitly introduces video-level query embeddings and designs two key modules to synchronize video-level query with frame-level query embeddings: a synchronized video-frame modeling paradigm and a synchronized embedding optimization strategy. The former attempts to promote the mutual learning of frame- and video-level embeddings with each other and the latter divides large video sequences into small clips for easier optimization. Extensive experimental evaluations are conducted on the challenging YouTube-VIS 2019 & 2021 & 2022, and OVIS benchmarks, and SyncVIS achieves state-of-the-art results, which demonstrates the effectiveness and generality of the proposed approach. The code is available at https://github.com/rkzheng99/SyncVIS.

Time Series

Shivam Grover, Amin Jalali, Ali Etemad

Existing approaches for learning representations of time-series keep the temporal arrangement of the time-steps intact with the presumption that the original order is the most optimal for learning. However, non-adjacent sections of real-world time-series may have strong dependencies. Accordingly, we raise the question: Is there an alternative arrangement for time-series which could enable more effective representation learning? To address this, we propose a simple plug-and-play neural network layer called Segment, Shuffle, and Stitch (S3) designed to improve representation learning in time-series models. S3 works by creating non-overlapping segments from the original sequence and shuffling them in a learned manner that is optimal for the task at hand. It then re-attaches the shuffled segments back together and performs a learned weighted sum with the original input to capture both the newly shuffled sequence along with the original sequence. S3 is modular and can be stacked to achieve different levels of granularity, and can be added to many forms of neural architectures including CNNs or Transformers with negligible computation overhead. Through extensive experiments on several datasets and state-of-the-art baselines, we show that incorporating S3 results in significant improvements for the tasks of time-series classification, forecasting, and anomaly detection, improving performance on certain datasets by up to 68\%. We also show that S3 makes the learning more stable with a smoother training loss curve and loss landscape compared to the original baseline. The code is available at https://github.com/shivam-grover/S3-TimeSeries.

Computer Vision · Segmentation

Ziyi Wang, Yanbo Wang, Xumin Yu, Jie Zhou, Jiwen Lu

Existing methodologies in open vocabulary 3D semantic segmentation primarily concentrate on establishing a unified feature space encompassing 3D, 2D, and textual modalities. Nevertheless, traditional techniques such as global feature alignment or vision-language model distillation tend to impose only approximate correspondence, struggling notably with delineating fine-grained segmentation boundaries. To address this gap, we propose a more meticulous mask-level alignment between 3D features and the 2D-text embedding space through a cross-modal mask reasoning framework, XMask3D. In our approach, we developed a mask generator based on the denoising UNet from a pre-trained diffusion model, leveraging its capability for precise textual control over dense pixel representations and enhancing the open-world adaptability of the generated masks. We further integrate 3D global features as implicit conditions into the pre-trained 2D denoising UNet, enabling the generation of segmentation masks with additional 3D geometry awareness. Subsequently, the generated 2D masks are employed to align mask-level 3D representations with the vision-language feature space, thereby augmenting the open vocabulary capability of 3D geometry embeddings. Finally, we fuse complementary 2D and 3D mask features, resulting in competitive performance across multiple benchmarks for 3D open vocabulary semantic segmentation. Code is available at https://github.com/wangzy22/XMask3D.

Deep Learning · Algorithms

Jinrui Yang, Xianhang Li, Druv Pai, Yuyin Zhou, Yi Ma, Yaodong Yu, Cihang Xie

CRATE, a white-box transformer architecture designed to learn compressed and sparse representations, offers an intriguing alternative to standard vision transformers (ViTs) due to its inherent mathematical interpretability. Despite extensive investigations into the scaling behaviors of language and vision transformers, the scalability of CRATE remains an open question which this paper aims to address. Specifically, we propose CRATE-$\alpha$, featuring strategic yet minimal modifications to the sparse coding block in the CRATE architecture design, and a light training recipe designed to improve the scalability of CRATE.Through extensive experiments, we demonstrate that CRATE-$\alpha$ can effectively scale with larger model sizes and datasets. For example, our CRATE-$\alpha$-B substantially outperforms the prior best CRATE-B model accuracy on ImageNet classification by 3.7%, achieving an accuracy of 83.2%. Meanwhile, when scaling further, our CRATE-$\alpha$-L obtains an ImageNet classification accuracy of 85.1%. More notably, these model performance improvements are achieved while preserving, and potentially even enhancing the interpretability of learned CRATE models, as we demonstrate through showing that the learned token representations of increasingly larger trained CRATE-$\alpha$ models yield increasingly higher-quality unsupervised object segmentation of images.

Computer Vision · Segmentation

Laurynas Karazija, Iro Laina, Christian Rupprecht, Andrea Vedaldi

We consider the problem of segmenting objects in videos based on their motion and no other forms of supervision. Prior work has often approached this problem by using the principle of common fate, namely the fact that the motion of points that belong to the same object is strongly correlated. However, most authors have only considered instantaneous motion from optical flow. In this work, we present a way to train a segmentation network using long-term point trajectories as a supervisory signal to complement optical flow. The key difficulty is that long-term motion, unlike instantaneous motion, is difficult to model -- any parametric approximation is unlikely to capture complex motion patterns over long periods of time. We instead draw inspiration from subspace clustering approaches, proposing a loss function that seeks to group the trajectories into low-rank matrices where the motion of object points can be approximately explained as a linear combination of other point tracks. Our method outperforms the prior art on motion-based segmentation, which shows the utility of long-term motion and the effectiveness of our formulation.

Online Learning

Stephen Pasteris, Chris Hicks, Vasilios Mavroudis, Mark Herbster

We consider the classic problem of online convex optimisation. Whereas the notion of static regret is relevant for stationary problems, the notion of switching regret is more appropriate for non-stationary problems. A switching regret is defined relative to any segmentation of the trial sequence, and is equal to the sum of the static regrets of each segment. In this paper we show that, perhaps surprisingly, we can achieve the asymptotically optimal switching regret on every possible segmentation simultaneously. Our algorithm for doing so is very efficient: having a space and per-trial time complexity that is logarithmic in the time-horizon. Our algorithm also obtains novel bounds on its dynamic regret: being adaptive to variations in the rate of change of the comparator sequence.

Computer Vision

Lei Zhu, Xinjiang Wang, Wayne Zhang, Rynson Lau

Convolutions (Convs) and multi-head self-attentions (MHSAs) are typically considered alternatives to each other for building vision backbones. Although some works try to integrate both, they apply the two operators simultaneously at the finest pixel granularity. With Convs responsible for per-pixel feature extraction already, the question is whether we still need to include the heavy MHSAs at such a fine-grained level. In fact, this is the root cause of the scalability issue w.r.t. the input resolution for vision transformers. To address this important problem, we propose in this work to use MSHAs and Convs in parallel \textbf{at different granularity levels} instead. Specifically, in each layer, we use two different ways to represent an image: a fine-grained regular grid and a coarse-grained set of semantic slots. We apply different operations to these two representations: Convs to the grid for local features, and MHSAs to the slots for global features. A pair of fully differentiable soft clustering and dispatching modules is introduced to bridge the grid and set representations, thus enabling local-global fusion. Through extensive experiments on various vision tasks, we empirically verify the potential of the proposed integration scheme, named \textit{GLMix}: by offloading the burden of fine-grained features to light-weight Convs, it is sufficient to use MHSAs in a few (e.g., 64) semantic slots to match the performance of recent state-of-the-art backbones, while being more efficient. Our visualization results also demonstrate that the soft clustering module produces a meaningful semantic grouping effect with only IN1k classification supervision, which may induce better interpretability and inspire new weakly-supervised semantic segmentation approaches. Code will be available at \url{https://github.com/rayleizhu/GLMix}.

Generative Models · Diffusion models

Sangwon Jang, Jaehyeong Jo, Kimin Lee, Sung Ju Hwang

Text-to-image diffusion models have shown remarkable success in generating personalized subjects based on a few reference images. However, current methods often fail when generating multiple subjects simultaneously, resulting in mixedidentities with combined attributes from different subjects. In this work, we present MuDI, a novel framework that enables multi-subject personalization by effectively decoupling identities from multiple subjects. Our main idea is to utilize segmented subjects generated by a foundation model for segmentation (Segment Anything) for both training and inference, as a form of data augmentation for training and initialization for the generation process. Moreover, we further introduce a new metric to better evaluate the performance of our method on multi-subject personalization. Experimental results show that our MuDI can produce high-quality personalized images without identity mixing, even for highly similar subjects as shown in Figure 1. Specifically, in human evaluation, MuDI obtains twice the success rate for personalizing multiple subjects without identity mixing over existing baselines and is preferred over 70% against the strongest baseline.

Miscellaneous Aspects of Machine Learning · General Machine Learning Techniques

Wangbo Zhao, Jiasheng Tang, Yizeng Han, Yibing Song, Kai Wang, Gao Huang, Fan Wang, Yang You

Existing parameter-efficient fine-tuning (PEFT) methods have achieved significant success on vision transformers (ViTs) adaptation by improving parameter efficiency. However, the exploration of enhancing inference efficiency during adaptation remains underexplored. This limits the broader application of pre-trained ViT models, especially when the model is computationally extensive. In this paper, we propose Dynamic Tuning (DyT), a novel approach to improve both parameter and inference efficiency for ViT adaptation. Specifically, besides using the lightweight adapter modules, we propose a token dispatcher to distinguish informative tokens from less important ones, allowing the latter to dynamically skip the original block, thereby reducing the redundant computation during inference. Additionally, we explore multiple design variants to find the best practice of DyT. Finally, inspired by the mixture-of-experts (MoE) mechanism, we introduce an enhanced adapter to further boost the adaptation performance. We validate DyT across various tasks, including image/video recognition and semantic segmentation. For instance, DyT achieves superior performance compared to existing PEFT methods while evoking only 71% of their FLOPs on the VTAB-1K benchmark.

Computer Vision · Segmentation

Duc Cao Dinh, Seok Joon Kim, Kyusung Cho

PAnoramic Semantic Segmentation (PASS) is an important task in computer vision,as it enables semantic understanding of a 360° environment. Currently,most of existing works have focused on addressing the distortion issues in 2Dpanoramic images without considering spatial properties of indoor scene. Thisrestricts PASS methods in perceiving contextual attributes to deal with the ambiguitywhen working with monocular images. In this paper, we propose a novelapproach for indoor panoramic semantic segmentation. Unlike previous works,we consider the panoramic image as a composition of segment groups: oversampledsegments, representing planar structures such as floors and ceilings, andunder-sampled segments, representing other scene elements. To optimize eachgroup, we first enhance over-sampled segments by jointly optimizing with a densedepth estimation task. Then, we introduce a transformer-based context modulethat aggregates different geometric representations of the scene, combinedwith a simple high-resolution branch, it serves as a robust hybrid decoder forestimating under-sampled segments, effectively preserving the resolution of predictedmasks while leveraging various indoor geometric properties. Experimentalresults on both real-world (Stanford2D3DS, Matterport3D) and synthetic (Structured3D)datasets demonstrate the robustness of our framework, by setting newstate-of-the-arts in almost evaluations, The code and updated results are availableat: https://github.com/caodinhduc/vertical_relative_distance.

Computer Vision · Segmentation

Hikaru Shindo, Manuel Brack, Gopika Sudhakaran, Devendra S Dhami, Patrick Schramowski, Kristian Kersting

Large-scale, pre-trained neural networks have demonstrated strong capabilities in various tasks, including zero-shot image segmentation. To identify concrete objects in complex scenes, humans instinctively rely on deictic descriptions in natural language, i.e., referring to something depending on the context such as "The object that is on the desk and behind the cup.". However, deep learning approaches cannot reliably interpret such deictic representations due to their lack of reasoning capabilities in complex scenarios. To remedy this issue, we propose DeiSAM — a combination of large pre-trained neural networks with differentiable logic reasoners — for deictic promptable segmentation. Given a complex, textual segmentation description, DeiSAM leverages Large Language Models (LLMs) to generate first-order logic rules and performs differentiable forward reasoning on generated scene graphs. Subsequently, DeiSAM segments objects by matching them to the logically inferred image regions. As part of our evaluation, we propose the Deictic Visual Genome (DeiVG) dataset, containing paired visual input and complex, deictic textual prompts. Our empirical results demonstrate that DeiSAM is a substantial improvement over purely data-driven baselines for deictic promptable segmentation.

Theory · Domain Adaptation and Transfer Learning

Kai Hu, JinHao Li, Yuan Zhang, Xiongjun Ye, Xieping Gao

In multi-sequence Magnetic Resonance Imaging (MRI), the accurate segmentation of the kidney and tumor based on traditional supervised methods typically necessitates detailed annotation for each sequence, which is both time-consuming and labor-intensive. Unsupervised Domain Adaptation (UDA) methods can effectively mitigate inter-domain differences by aligning cross-modal features, thereby reducing the annotation burden. However, most existing UDA methods are limited to one-to-one domain adaptation, which tends to be inefficient and resource-intensive when faced with multi-target domain transfer tasks. To address this challenge, we propose a novel and efficient One-to-Multiple Progressive Style Transfer Unsupervised Domain-Adaptive (PSTUDA) framework for kidney and tumor segmentation in multi-sequence MRI. Specifically, we develop a multi-level style dictionary to explicitly store the style information of each target domain at various stages, which alleviates the burden of a single generator in a multi-target transfer task and enables effective decoupling of content and style. Concurrently, we employ multiple cascading style fusion modules that utilize point-wise instance normalization to progressively recombine content and style features, which enhances cross-modal alignment and structural consistency. Experiments conducted on the private MSKT and public KiTS19 datasets demonstrate the superiority of the proposed PSTUDA over comparative methods in multi-sequence kidney and tumor segmentation. The average Dice Similarity Coefficients are increased by at least 1.8% and 3.9%, respectively. Impressively, our PSTUDA not only significantly reduces the floating-point computation by approximately 72% but also reduces the number of model parameters by about 50%, bringing higher efficiency and feasibility to practical clinical applications.

Anwesa Choudhuri, Girish Chowdhary, Alex Schwing

We propose the new task open-world video instance segmentation and captioning. It requires to detect, segment, track and describe with rich captions never before seen objects. This challenging task can be addressed by developing "abstractors" which connect a vision model and a language foundation model. Concretely, we connect a multi-scale visual feature extractor and a large language model (LLM) by developing an object abstractor and an object-to-text abstractor. The object abstractor, consisting of a prompt encoder and transformer blocks, introduces spatially-diverse open-world object queries to discover never before seen objects in videos. An inter-query contrastive loss further encourages the diversity of object queries. The object-to-text abstractor is augmented with masked cross-attention and acts as a bridge between the object queries and a frozen LLM to generate rich and descriptive object-centric captions for each detected object. Our generalized approach surpasses the baseline that jointly addresses the tasks of open-world video instance segmentation and dense video object captioning by 13% on never before seen objects, and by 10% on object-centric captions.