Unsupervised domain adaptation (UDA) aims to adapt a model of the labeled source domain to an unlabeled target domain. Although the domain shifts may exist in various dimensions such as appearance, textures, etc, the contextual dependency, which is generally shared across different domains, is neglected by recent methods. In this paper, we utilize this important clue as explicit prior knowledge and propose end-to-end Context-Aware Mixup (CAMix) for domain adaptive semantic segmentation. Firstly, we design a contextual mask generation strategy by leveraging accumulated spatial distributions and contextual relationships. The generated contextual mask is critical in this work and will guide the domain mixup. In addition, we define the significance mask to indicate where the pixels are credible. To alleviate the over-alignment (e.g., early performance degradation), the source and target significance masks are mixed based on the contextual mask into the mixed significance mask, and we introduce a significance-reweighted consistency loss on it. Experimental results show that the proposed method outperforms the state-of-the-art methods by a large margin on two widely-used domain adaptation benchmarks, i.e., GTAV $\rightarrow $ Cityscapes and SYNTHIA $\rightarrow $ Cityscapes.
Domain adaptation aims to bridge the domain shifts between the source and target domains. These shifts may span different dimensions such as fog, rainfall, etc. However, recent methods typically do not consider explicit prior knowledge on a specific dimension, thus leading to less desired adaptation performance. In this paper, we study a practical setting called Specific Domain Adaptation (SDA) that aligns the source and target domains in a demanded-specific dimension. Within this setting, we observe the intra-domain gap induced by different domainness (i.e., numerical magnitudes of this dimension) is crucial when adapting to a specific domain. To address the problem, we propose a novel Self-Adversarial Disentangling (SAD) framework. In particular, given a specific dimension, we first enrich the source domain by introducing a domainness creator with providing additional supervisory signals. Guided by the created domainness, we design a self-adversarial regularizer and two loss functions to jointly disentangle the latent representations into domainness-specific and domainness-invariant features, thus mitigating the intra-domain gap. Our method can be easily taken as a plug-and-play framework and does not introduce any extra costs in the inference time. We achieve consistent improvements over state-of-the-art methods in both object detection and semantic segmentation tasks.
Video Instance Segmentation (VIS) is a new and inherently multi-task problem, which aims to detect, segment and track each instance in a video sequence. Existing approaches are mainly based on single-frame features or single-scale features of multiple frames, where temporal information or multi-scale information is ignored. To incorporate both temporal and scale information, we propose a Temporal Pyramid Routing (TPR) strategy to conditionally align and conduct pixel-level aggregation from a feature pyramid pair of two adjacent frames. Specifically, TPR contains two novel components, including Dynamic Aligned Cell Routing (DACR) and Cross Pyramid Routing (CPR), where DACR is designed for aligning and gating pyramid features across temporal dimension, while CPR transfers temporally aggregated features across scale dimension. Moreover, our approach is a plug-and-play module and can be easily applied to existing instance segmentation methods. Extensive experiments on YouTube-VIS dataset demonstrate the effectiveness and efficiency of the proposed approach on several state-of-the-art instance segmentation methods. Codes and trained models will be publicly available to facilitate future research.(\url{https://github.com/lxtGH/TemporalPyramidRouting}).
Modelling long-range contextual relationships is critical for pixel-wise prediction tasks such as semantic segmentation. However, convolutional neural networks (CNNs) are inherently limited to model such dependencies due to the naive structure in its building modules (\eg, local convolution kernel). While recent global aggregation methods are beneficial for long-range structure information modelling, they would oversmooth and bring noise to the regions containing fine details (\eg,~boundaries and small objects), which are very much cared for the semantic segmentation task. To alleviate this problem, we propose to explore the local context for making the aggregated long-range relationship being distributed more accurately in local regions. In particular, we design a novel local distribution module which models the affinity map between global and local relationship for each pixel adaptively. Integrating existing global aggregation modules, we show that our approach can be modularized as an end-to-end trainable block and easily plugged into existing semantic segmentation networks, giving rise to the \emph{GALD} networks. Despite its simplicity and versatility, our approach allows us to build new state of the art on major semantic segmentation benchmarks including Cityscapes, ADE20K, Pascal Context, Camvid and COCO-stuff. Code and trained models are released at \url{https://github.com/lxtGH/GALD-DGCNet} to foster further research.
We propose a novel method for fine-grained high-quality image segmentation of both objects and scenes. Inspired by dilation and erosion from morphological image processing techniques, we treat the pixel level segmentation problems as squeezing object boundary. From this perspective, we propose \textbf{Boundary Squeeze} module: a novel and efficient module that squeezes the object boundary from both inner and outer directions which leads to precise mask representation. To generate such squeezed representation, we propose a new bidirectionally flow-based warping process and design specific loss signals to supervise the learning process. Boundary Squeeze Module can be easily applied to both instance and semantic segmentation tasks as a plug-and-play module by building on top of existing models. We show that our simple yet effective design can lead to high qualitative results on several different datasets and we also provide several different metrics on boundary to prove the effectiveness over previous work. Moreover, the proposed module is light-weighted and thus has potential for practical usage. Our method yields large gains on COCO, Cityscapes, for both instance and semantic segmentation and outperforms previous state-of-the-art PointRend in both accuracy and speed under the same setting. Code and model will be available.
Recently, DETR and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors. However, their performance on Video Object Detection (VOD) has not been well explored. In this paper, we present TransVOD, an end-to-end video object detection model based on a spatial-temporal Transformer architecture. The goal of this paper is to streamline the pipeline of VOD, effectively removing the need for many hand-crafted components for feature aggregation, e.g., optical flow, recurrent neural networks, relation networks. Besides, benefited from the object query design in DETR, our method does not need complicated post-processing methods such as Seq-NMS or Tubelet rescoring, which keeps the pipeline simple and clean. In particular, we present temporal Transformer to aggregate both the spatial object queries and the feature memories of each frame. Our temporal Transformer consists of three components: Temporal Deformable Transformer Encoder (TDTE) to encode the multiple frame spatial details, Temporal Query Encoder (TQE) to fuse object queries, and Temporal Deformable Transformer Decoder to obtain current frame detection results. These designs boost the strong baseline deformable DETR by a significant margin (3%-4% mAP) on the ImageNet VID dataset. TransVOD yields comparable results performance on the benchmark of ImageNet VID. We hope our TransVOD can provide a new perspective for video object detection. Code will be made publicly available at https://github.com/SJTU-LuHe/TransVOD.
Glass-like objects such as windows, bottles, and mirrors exist widely in the real world. Sensing these objects has many applications, including robot navigation and grasping. However, this task is very challenging due to the arbitrary scenes behind glass-like objects. This paper aims to solve the glass-like object segmentation problem via enhanced boundary learning. In particular, we first propose a novel refined differential module for generating finer boundary cues. Then an edge-aware point-based graph convolution network module is proposed to model the global shape representation along the boundary. Both modules are lightweight and effective, which can be embedded into various segmentation models. Moreover, we use these two modules to design a decoder to get accurate segmentation results, especially on the boundary. Extensive experiments on three recent glass-like object segmentation datasets, including Trans10k, MSD, and GDD, show that our approach establishes new state-of-the-art performances. We also offer the generality and superiority of our approach compared with recent methods on three general segmentation datasets, including Cityscapes, BDD, and COCO Stuff. Code and models will be available at (\url{https://github.com/hehao13/EBLNet})
Aerial Image Segmentation is a particular semantic segmentation problem and has several challenging characteristics that general semantic segmentation does not have. There are two critical issues: The one is an extremely foreground-background imbalanced distribution, and the other is multiple small objects along with the complex background. Such problems make the recent dense affinity context modeling perform poorly even compared with baselines due to over-introduced background context. To handle these problems, we propose a point-wise affinity propagation module based on the Feature Pyramid Network (FPN) framework, named PointFlow. Rather than dense affinity learning, a sparse affinity map is generated upon selected points between the adjacent features, which reduces the noise introduced by the background while keeping efficiency. In particular, we design a dual point matcher to select points from the salient area and object boundaries, respectively. Experimental results on three different aerial segmentation datasets suggest that the proposed method is more effective and efficient than state-of-the-art general semantic segmentation methods. Especially, our methods achieve the best speed and accuracy trade-off on three aerial benchmarks. Further experiments on three general semantic segmentation datasets prove the generality of our method. Code will be provided in (https: //github.com/lxtGH/PFSegNets).
In real applications, different computation-resource devices need different-depth networks (e.g., ResNet-18/34/50) with high-accuracy. Usually, existing strategies either design multiple networks (nets) and train them independently, or utilize compression techniques (e.g., low-rank decomposition, pruning, and teacher-to-student) to evolve a trained large model into a small net. These methods are subject to the low-accuracy of small nets, or complicated training processes induced by the dependence of accompanying assistive large models. In this article, we propose an elegant Depth-level Dynamic Neural Network (DDNN) integrated different-depth sub-nets of similar architectures. Instead of training individual nets with different-depth configurations, we only train a DDNN to dynamically switch different-depth sub-nets at runtime using one set of shared weight parameters. To improve the generalization of sub-nets, we design the Embedded-Knowledge-Distillation (EKD) training mechanism for the DDNN to implement semantic knowledge transfer from the teacher (full) net to multiple sub-nets. Specifically, the Kullback-Leibler divergence is introduced to constrain the posterior class probability consistency between full-net and sub-net, and self-attention on the same resolution feature of different depth is addressed to drive more abundant feature representations of sub-nets. Thus, we can obtain multiple high accuracy sub-nets simultaneously in a DDNN via the online knowledge distillation in each training iteration without extra computation cost. Extensive experiments on CIFAR-10, CIFAR-100, and ImageNet datasets demonstrate that sub-nets in DDNN with EKD training achieves better performance than the depth-level pruning or individually training while preserving the original performance of full-net.
Graph-based convolutional model such as non-local block has shown to be effective for strengthening the context modeling ability in convolutional neural networks (CNNs). However, its pixel-wise computational overhead is prohibitive which renders it unsuitable for high resolution imagery. In this paper, we explore the efficiency of context graph reasoning and propose a novel framework called Squeeze Reasoning. Instead of propagating information on the spatial map, we first learn to squeeze the input feature into a channel-wise global vector and perform reasoning within the single vector where the computation cost can be significantly reduced. Specifically, we build the node graph in the vector where each node represents an abstract semantic concept. The refined feature within the same semantic category results to be consistent, which is thus beneficial for downstream tasks. We show that our approach can be modularized as an end-to-end trained block and can be easily plugged into existing networks. Despite its simplicity and being lightweight, our strategy allows us to establish a new state-of-the-art on semantic segmentation and show significant improvements with respect to strong, state-of-the-art baselines on various other scene understanding tasks including object detection, instance segmentation and panoptic segmentation. Code will be made available to foster any further research