As a de facto solution, the vanilla Vision Transformers (ViTs) are encouraged to model long-range dependencies between arbitrary image patches while the global attended receptive field leads to quadratic computational cost. Another branch of Vision Transformers exploits local attention inspired by CNNs, which only models the interactions between patches in small neighborhoods. Although such a solution reduces the computational cost, it naturally suffers from small attended receptive fields, which may limit the performance. In this work, we explore effective Vision Transformers to pursue a preferable trade-off between the computational complexity and size of the attended receptive field. By analyzing the patch interaction of global attention in ViTs, we observe two key properties in the shallow layers, namely locality and sparsity, indicating the redundancy of global dependency modeling in shallow layers of ViTs. Accordingly, we propose Multi-Scale Dilated Attention (MSDA) to model local and sparse patch interaction within the sliding window. With a pyramid architecture, we construct a Multi-Scale Dilated Transformer (DilateFormer) by stacking MSDA blocks at low-level stages and global multi-head self-attention blocks at high-level stages. Our experiment results show that our DilateFormer achieves state-of-the-art performance on various vision tasks. On ImageNet-1K classification task, DilateFormer achieves comparable performance with 70% fewer FLOPs compared with existing state-of-the-art models. Our DilateFormer-Base achieves 85.6% top-1 accuracy on ImageNet-1K classification task, 53.5% box mAP/46.1% mask mAP on COCO object detection/instance segmentation task and 51.1% MS mIoU on ADE20K semantic segmentation task.
LiDAR-based 3D object detection and panoptic segmentation are two crucial tasks in the perception systems of autonomous vehicles and robots. In this paper, we propose All-in-One Perception Network (AOP-Net), a LiDAR-based multi-task framework that combines 3D object detection and panoptic segmentation. In this method, a dual-task 3D backbone is developed to extract both panoptic- and detection-level features from the input LiDAR point cloud. Also, a new 2D backbone that intertwines Multi-Layer Perceptron (MLP) and convolution layers is designed to further improve the detection task performance. Finally, a novel module is proposed to guide the detection head by recovering useful features discarded during down-sampling operations in the 3D backbone. This module leverages estimated instance segmentation masks to recover detailed information from each candidate object. The AOP-Net achieves state-of-the-art performance for published works on the nuScenes benchmark for both 3D object detection and panoptic segmentation tasks. Also, experiments show that our method easily adapts to and significantly improves the performance of any BEV-based 3D object detection method.
Recently, inspired by DETR variants, query-based end-to-end instance segmentation (QEIS) methods have outperformed CNN-based models on large-scale datasets. Yet they would lose efficacy when only a small amount of training data is available since it's hard for the crucial queries/kernels to learn localization and shape priors. To this end, this work offers a novel unsupervised pre-training solution for low-data regimes. Inspired by the recent success of the Prompting technique, we introduce a new pre-training method that boosts QEIS models by giving Saliency Prompt for queries/kernels. Our method contains three parts: 1) Saliency Masks Proposal is responsible for generating pseudo masks from unlabeled images based on the saliency mechanism. 2) Prompt-Kernel Matching transfers pseudo masks into prompts and injects the corresponding localization and shape priors to the best-matched kernels. 3) Kernel Supervision is applied to supply supervision at the kernel level for robust learning. From a practical perspective, our pre-training method helps QEIS models achieve a similar convergence speed and comparable performance with CNN-based models in low-data regimes. Experimental results show that our method significantly boosts several QEIS models on three datasets. Code will be made available.
Minerals, metals, and plastics are indispensable for a functioning modern society. Yet, their supply is limited causing a need for optimizing ore extraction and recuperation from recyclable materials.Typically, those processes must be meticulously adapted to the precise properties of the processed materials. Advancing our understanding of these materials is thus vital and can be achieved by crushing them into particles of micrometer size followed by their characterization. Current imaging approaches perform this analysis based on segmentation and characterization of particles imaged with computed tomography (CT), and rely on rudimentary postprocessing techniques to separate touching particles. However, their inability to reliably perform this separation as well as the need to retrain methods for each new image, these approaches leave untapped potential to be leveraged. Here, we propose ParticleSeg3D, an instance segmentation method able to extract individual particles from large CT images of particle samples containing different materials. Our approach is based on the powerful nnU-Net framework, introduces a particle size normalization, uses a border-core representation to enable instance segmentation, and is trained with a large dataset containing particles of numerous different sizes, shapes, and compositions of various materials. We demonstrate that ParticleSeg3D can be applied out-of-the-box to a large variety of particle types, including materials and appearances that have not been part of the training set. Thus, no further manual annotations and retraining are required when applying the method to new particle samples, enabling substantially higher scalability of experiments than existing methods. Our code and dataset are made publicly available.
Unsupervised Video Object Segmentation (UVOS) aims at discovering objects and tracking them through videos. For accurate UVOS, we observe if one can locate precise segment proposals on key frames, subsequent processes are much simpler. Hence, we propose to reason about key frame proposals using a graph built with the object probability masks initially generated from multiple frames around the key frame and then propagated to the key frame. On this graph, we compute maximal cliques, with each clique representing one candidate object. By making multiple proposals in the clique to vote for the key frame proposal, we obtain refined key frame proposals that could be better than any of the single-frame proposals. A semi-supervised VOS algorithm subsequently tracks these key frame proposals to the entire video. Our algorithm is modular and hence can be used with any instance segmentation and semi-supervised VOS algorithm. We achieve state-of-the-art performance on the DAVIS-2017 validation and test-dev dataset. On the related problem of video instance segmentation, our method shows competitive performance with the previous best algorithm that requires joint training with the VOS algorithm.
We propose a graph clustering formulation based on multicut (a.k.a. weighted correlation clustering) on the complete graph. Our formulation does not need specification of the graph topology as in the original sparse formulation of multicut, making our approach simpler and potentially better performing. In contrast to unweighted correlation clustering we allow for a more expressive weighted cost structure. In dense multicut, the clustering objective is given in a factorized form as inner products of node feature vectors. This allows for an efficient formulation and inference in contrast to multicut/weighted correlation clustering, which has at least quadratic representation and computation complexity when working on the complete graph. We show how to rewrite classical greedy algorithms for multicut in our dense setting and how to modify them for greater efficiency and solution quality. In particular, our algorithms scale to graphs with tens of thousands of nodes. Empirical evidence on instance segmentation on Cityscapes and clustering of ImageNet datasets shows the merits of our approach.
Despite recent advances in data-independent and deep-learning algorithms, unstained live adherent cell instance segmentation remains a long-standing challenge in cell image processing. Adherent cells' inherent visual characteristics, such as low contrast structures, fading edges, and irregular morphology, have made it difficult to distinguish from one another, even by human experts, let alone computational methods. In this study, we developed a novel deep-learning algorithm called dual-view selective instance segmentation network (DVSISN) for segmenting unstained adherent cells in differential interference contrast (DIC) images. First, we used a dual-view segmentation (DVS) method with pairs of original and rotated images to predict the bounding box and its corresponding mask for each cell instance. Second, we used a mask selection (MS) method to filter the cell instances predicted by the DVS to keep masks closest to the ground truth only. The developed algorithm was trained and validated on our dataset containing 520 images and 12198 cells. Experimental results demonstrate that our algorithm achieves an AP_segm of 0.555, which remarkably overtakes a benchmark by a margin of 23.6%. This study's success opens up a new possibility of using rotated images as input for better prediction in cell images.
Contemporary approaches to instance segmentation in cell science use 2D or 3D convolutional networks depending on the experiment and data structures. However, limitations in microscopy systems or efforts to prevent phototoxicity commonly require recording sub-optimally sampled data regimes that greatly reduces the utility of such 3D data, especially in crowded environments with significant axial overlap between objects. In such regimes, 2D segmentations are both more reliable for cell morphology and easier to annotate. In this work, we propose the Projection Enhancement Network (PEN), a novel convolutional module which processes the sub-sampled 3D data and produces a 2D RGB semantic compression, and is trained in conjunction with an instance segmentation network of choice to produce 2D segmentations. Our approach combines augmentation to increase cell density using a low-density cell image dataset to train PEN, and curated datasets to evaluate PEN. We show that with PEN, the learned semantic representation in CellPose encodes depth and greatly improves segmentation performance in comparison to maximum intensity projection images as input, but does not similarly aid segmentation in region-based networks like Mask-RCNN. Finally, we dissect the segmentation strength against cell density of PEN with CellPose on disseminated cells from side-by-side spheroids. We present PEN as a data-driven solution to form compressed representations of 3D data that improve 2D segmentations from instance segmentation networks.
We propose Cut-and-LEaRn (CutLER), a simple approach for training unsupervised object detection and segmentation models. We leverage the property of self-supervised models to 'discover' objects without supervision and amplify it to train a state-of-the-art localization model without any human labels. CutLER first uses our proposed MaskCut approach to generate coarse masks for multiple objects in an image and then learns a detector on these masks using our robust loss function. We further improve the performance by self-training the model on its predictions. Compared to prior work, CutLER is simpler, compatible with different detection architectures, and detects multiple objects. CutLER is also a zero-shot unsupervised detector and improves detection performance AP50 by over 2.7 times on 11 benchmarks across domains like video frames, paintings, sketches, etc. With finetuning, CutLER serves as a low-shot detector surpassing MoCo-v2 by 7.3% APbox and 6.6% APmask on COCO when training with 5% labels.
Visual objects often have acoustic signatures that are naturally synchronized with them in audio-bearing video recordings. For this project, we explore the multimodal feature aggregation for video instance segmentation task, in which we integrate audio features into our video segmentation model to conduct an audio-visual learning scheme. Our method is based on existing video instance segmentation method which leverages rich contextual information across video frames. Since this is the first attempt to investigate the audio-visual instance segmentation, a novel dataset, including 20 vocal classes with synchronized video and audio recordings, is collected. By utilizing combined decoder to fuse both video and audio features, our model shows a slight improvements compared to the base model. Additionally, we managed to show the effectiveness of different modules by conducting extensive ablations.
Large-scale object detection and instance segmentation face a severe data imbalance. The finer-grained object classes become, the less frequent they appear in our datasets. However, at test-time, we expect a detector that performs well for all classes and not just the most frequent ones. In this paper, we provide a theoretical understanding of the long-trail detection problem. We show how the commonly used mean average precision evaluation metric on an unknown test set is bound by a margin-based binary classification error on a long-tailed object detection training set. We optimize margin-based binary classification error with a novel surrogate objective called \textbf{Effective Class-Margin Loss} (ECM). The ECM loss is simple, theoretically well-motivated, and outperforms other heuristic counterparts on LVIS v1 benchmark over a wide range of architecture and detectors. Code is available at \url{https://github.com/janghyuncho/ECM-Loss}.
Most existing transformer based video instance segmentation methods extract per frame features independently, hence it is challenging to solve the appearance deformation problem. In this paper, we observe the temporal information is important as well and we propose TAFormer to aggregate spatio-temporal features both in transformer encoder and decoder. Specifically, in transformer encoder, we propose a novel spatio-temporal joint multi-scale deformable attention module which dynamically integrates the spatial and temporal information to obtain enriched spatio-temporal features. In transformer decoder, we introduce a temporal self-attention module to enhance the frame level box queries with the temporal relation. Moreover, TAFormer adopts an instance level contrastive loss to increase the discriminability of instance query embeddings. Therefore the tracking error caused by visually similar instances can be decreased. Experimental results show that TAFormer effectively leverages the spatial and temporal information to obtain context-aware feature representation and outperforms state-of-the-art methods.
Contour-based instance segmentation has been actively studied, thanks to its flexibility and elegance in processing visual objects within complex backgrounds. In this work, we propose a novel deep network architecture, i.e., PolySnake, for generic contour-based instance segmentation. Motivated by the classic Snake algorithm, the proposed PolySnake achieves superior and robust segmentation performance with an iterative and progressive contour refinement strategy. Technically, PolySnake introduces a recurrent update operator to estimate the object contour iteratively. It maintains a single estimate of the contour that is progressively deformed toward the object boundary. At each iteration, PolySnake builds a semantic-rich representation for the current contour and feeds it to the recurrent operator for further contour adjustment. Through the iterative refinements, the contour progressively converges to a stable status that tightly encloses the object instance. Beyond the scope of general instance segmentation, extensive experiments are conducted to validate the effectiveness and generalizability of our PolySnake in two additional specific task scenarios, including scene text detection and lane detection. The results demonstrate that the proposed PolySnake outperforms the existing advanced methods on several multiple prevalent benchmarks across the three tasks. The codes and pre-trained models are available at https://github.com/fh2019ustc/PolySnake
In this work, we present a method to extract the skeleton of a self-occluded tree canopy by estimating the unobserved structures of the tree. A tree skeleton compactly describes the topological structure and contains useful information such as branch geometry, positions and hierarchy. This can be critical to planning contact interactions for agricultural manipulation, yet is difficult to gain due to occlusion by leaves, fruits and other branches. Our method uses an instance segmentation network to detect visible trunk, branches, and twigs. Then, based on the observed tree structures, we build a custom 3D likelihood map in the form of an occupancy grid to hypothesize on the presence of occluded skeletons through a series of minimum cost path searches. We show that our method outperforms baseline methods in highly occluded scenes, demonstrated through a set of experiments on a synthetic tree dataset. Qualitative results are also presented on a real tree dataset collected from the field.
Recent advancements in vision-language pre-training (e.g. CLIP) have shown that vision models can benefit from language supervision. While many models using language modality have achieved great success on 2D vision tasks, the joint representation learning of 3D point cloud with text remains under-explored due to the difficulty of 3D-Text data pair acquisition and the irregularity of 3D data structure. In this paper, we propose a novel Text4Point framework to construct language-guided 3D point cloud models. The key idea is utilizing 2D images as a bridge to connect the point cloud and the language modalities. The proposed Text4Point follows the pre-training and fine-tuning paradigm. During the pre-training stage, we establish the correspondence of images and point clouds based on the readily available RGB-D data and use contrastive learning to align the image and point cloud representations. Together with the well-aligned image and text features achieved by CLIP, the point cloud features are implicitly aligned with the text embeddings. Further, we propose a Text Querying Module to integrate language information into 3D representation learning by querying text embeddings with point cloud features. For fine-tuning, the model learns task-specific 3D representations under informative language guidance from the label set without 2D images. Extensive experiments demonstrate that our model shows consistent improvement on various downstream tasks, such as point cloud semantic segmentation, instance segmentation, and object detection. The code will be available here: https://github.com/LeapLabTHU/Text4Point
We propose Mask Auto-Labeler (MAL), a high-quality Transformer-based mask auto-labeling framework for instance segmentation using only box annotations. MAL takes box-cropped images as inputs and conditionally generates their mask pseudo-labels.We show that Vision Transformers are good mask auto-labelers. Our method significantly reduces the gap between auto-labeling and human annotation regarding mask quality. Instance segmentation models trained using the MAL-generated masks can nearly match the performance of their fully-supervised counterparts, retaining up to 97.4\% performance of fully supervised models. The best model achieves 44.1\% mAP on COCO instance segmentation (test-dev 2017), outperforming state-of-the-art box-supervised methods by significant margins. Qualitative results indicate that masks produced by MAL are, in some cases, even better than human annotations.
Handwritten circuit diagrams from educational scenarios or historic sources usually exist on analogue media. For deriving their functional principles or flaws automatically, they need to be digitized, extracting their electrical graph. Recently, the base technologies for automated pipelines facilitating this process shifted from computer vision to machine learning. This paper describes an approach for extracting both the electrical components (including their terminals and describing texts) as well their interconnections (including junctions and wire hops) by the means of instance segmentation and keypoint extraction. Consequently, the resulting graph extraction process consists of a simple two-step process of model inference and trivial geometric keypoint matching. The dataset itself, its preparation, model training and post-processing are described and publicly available.
We identify and overcome two key obstacles in extending the success of BERT-style pre-training, or the masked image modeling, to convolutional networks (convnets): (i) convolution operation cannot handle irregular, random-masked input images; (ii) the single-scale nature of BERT pre-training is inconsistent with convnet's hierarchical structure. For (i), we treat unmasked pixels as sparse voxels of 3D point clouds and use sparse convolution to encode. This is the first use of sparse convolution for 2D masked modeling. For (ii), we develop a hierarchical decoder to reconstruct images from multi-scale encoded features. Our method called Sparse masKed modeling (SparK) is general: it can be used directly on any convolutional model without backbone modifications. We validate it on both classical (ResNet) and modern (ConvNeXt) models: on three downstream tasks, it surpasses both state-of-the-art contrastive learning and transformer-based masked modeling by similarly large margins (around +1.0%). Improvements on object detection and instance segmentation are more substantial (up to +3.5%), verifying the strong transferability of features learned. We also find its favorable scaling behavior by observing more gains on larger models. All this evidence reveals a promising future of generative pre-training on convnets. Codes and models are released at https://github.com/keyu-tian/SparK.
The general domain of video segmentation is currently fragmented into different tasks spanning multiple benchmarks. Despite rapid progress in the state-of-the-art, current methods are overwhelmingly task-specific and cannot conceptually generalize to other tasks. Inspired by recent approaches with multi-task capability, we propose TarViS: a novel, unified network architecture that can be applied to any task that requires segmenting a set of arbitrarily defined 'targets' in video. Our approach is flexible with respect to how tasks define these targets, since it models the latter as abstract 'queries' which are then used to predict pixel-precise target masks. A single TarViS model can be trained jointly on a collection of datasets spanning different tasks, and can hot-swap between tasks during inference without any task-specific retraining. To demonstrate its effectiveness, we apply TarViS to four different tasks, namely Video Instance Segmentation (VIS), Video Panoptic Segmentation (VPS), Video Object Segmentation (VOS) and Point Exemplar-guided Tracking (PET). Our unified, jointly trained model achieves state-of-the-art performance on 5/7 benchmarks spanning these four tasks, and competitive performance on the remaining two. Code and model weights are available at: https://github.com/Ali2500/TarViS
Unlike language tasks, where the output space is usually limited to a set of tokens, the output space of visual tasks is more complicated, making it difficult to build a unified visual model for various visual tasks. In this paper, we seek to unify the output space of visual tasks, so that we can also build a unified model for visual tasks. To this end, we demonstrate a single unified model that simultaneously handles two typical visual tasks of instance segmentation and depth estimation, which have discrete/fixed-length and continuous/varied-length outputs, respectively. We propose several new techniques that take into account the particularity of visual tasks: 1) Soft token. We employ soft token to represent the task output. Unlike hard tokens in the common VQ-VAE which are assigned one-hot to discrete codebooks/vocabularies, the soft token is assigned softly to the codebook embeddings. Soft token can improve the accuracy of both the next token inference and decoding of the task output; 2) Mask augmentation. Many visual tasks have corruption, undefined or invalid values in label annotations, i.e., occluded area of depth maps. We show that a mask augmentation technique can greatly benefit these tasks. With these new techniques and other designs, we show that the proposed general-purpose task-solver can perform both instance segmentation and depth estimation well. Particularly, we achieve 0.279 RMSE on the specific task of NYUv2 depth estimation, setting a new record on this benchmark. The general-purpose task-solver, dubbed AiT, is available at \url{https://github.com/SwinTransformer/AiT}.