In semi-supervised medical image segmentation tasks, the annotation quality of complex 3D samples is often inconsistent, manual annotation is costly, and differences in annotations from different radiologists further complicate the segmentation process. Moreover, the limited number of annotated samples reduces the model’s generalization ability, making it difficult to fully capture the 3D information inherent in medical data. To address these issues, we propose a Coarse Label Generation and Reorganization Network (CoGRNet), which introduces an efficient slice annotation method into semi-supervised models. Using manually annotated 2D slices on two mutually orthogonal planes, complete 3D coarse labels are generated through a spatial mapping module, significantly reducing annotation complexity. We adopt the Mean Teacher (MT) framework as the backbone network, combining coarse labels generated from different slice mappings with samples to form new training samples, which are cyclically fed into the network. Additionally, based on the characteristics of different datasets, a Focus Area (FA) strategy is employed to guide the reorganization of labeled and unlabeled samples, enhancing information fusion and improving model generalization. This approach achieves better segmentation performance while preserving detail. We compared our method with other classical semi-supervised approaches, as well as the MT method using fully annotated datasets, and validated its effectiveness on three public datasets.

When applied to autonomous vehicle (AV) settings, action recognition can enhance an environment model's situational awareness. This is especially prevalent in scenarios where traditional geometric descriptions and heuristics in AVs are insufficient. However, action recognition has traditionally been studied for humans, and its limited adaptability to noisy, un-clipped, un-pampered, raw RGB data has limited its application in other fields. To push for the advancement and adoption of action recognition into AVs, this work proposes a novel two-stage action recognition system, termed RALACs. RALACs formulates the problem of action recognition for road scenes, and bridges the gap between it and the established field of human action recognition. This work shows how attention layers can be useful for encoding the relations across agents, and stresses how such a scheme can be class-agnostic. Furthermore, to address the dynamic nature of agents on the road, RALACs constructs a novel approach to adapting Region of Interest (ROI) alignment to agent tracks for downstream action classification. Finally, our scheme also considers the problem of active agent detection, and utilizes a novel application of fusing optical flow maps to discern relevant agents in a road scene. We show that our proposed scheme can outperform the baseline on the ICCV2021 Road Challenge dataset (Singh et al., 2023) algorithm and by deploying it on a real vehicle platform, we provide preliminary insight to the usefulness of action recognition in decision making. The code is publicly available at https://github.com/WATonomous/action-classification.

Unsupervised anomaly detection methods based on knowledge distillation have exhibited promising results. However, there is still room for improvement in the differential characterization of anomalous samples. In this paper, a novel anomaly detection and localization model based on reverse knowledge distillation is proposed, where an enhanced multi-scale feature mutual mapping feature fusion module is proposed to greatly extract discrepant features at different scales. This module helps enhance the difference in anomaly region representation in the teacher-student structure by inhomogeneously fusing features at different levels. Then, the coordinate attention mechanism is introduced in the reverse distillation structure to pay special attention to dominant issues, facilitating nice direction guidance and position encoding. Furthermore, an innovative single-category embedding memory bank, inspired by human memory mechanisms, is developed to normalize single-category embedding to encourage high-quality model reconstruction. Finally, in several categories of the well-known MVTec dataset, our model achieves better results than state-of-the-art models in terms of AUROC and PRO, with an overall average of 98.1%, 98.3%, and 95.0% for detection AUROC scores, localization AUROC scores, and localization PRO scores, respectively, across 15 categories. Extensive experiments are conducted on the ablation study to validate the contribution of each component of the model.

Recently proposed decoupled training methods emerge as a dominant paradigm for long-tailed object detection. But they require an extra fine-tuning stage, and the dis-jointed optimization of representation and classifier might lead to suboptimal results. However, end-to-end training methods, like equalization loss (EQL), still perform worse than decoupled training methods. In this paper, we re-veal the main issue in long-tailed object detection is the imbalanced gradients between positives and negatives, and find that EQL does not solve it well. To address the problem of imbalanced gradients, we introduce a new version of equalization loss, called equalization loss v2 (EQL v2), a novel gradient guided reweighing mechanism that re-balances the training process for each category independently and equally. Extensive experiments are performed on the challenging LVIS benchmark. EQL v2 outperforms origin EQL by about 4 points overall AP with 14 ∼ 18 points improvements on the rare categories. More importantly, it also surpasses decoupled training methods. With-out further tuning for the Open Images dataset, EQL v2 improves EQL by 7.3 points AP, showing strong generalization ability. Codes have been released at https://github.com/tztztztztz/eqlv2

The two-stage methods for instance segmentation, e.g. Mask R-CNN, have achieved excellent performance recently. However, the segmented masks are still very coarse due to the downsampling operations in both the feature pyramid and the instance-wise pooling process, especially for large objects. In this work, we propose a new method called RefineMask for high-quality instance segmentation of objects and scenes, which incorporates fine-grained features during the instance-wise segmenting process in a multi-stage manner. Through fusing more detailed information stage by stage, RefineMask is able to refine high-quality masks consistently. RefineMask succeeds in segmenting hard cases such as bent parts of objects that are oversmoothed by most previous methods and outputs accurate boundaries. Without bells and whistles, RefineMask yields significant gains of 2.6, 3.4, 3.8 AP over Mask R-CNN on COCO, LVIS, and Cityscapes benchmarks respectively at a small amount of additional computational cost. Furthermore, our single-model result outperforms the winner of the LVIS Challenge 2020 by 1.3 points on the LVIS test-dev set and establishes a new state-of-the-art. Code will be available at https://github.com/zhanggang001/RefineMask.

A standard practice of deploying deep neural networks is to apply the same architecture to all the input instances. However, a fixed architecture may not be suitable for different data with high diversity. To boost the model capacity, existing methods usually employ larger convolutional kernels or deeper network layers, which incurs prohibitive computational costs. In this paper, we address this issue by proposing Differentiable Dynamic Wirings (DDW), which learns the instance-aware connectivity that creates different wiring patterns for different instances. 1) Specifically, the network is initialized as a complete directed acyclic graph, where the nodes represent convolutional blocks and the edges represent the connection paths. 2) We generate edge weights by a learnable module, Router, and select the edges whose weights are larger than a threshold, to adjust the connectivity of the neural network structure. 3) Instead of using the same path of the network, DDW aggregates features dynamically in each node, which allows the network to have more representation power.To facilitate effective training, we further represent the network connectivity of each sample as an adjacency matrix. The matrix is updated to aggregate features in the forward pass, cached in the memory, and used for gradient computing in the backward pass. We validate the effectiveness of our approach with several mainstream architectures, including MobileNetV2, ResNet, ResNeXt, and RegNet. Extensive experiments are performed on ImageNet classification and COCO object detection, which demonstrates the effectiveness and generalization ability of our approach.

Recent works imply that the channel pruning can be regarded as searching optimal sub-structure from unpruned networks. However, existing works based on this observation require training and evaluating a large number of structures, which limits their application. In this paper, we propose a novel differentiable method for channel pruning, named Differentiable Markov Channel Pruning (DMCP), to efficiently search the optimal sub-structure. Our method is differentiable and can be directly optimized by gradient descent with respect to standard task loss and budget regularization (e.g. FLOPs constraint). In DMCP, we model the channel pruning as a Markov process, in which each state represents for retaining the corresponding channel during pruning, and transitions between states denote the pruning process. In the end, our method is able to implicitly select the proper number of channels in each layer by the Markov process with optimized transitions. To validate the effectiveness of our method, we perform extensive experiments on Imagenet with ResNet and MobilenetV2. Results show our method can achieve consistent improvement than state-of-the-art pruning methods in various FLOPs settings.

Object recognition techniques using convolutional neural networks (CNN) have achieved great success. However, state-of-the-art object detection methods still perform poorly on large vocabulary and long-tailed datasets, e.g. LVIS. In this work, we analyze this problem from a novel perspective: each positive sample of one category can be seen as a negative sample for other categories, making the tail categories receive more discouraging gradients. Based on it, we propose a simple but effective loss, named equalization loss, to tackle the problem of long-tailed rare categories by simply ignoring those gradients for rare categories. The equalization loss protects the learning of rare categories from being at a disadvantage during the network parameter updating. Thus the model is capable of learning better discriminative features for objects of rare classes. Without any bells and whistles, our method achieves AP gains of 4.1% and 4.8% for the rare and common categories on the challenging LVIS benchmark, compared to the Mask R-CNN baseline. With the utilization of the effective equalization loss, we finally won the 1st place in the LVIS Challenge 2019. Code has been made available at: https://github.com/tztztztztz/eql.detectron2.

This paper proposes a novel object detection framework named Grid R-CNN, which adopts a grid guided localization mechanism for accurate object detection. Different from the traditional regression based methods, the Grid R-CNN captures the spatial information explicitly and enjoys the position sensitive property of fully convolutional architecture. Instead of using only two independent points, we design a multi-point supervision formulation to encode more clues in order to reduce the impact of inaccurate prediction of specific points. To take the full advantage of the correlation of points in a grid, we propose a two-stage information fusion strategy to fuse feature maps of neighbor grid points. The grid guided localization approach is easy to be extended to different state-of-the-art detection frameworks. Grid R-CNN leads to high quality object localization, and experiments demonstrate that it achieves a 4.1% AP gain at IoU=0.8 and a 10.0% AP gain at IoU=0.9 on COCO benchmark compared to Faster R-CNN with Res50 backbone and FPN architecture.

Feature extraction, deformation handling, occlusion handling, and classification are four important components in pedestrian detection. Existing methods learn or design these components either individually or sequentially. The interaction among these components is not yet well explored. This paper proposes that they should be jointly learned in order to maximize their strengths through cooperation. We formulate these four components into a joint deep learning framework and propose a new deep network architecture (Code available on www.ee.cuhk.edu.hk/wlouyang/projects/ouyangWiccv13Joint/index.html). By establishing automatic, mutual interaction among components, the deep model has average miss rate 8.57 percent/11.71 percent on the Caltech benchmark dataset with new/original annotations.

Current CNN based object detectors need initialization from pre-trained ImageNet classification models, which are usually time-consuming. In this paper, we present a fully convolutional feature mimic framework to train very efficient CNN based detectors, which do not need ImageNet pre-training and achieve competitive performance as the large and slow models. We add supervision from high-level features of the large networks in training to help the small network better learn object representation. More specifically, we conduct a mimic method for the features sampled from the entire feature map and use a transform layer to map features from the small network onto the same dimension of the large network. In training the small network, we optimize the similarity between features sampled from the same region on the feature maps of both networks. Extensive experiments are conducted on pedestrian and common object detection tasks using VGG, Inception and ResNet. On both Caltech and Pascal VOC, we show that the modified 2.5× accelerated Inception network achieves competitive performance as the full Inception Network. Our faster model runs at 80 FPS for a 1000×1500 large input with only a minor degradation of performance on Caltech.